Internal arteriovenous fistula power loss early warning system based on fusion of miniature ultrasound and biological impedance

Abstract

The invention particularly relates to an internal arteriovenous fistula power loss early warning system based on fusion of miniature ultrasound and biological impedance, and relates to the technical field of medical instruments. A data processing module; and an intelligent early warning module. According to the invention, through the integrated design of the miniature ultrasonic probe module and the biological impedance electrode module, the synchronous measurement of the blood flow velocity and the blood vessel volume change is realized; wherein the PMUT array is combined with a three-axis accelerometer to correct the angle of a probe in real time, angle errors caused by operation are avoided, meanwhile, the biological impedance electrode measures the blood vessel volume through alternating current, an impedance diameter model is dynamically updated through AI, the cross sectional area of the blood vessel is calculated, and traditional static calibration is replaced; the problem of insufficient precision of a single mode is solved, more reliable hemodynamic data is provided for clinic, and the abnormal state of the blood vessel is recognized in an early stage.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to an arteriovenous fistula failure warning system based on the fusion of micro-ultrasound and bioimpedance. Background Art

[0002] Arteriovenous fistulas are the lifeline of hemodialysis patients, and early warning of malfunctions (such as stenosis and thrombosis) is crucial for reducing complications. Existing wearable ultrasound monitoring devices suffer from limited single-modality accuracy and short battery life (e.g., CN113576498A, with an error of ±25% and a battery life of less than 8 hours). Ultrasound combined with bioimpedance systems, which rely on dialysis machines, cannot achieve continuous monitoring (e.g., EP3120781B1, which is limited to use during treatment).

[0003] Traditional technologies are unable to meet clinical needs for real-time early warning due to problems such as single modality, non-continuous monitoring and reliance on manual calibration. Summary of the Invention

[0004] The purpose of the present invention is to solve the above problems and to propose an arteriovenous fistula failure warning system based on the fusion of micro-ultrasound and bioimpedance.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: The arteriovenous fistula failure warning system based on the fusion of micro-ultrasound and bioimpedance includes: Multimodal sensing module: This module includes a miniature ultrasound probe module consisting of a piezoelectric micromachined ultrasound transducer array embedded in a flexible substrate and a built-in triaxial accelerometer, and a bioimpedance electrode module with four electrodes symmetrically distributed on both sides of the ultrasound probe, which applies a 50kHz-1MHz alternating current to measure changes in vascular volume. These modules are used to measure blood flow velocity and vascular volume changes, respectively. Data processing module: This module implements Doppler frequency shift extraction, impedance signal demodulation, and AI inference to fuse ultrasound blood flow velocity and bioimpedance vessel diameter to calculate blood flow, and dynamically adjusts the weights of ultrasound and impedance data based on signal quality. Intelligent early warning module: An AI model based on an LSTM network inputs historical flow trends, spectrum width, pulsatility index, and patient baseline data, and outputs risk classification.

[0006] Preferably, the PMUT array of the micro-ultrasound probe module uses beamforming technology to improve the signal-to-noise ratio and resolve the contradiction between miniaturization and acoustic energy attenuation.

[0007] Preferably, the four electrodes of the bioimpedance electrode module and the ultrasound probe are placed on the same plane of the flexible patch to form a multimodal integrated structure.

[0008] Preferably, the local storage unit of the data processing module is a 4GB Flash, which supports Bluetooth 5.0 real-time data transmission and stores monitoring data when the signal is interrupted.

[0009] Preferably, the AI ​​model of the intelligent early warning module is trained based on data from 10,000 cases of arteriovenous fistula failure, and can identify stenosis risk 3 to 5 days in advance in clinical trials.

[0010] Preferably, the thickness of the flexible wearable patch is ≤5 mm and the size is ≤3×3 cm². Non-invasive fixation is achieved through biocompatible adhesive tape, avoiding the reliance on manual positioning of traditional ultrasound probes.

[0011] Preferably, the low-power design of the data processing module includes: the PMUT adopts a low-duty cycle working mode, and AI reasoning is completed on-chip to replace external host calculations, so that the overall power consumption is reduced to less than 1 / 3 of the existing wearable ultrasound patch.

[0012] Preferably, the graded warning mechanism of the intelligent warning module includes: when the blood flow error is ≤±12%, it is normal; when an abnormal trend occurs but does not reach a critical value, a yellow warning is triggered; when the predicted stenosis probability is ≥70%, a red warning is triggered.

