Mobile detection terminal and detection method for artery blood vessels of nursing personnel

Abstract

The invention relates to a nursing personnel artery blood vessel mobile detection terminal and a detection method, and provides an intelligent artery blood vessel mobile detection terminal which can be worn on the wrist of a nurse to carry out mobile nursing detection on the blood vessel of a patient and can analyze and generate an X-Y curve function image related to the blood vessel tremor frequency and the tremor intensity. Visual monitoring of tremor fluctuation data of artery blood vessels is facilitated, and nurses can analyze symptoms conveniently. The system can perform abnormal analysis of tremor frequency and tremor intensity in combination with a background, analyzes and judges whether the tremor conversion of the artery blood vessel of the patient is abnormal or not through a big data technology, gives a corresponding abnormal recognition supervision conclusion and a clinical pre-diagnosis nursing strategy corresponding to the abnormality, and can issue the abnormal recognition supervision conclusion and the clinical pre-diagnosis nursing strategy to a strategy intelligent terminal for display. A nurse is guided to clinically nurse the artery blood vessel of the patient in advance, the clinical applicability of terminal equipment is improved, and the nursing quality of the abnormal blood vessel of the patient is enhanced.

Description

Technical Field

[0001] The present disclosure relates to the technical field of clinical monitoring equipment, and in particular to a nursing staff arterial blood vessel movement detection terminal, detection method and electronic equipment. Background Art

[0002] Clinical monitoring of the frequency and intensity of arterial tremor is of great significance, mainly in the early detection and assessment of cardiovascular disease. Tremor is one of the characteristic signs of organic cardiovascular disease. It is usually caused by turbulence when blood flows through narrow valve openings or abnormal channels to wider areas, resulting in vibration of valves, heart walls or blood vessel walls. The frequency and intensity of this tremor can reflect the hemodynamic state and abnormalities of the heart or blood vessel structure.

[0003] Therefore, clinical monitoring of the frequency and intensity of arterial tremor is of great significance for the early detection and assessment of cardiovascular disease.

[0004] The existing monitoring methods mainly include physical inspection, instrument monitoring and the use of new monitoring equipment, but they also have corresponding application defects:

[0005] 1. Physical examination mainly uses the doctor's palpation to perceive the tremor of the arterial blood vessels. For example, in heart palpation, the doctor will use the palm or fingertips to palpate the heart valve area to feel the presence of tremor and judge its frequency and intensity. This method is simple and easy, but it depends on the doctor's experience and subjective judgment. This method requires rich clinical experience and professional knowledge, has a high skill and professional entry threshold, and is difficult.

[0006] 2. Instrument monitoring uses special equipment to objectively evaluate arterial tremor. Doppler ultrasound is a commonly used non-invasive monitoring method that can display blood flow velocity and direction in real time, thereby indirectly reflecting the condition of vascular tremor. Magnetic resonance vascular examination can provide more detailed information on vascular structure and hemodynamics, which helps to detect lesions such as vascular stenosis and aneurysms. Doppler ultrasound equipment is generally performed in a color ultrasound room. The equipment is expensive, the cost is high, and it is fixed for use and cannot be moved for detection.

[0007] 3. Arteriovenous tremor monitoring devices such as wristbands can monitor the frequency and intensity of vascular tremors in real time through vibration sensors, and display the monitoring information in digital form, which improves the accuracy and objectivity of monitoring. Currently, wristbands can display the frequency and intensity of vascular tremors, but they are all numerical data, which is not convenient for intuitive monitoring of abnormal information.

[0008] 4. The above method cannot provide a symptom prediction and prompt scheme for abnormal signals when detecting arterial blood vessels, and can only perform simple signal monitoring, which has low clinical applicability. Summary of the invention

[0009] To solve the above problems:

[0010] In one aspect, the present application provides a nursing staff arterial blood vessel mobile detection terminal, including a mobile carrier, on which is integrated:

[0011] Ultrasound module, used to collect raw signal data of arterial blood vessels and feed it back to MCU;

[0012] MCU, used to control the ultrasound module to sample according to a preset sampling frequency, pre-process the raw signal data, separate the arterial vascular tremor audio signal, and perform spectrum analysis on the arterial vascular tremor audio signal based on a frequency domain analysis algorithm, extract the corresponding tremor frequency and tremor intensity therein, and send them to the FPGA;