[0013] Preferably, the multimodal sensing fusion technology corrects the θ angle in real time through an accelerometer and dynamically updates the impedance combined with the diameter model in combination with AI, thereby solving the defects of large angle error and static calibration in the existing technology and realizing continuous monitoring between dialysis sessions.

[0014] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. This invention achieves the synchronous measurement of blood flow velocity and vascular volume changes through the integrated design of a miniature ultrasound probe module and a bioimpedance electrode module. The PMUT array, combined with a three-axis accelerometer, corrects the probe angle in real time to avoid angle errors caused by operation. Simultaneously, the bioimpedance electrode measures vascular volume using alternating current, and the impedance diameter model dynamically updated by AI calculates the vascular cross-sectional area, replacing traditional static calibration. This solves the problem of insufficient accuracy of a single modality, provides more reliable hemodynamic data for clinical use, and enables early identification of vascular abnormalities.

[0015] 2. The present invention adopts a layered structure through a flexible patch, which is non-invasively fixed by silicone gel, adapts to the skin and does not require manual positioning; the low-power design reduces power consumption to less than 1 / 3 of existing devices through the PMUT low-duty cycle working mode and on-chip AI reasoning, covering the high-risk period between dialysis sessions; it realizes automatic measurement every 5 minutes, continuously captures blood flow trends, and cooperates with the AI ​​model to warn of stenosis risks 3 to 5 days in advance, significantly improving the timeliness of monitoring and the initiative of clinical intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 Flowchart of the present invention. DETAILED DESCRIPTION

[0017] Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and for many different purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the present application comprehensive and complete and to fully convey the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0018] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless expressly defined as such herein.

[0019] See also Figure 1 As shown, the present invention provides a technical solution: The arteriovenous fistula failure warning system based on the fusion of micro-ultrasound and bioimpedance includes: Multimodal sensing module: This module includes a miniature ultrasound probe module consisting of a piezoelectric micromachined ultrasound transducer array embedded in a flexible substrate and a built-in triaxial accelerometer, and a bioimpedance electrode module with four electrodes symmetrically distributed on both sides of the ultrasound probe, which applies a 50kHz-1MHz alternating current to measure changes in vascular volume. These modules are used to measure blood flow velocity and vascular volume changes, respectively. Multimodal sensor fusion technology uses an accelerometer to correct the θ angle in real time and combines AI to dynamically update the impedance and diameter model, solving the defects of large angle errors and static calibration in existing technologies and achieving continuous monitoring between dialysis sessions. The PMUT array of the miniature ultrasound probe module uses beamforming technology to improve the signal-to-noise ratio and resolve the contradiction between miniaturization and acoustic energy attenuation; Data processing module: This module implements Doppler frequency shift extraction, impedance signal demodulation, and AI inference to fuse ultrasound blood flow velocity and bioimpedance vessel diameter to calculate blood flow, and dynamically adjusts the weights of ultrasound and impedance data based on signal quality. The local storage unit is 4GB Flash, which supports Bluetooth 5.0 real-time data transmission and stores monitoring data when the signal is interrupted; Low-power design includes: PMUT adopts low duty cycle operation mode, AI reasoning is completed on-chip to replace external host calculations, reducing overall power consumption to less than 1 / 3 of existing wearable ultrasound patches Intelligent Early Warning Module: An AI model based on an LSTM network inputs historical flow trends, spectral width, pulsatility index, and patient baseline data to output a risk classification. This tiered early warning mechanism includes: normal blood flow error ≤±12%; yellow alert triggered when an abnormal trend appears but does not reach a critical value; and red alert triggered when the predicted probability of stenosis is ≥70%. The AI ​​model, trained on data from 10,000 cases of arteriovenous fistula failure, can identify stenosis risk 3-5 days in advance in clinical trials, with a sensitivity of ≥92% and a specificity of ≥88%. The AI ​​model was trained based on data from 10,000 cases of arteriovenous fistula failure and, in clinical trials, was able to identify stenosis risk 3 to 5 days in advance. The four electrodes of the bioimpedance electrode module and the ultrasound probe are placed on the same plane of the flexible patch to form a multimodal integrated structure; The hardware structure includes: Flexible wearable patches: Layered structure: From the outside to the inside, it consists of a waterproof and breathable layer (medical polyurethane film), an ultrasound probe combined with an impedance electrode layer, a flexible circuit layer (silver nanowire printing, with 200% increased flexibility), and a biocompatible adhesive layer (silicone gel). Physical characteristics: Thickness ≤ 5mm, size ≤ 3×3cm², single-charge life of 72 hours, support for Qi standard wireless charging; non-invasive fixation through biocompatible adhesive, eliminating the reliance on manual positioning of traditional ultrasound probes; The four electrodes of the bioimpedance electrode module and the ultrasound probe are placed on the same plane as the flexible patch, forming an integrated multimodal structure, which is different from the discrete design of the existing technology; The flexible wearable patch has a thickness of ≤5mm and a size of ≤3×3cm². It is non-invasively fixed through a biocompatible adhesive patch, avoiding the reliance on manual positioning of traditional ultrasound probes.

[0020] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The influencing weight factors and specific coefficient values ​​in the formula are set by technical personnel in this field according to actual conditions, and can be adjusted and modified later.

[0021] The above description of the embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An arteriovenous fistula failure warning system based on the fusion of micro-ultrasound and bioimpedance, characterized by: include: Multimodal sensing module: This module includes a miniature ultrasound probe module consisting of a piezoelectric micromachined ultrasound transducer array embedded in a flexible substrate and a built-in triaxial accelerometer, and a bioimpedance electrode module with four electrodes symmetrically distributed on both sides of the ultrasound probe, which applies a 50kHz-1MHz alternating current to measure changes in vascular volume. These modules are used to measure blood flow velocity and vascular volume changes, respectively. Data processing module: This module implements Doppler frequency shift extraction, impedance signal demodulation, and AI inference to fuse ultrasound blood flow velocity and bioimpedance vessel diameter to calculate blood flow, and dynamically adjusts the weights of ultrasound and impedance data based on signal quality. Intelligent early warning module: An AI model based on an LSTM network inputs historical flow trends, spectrum width, pulsatility index, and patient baseline data, and outputs risk classification.

2. The arteriovenous fistula failure warning system based on fusion of micro-ultrasound and bioimpedance according to claim 1 is characterized in that: The PMUT array of the micro-ultrasound probe module adopts beamforming technology to improve the signal-to-noise ratio and resolve the contradiction between miniaturization and acoustic energy attenuation.

3. The arteriovenous fistula failure warning system based on fusion of micro-ultrasound and bioimpedance according to claim 1 is characterized in that: The four electrodes of the bioimpedance electrode module and the ultrasound probe are placed on the same plane of the flexible patch to form a multimodal integrated structure.

4. The arteriovenous fistula failure warning system based on fusion of micro-ultrasound and bioimpedance according to claim 1 is characterized in that: The local storage unit of the data processing module is 4GB Flash, which supports Bluetooth 5.0 real-time data transmission and stores monitoring data when the signal is interrupted.

5. The arteriovenous fistula failure warning system based on fusion of micro-ultrasound and bioimpedance according to claim 1 is characterized in that: The AI ​​model of the intelligent early warning module is trained based on data from 10,000 cases of arteriovenous fistula failure, and in clinical trials it can identify stenosis risk 3 to 5 days in advance.

6. The arteriovenous fistula failure warning system based on fusion of micro-ultrasound and bioimpedance according to claim 1 is characterized in that: The flexible wearable patch has a thickness of ≤5 mm and a size of ≤3×3 cm². It is non-invasively fixed using a biocompatible adhesive patch, avoiding the reliance on manual positioning of traditional ultrasound probes.

7. The arteriovenous fistula failure warning system based on fusion of micro-ultrasound and bioimpedance according to claim 1 is characterized in that: The low-power design of the data processing module includes: the PMUT adopts a low-duty cycle operating mode, and AI reasoning is completed on-chip to replace external host calculations, reducing the overall power consumption to less than 1 / 3 of existing wearable ultrasound patches.

8. The arteriovenous fistula failure warning system based on fusion of micro-ultrasound and bioimpedance according to claim 1 is characterized in that: The hierarchical warning mechanism of the intelligent warning module includes: when the blood flow error is ≤±12%, it is normal; when an abnormal trend appears but does not reach a critical value, a yellow warning is triggered; when the predicted probability of stenosis is ≥70%, a red warning is triggered.

9. The arteriovenous fistula failure warning system based on fusion of micro-ultrasound and bioimpedance according to claim 1 is characterized in that: The multimodal sensing fusion technology uses an accelerometer to correct the θ angle in real time and combines AI to dynamically update the impedance and diameter model, thereby solving the defects of large angle errors and static calibration in the existing technology and realizing continuous monitoring between dialysis sessions.

Images