[0013] FPGA, used for receiving the tremor frequency and the tremor intensity in real time, and inputting the tremor frequency and the tremor intensity into a preset X function and a Y function respectively, and fitting and generating an XY curve function corresponding to the tremor frequency and the tremor intensity;

[0014] The wireless module is used to upload the tremor frequency and the tremor intensity to the nurse station backend, and after the nurse station backend performs big data analysis, the corresponding arterial vascular pre-diagnosis nursing strategy is fed back and sent to the wireless module, and the wireless module is forwarded to the MCU, and then sent to the electronic screen after being parsed and processed by the MCU;

[0015] An electronic screen, used for reading the XY curve function of the tremor frequency and the tremor intensity and displaying the XY curve function image of the tremor frequency and the tremor intensity in an XY coordinate system; and / or reading and displaying the arterial vascular pre-diagnosis care strategy;

[0016] A control panel for inputting control parameters;

[0017] Power supply, used for power supply;

[0018] The ultrasound module, FPGA, wireless module, electronic screen, control panel and power supply are electrically connected to the MCU respectively.

[0019] Preferably, the mobile carrier is a bracelet or a wristband.

[0020] Preferably, the calculation method of the tremor intensity is:

[0021] Collecting a plurality of original signal values ​​sampled at each of the tremor frequencies and performing spectrum analysis to obtain a plurality of corresponding tremor intensity values;

[0022] The maximum and minimum values ​​among several tremor intensity values ​​are removed, and the average of the remaining tremor intensity values ​​is calculated to produce the tremor intensity collected at the current tremor frequency.

[0023] On the other hand, the present application proposes a detection method of a nursing staff arterial blood vessel movement detection terminal, comprising the following steps:

[0024] Activate the nursing staff's arterial blood vessel mobile detection terminal, establish a communication link with the nurse station background, and bind the terminal number and medical staff information on the nurse station background;

[0025] Sending a sampling instruction to the nursing staff's arterial blood vessel mobile detection terminal through the nurse station background;

[0026] The nursing staff arterial blood vessel movement detection terminal receives and responds:

[0027] The wireless module receives and forwards the sampling instruction to the MCU;

[0028] The MCU controls the ultrasonic module to sample according to the preset sampling frequency, collects the original signal data of the arterial blood vessels, pre-processes the original signal data, separates the arterial blood vessel tremor audio signal, and performs spectrum analysis on the arterial blood vessel tremor audio signal based on the frequency domain analysis algorithm, extracts the corresponding tremor frequency and tremor intensity and sends them to the FPGA; at the same time, the tremor frequency and the tremor intensity are reported to the nurse station backstage through the wireless module;

[0029] The FPGA receives the tremor frequency and the tremor intensity in real time, and inputs the tremor frequency and the tremor intensity into a preset X function and a preset Y function, respectively, to generate an XY curve function corresponding to the tremor frequency and the tremor intensity by fitting;

[0030] The MCU forwards the XY curve function of the tremor frequency and the tremor intensity to the electronic screen, and the electronic screen reads the XY curve function of the tremor frequency and the tremor intensity and displays the XY curve function image of the tremor frequency and the tremor intensity in an XY coordinate system;

[0031] After receiving the tremor frequency and the tremor intensity, the nurse station backend writes them into the patient's electronic medical record, performs big data analysis on the tremor frequency and the tremor intensity, predicts and feeds back the corresponding arterial vascular pre-diagnosis nursing strategy and sends it to the wireless module, which is then forwarded to the MCU and sent to the electronic screen after being parsed and processed by the MCU;

[0032] The electronic screen reads and displays the arterial vascular pre-diagnosis care strategy.

[0033] Preferably, a big data analysis is performed on the tremor frequency and the tremor intensity to predict and provide feedback on the corresponding arterial vascular pre-diagnosis nursing strategy, including:

[0034] Based on the historical data set of arterial tremor diagnosis, an arterial pre-diagnosis analysis AI model is trained and constructed and deployed on the backend of the nurse station;

[0035] The nurse station backend inputs the patient's tremor frequency and tremor intensity into the arterial vascular pre-diagnosis analysis AI model, and the arterial vascular pre-diagnosis analysis AI model identifies the characteristic values ​​of the tremor frequency and the tremor intensity, and outputs the arterial vascular pre-diagnosis nursing strategy that matches the characteristic values ​​of the tremor frequency and the tremor intensity;

[0036] The arterial vascular pre-diagnosis care strategy is written into the patient's electronic medical record.

[0037] Preferably, the method for generating the arterial vascular pre-diagnosis analysis AI model comprises:

[0038] The arterial tremor diagnosis history data of several patients are collected and preprocessed to construct the arterial tremor diagnosis history data set, wherein the arterial tremor diagnosis history data includes:

[0039] The patient's vascular ultrasound images, vascular tremor data, vascular abnormality symptom information, and corresponding nursing strategy information prescribed by medical staff based on the vascular ultrasound images, vascular tremor data, and / or vascular abnormality symptom information;

[0040] Perform feature engineering to extract relevant features related to vascular abnormalities in the arterial vascular tremor diagnosis history data of each patient: image spectrum image features related to vascular abnormalities, feature values ​​in the vascular tremor data and / or vascular abnormality symptom feature keywords;

[0041] Performing feature annotation on the associated features of vascular abnormalities in the arterial vascular fibrillation diagnosis history data of each patient, wherein the annotation information includes: nursing strategy information corresponding to the associated features;

[0042] The annotated associated features are combined into a feature set, and the feature set is divided into a training set and a validation set according to a preset ratio;

[0043] Input the training set into a preset random deep forest model to perform feature training and learning, thereby generating a method for generating the arterial vascular pre-diagnosis analysis AI model;

[0044] The recognition performance of the generation method of the arterial vascular pre-diagnosis analysis AI model was verified using a validation set:

[0045] If the verification is passed, the method for generating the arterial vascular pre-diagnosis analysis AI model is deployed in the background of the nurse station;

[0046] On the contrary, the above steps are repeated to reconstruct the generation method of the arterial vascular pre-diagnosis analysis AI model.

[0047] In another aspect, the present application further provides an electronic device, comprising:

[0048] processor;

[0049] a memory for storing processor-executable instructions;

[0050] Wherein, the processor is configured to implement the detection method when executing the executable instructions.

[0051] Technical effects of the present invention:

[0052] The present invention provides an intelligent arterial blood vessel mobile detection terminal, which can be worn on the wrist of a nurse to perform mobile nursing detection on the patient's blood vessels, and can analyze and generate XY curve function images of the tremor frequency and tremor intensity of the blood vessels, so as to facilitate visual monitoring of the tremor fluctuation data of the arterial blood vessels and facilitate nursing staff to analyze symptoms. In addition, the present invention can combine the background to perform abnormal analysis of the tremor frequency and tremor intensity, analyze and judge whether the patient's arterial blood vessel tremor conversion is abnormal through big data technology, and give corresponding abnormal identification supervision conclusions and corresponding abnormal clinical pre-diagnosis nursing strategies, and can issue strategies for intelligent terminal display, guide nurses to perform pre-clinical nursing on the patient's arterial blood vessels, improve the clinical applicability of the terminal equipment, and enhance the nursing quality of the patient's abnormal blood vessels.

[0053] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0055] Figure 1 It is a schematic diagram showing the integrated structure of the detection terminal of the present invention;

[0056] Figure 2 It is shown as a schematic diagram of the background system structure of the present invention;

[0057] Figure 3 The figure shows a training process diagram of the AI ​​model of the present invention;

[0058] Figure 4 It is a schematic diagram showing the application of the electronic device of the present invention. DETAILED DESCRIPTION

[0059] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0060] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0061] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0062] Example 1

[0063] The present invention provides an intelligent arterial blood vessel mobile detection terminal, which can be worn on the wrist of a nurse to perform mobile nursing detection on the patient's blood vessels, and can analyze and generate XY curve function images of the tremor frequency and tremor intensity of the blood vessels, so as to facilitate visual monitoring of the tremor fluctuation data of the arterial blood vessels and facilitate nursing staff to analyze symptoms. In addition, the present invention can combine the background to perform abnormal analysis of the tremor frequency and tremor intensity, analyze and judge whether the patient's arterial blood vessel tremor conversion is abnormal through big data technology, and give corresponding abnormal identification supervision conclusions and corresponding abnormal clinical pre-diagnosis nursing strategies, and can issue strategies for intelligent terminal display, guide nurses to perform pre-clinical nursing on the patient's arterial blood vessels, improve the clinical applicability of the terminal equipment, and enhance the nursing quality of the patient's abnormal blood vessels.

[0064] The terminal carrier (mobile carrier) of the present invention is preferably a bracelet or wristband. For the specific carrier structure and application scheme used for integration, please refer to the bracelet or wristband structure worn by nurses in existing hospitals.

[0065] The control surface (including MCU chip), power supply, and wireless module (such as Bluetooth module and its wireless communication mode with the background) in the smart bracelet or smart wristband can be understood in combination with the existing technology and will not be described in detail in this embodiment.

[0066] Each integrated electronic hardware facility of the present invention can be automatically configured by the user or by the manufacturer according to parameters and rules. This embodiment is not limited. For example, the MCU chip uses STM32F103C8T6, and the FPGA uses SPARTAN, ART IX, KINTEX and VI RTEX models.

[0067] like Figure 1 As shown, in one aspect, the present application proposes a nursing staff arterial blood vessel mobile detection terminal (hereinafter referred to as terminal), including a mobile carrier, on which is integrated:

[0068] Ultrasound module, used to collect raw signal data of arterial blood vessels and feed it back to MCU;

[0069] MCU, used to control the ultrasound module to sample according to a preset sampling frequency, pre-process the raw signal data, separate the arterial vascular tremor audio signal, and perform spectrum analysis on the arterial vascular tremor audio signal based on a frequency domain analysis algorithm, extract the corresponding tremor frequency and tremor intensity therein, and send them to the FPGA;

[0070] FPGA, used for receiving the tremor frequency and the tremor intensity in real time, and inputting the tremor frequency and the tremor intensity into a preset X function and a Y function respectively, and fitting and generating an XY curve function corresponding to the tremor frequency and the tremor intensity;

[0071] The wireless module is used to upload the tremor frequency and the tremor intensity to the nurse station backend, and after the nurse station backend performs big data analysis, the corresponding arterial vascular pre-diagnosis nursing strategy is fed back and sent to the wireless module, and the wireless module is forwarded to the MCU, and then sent to the electronic screen after being parsed and processed by the MCU;

[0072] An electronic screen, used for reading the XY curve function of the tremor frequency and the tremor intensity and displaying the XY curve function image of the tremor frequency and the tremor intensity in an XY coordinate system; and / or reading and displaying the arterial vascular pre-diagnosis care strategy;

[0073] A control panel for inputting control parameters;

[0074] Power supply, used for power supply;

[0075] The ultrasound module, FPGA, wireless module, electronic screen, control panel and power supply are electrically connected to the MCU respectively.

[0076] During the specific operation, the administrator can first input the control parameters through the control panel, including the correction algorithm for tremor frequency and tremor intensity, various coefficients, etc. The nurse activates the terminal through the panel control and starts working.

[0077] Please refer to the following description for the functions, interfaces and interactions of each component:

[0078] 1. Ultrasonic module

[0079] Function: Collect raw signal data of arterial blood vessels.

[0080] Interface: Provides raw signal data output interface to MCU.

[0081] Implementation: Use high-performance ultrasonic sensors to ensure the collected signals are of high quality and low noise.

[0082] 2. MCU (Microcontroller)

[0083] Function:

[0084] Control the ultrasonic module to perform sampling according to the preset sampling frequency.

[0085] The original signal data is preprocessed to separate the arterial blood vessel tremor audio signal.

[0086] The frequency spectrum of the arterial tremor audio signal is analyzed based on the frequency domain analysis algorithm to extract the tremor frequency and tremor intensity.

[0087] The original signal data is preprocessed to separate the arterial blood vessel tremor audio signal, and the signal is subjected to spectrum analysis based on the frequency domain analysis algorithm to extract the tremor frequency and tremor intensity, according to the following steps:

[0088] 1. Raw signal data preprocessing

[0089] Target:

[0090] The arterial tremor audio signal is separated from the original signal.

[0091] step:

[0092] Signal filtering:

[0093] Use a bandpass filter to remove noise and unwanted frequency components from the original signal. Arterial vascular vibrations are usually located in a specific frequency range, so these frequency components can be retained by setting the passband range of the filter.

[0094] Signal Enhancement:

[0095] If the tremor signal is weak, signal enhancement techniques (such as amplification, adaptive filtering, etc.) can be used to improve the quality of the signal.

[0096] Window function processing:

[0097] Apply window functions (such as Hamming window, Hanning window, etc.) to the signal to reduce spectrum leakage and aliasing and improve the accuracy of spectrum analysis.

[0098] 2. Spectrum Analysis

[0099] Target:

[0100] Extracting tremor frequency and tremor intensity from arterial vascular tremor audio signals.

[0101] step:

[0102] Fast Fourier Transform (FFT):

[0103] Perform FFT transformation on the preprocessed signal to convert the time domain signal into a frequency domain signal. FFT is one of the most commonly used methods in spectrum analysis and can efficiently calculate the spectrum of the signal.

[0104] Spectrum peak detection:

[0105] Peaks are detected in the spectrum, which correspond to the main frequency components of arterial vascular tremor. These peaks can be identified by setting thresholds or using other peak detection techniques.

[0106] Tremor frequency extraction:

[0107] According to the position of the spectrum peak, the main frequency of the tremor is determined. This frequency is the frequency of arterial vascular tremor.

[0108] Tremor intensity calculation:

[0109] The intensity of the tremor can be obtained by calculating the size of the spectrum peak (i.e., amplitude) or the energy near the peak. This reflects the strength or energy level of the tremor signal.

[0110] 3. Implementation considerations

[0111] Algorithm selection: Select appropriate filtering algorithm, window function and spectrum analysis method according to the signal characteristics and processing requirements.

[0112] Parameter setting: The filter parameters (such as passband range), number of FFT points, peak detection threshold, etc. need to be set and adjusted according to the specific situation.

[0113] Real-time requirements: If real-time signals are being processed, the complexity and processing speed of the algorithm need to be considered to ensure that real-time requirements are met.

[0114] Hardware implementation: When implementing the above algorithm on an MCU or FPGA, it is necessary to consider the limitations of hardware resources and the feasibility of the algorithm. It may be necessary to use hardware acceleration technology (such as DSP, ASIC, etc.) to increase the processing speed.

[0115] 4. Example process (assuming implementation on MCU)

[0116] Initialization: Configure the MCU's ADC (analog-to-digital converter) to acquire raw signal data and set necessary filter and FFT parameters.

[0117] Data acquisition: Continuously collect raw signal data through ADC.

[0118] Signal preprocessing: Perform preprocessing operations such as filtering and window function processing on the collected data.

[0119] Spectrum analysis: Perform FFT transformation on the preprocessed signal to obtain a spectrum diagram.

[0120] Peak detection and extraction: Detect peaks in the spectrogram and extract tremor frequency and tremor intensity.

[0121] Result output: The extracted tremor frequency and tremor intensity are sent to other devices through the communication interface of the MCU (such as UART, SPI, etc.) or for subsequent processing.

[0122] Through the above steps, the preprocessing and spectrum analysis of the original signal data can be realized, thereby extracting the frequency and intensity information of arterial vascular tremor. This information has important reference value for the subsequent diagnosis and treatment of arterial vascular diseases.

[0123] Send the tremor frequency and tremor intensity to the FPGA.

[0124] Receive XY curve function data generated by FPGA.

[0125] Receive the arterial vascular pre-diagnosis and care strategy issued by the wireless module and send it to the electronic screen.

[0126] interface:

[0127] Connect to the ultrasound module to receive raw signal data.

[0128] Connects to FPGA, sends vibration frequency and vibration intensity, and optionally receives XY curve function data.

[0129] Connect to the wireless module to receive and send data.

[0130] Connect to the electronic screen and send display data.

[0131] Implementation: Choose an MCU with powerful processing capabilities and rich peripheral interfaces.

[0132] 3. FPGA (Field Programmable Gate Array)

[0133] Function:

[0134] Receive the vibration frequency and vibration intensity sent by MCU in real time.

[0135] The tremor frequency and tremor intensity are input into the preset X function and Y function to generate an XY curve function. The program is pre-edited by the user and burned into the core program.

[0136] Send XY curve function data back to MCU.

[0137] interface:

[0138] Connect to MCU, receive vibration frequency and vibration intensity, and optionally send XY curve function data.

[0139] Implementation: Use high-performance FPGA to ensure real-time processing capability and accuracy of function fitting.

[0140] 4. Wireless module

[0141] Function:

[0142] The tremor frequency and tremor intensity sent by the MCU are uploaded to the nurse station backend.

[0143] Receive the arterial vascular pre-diagnosis nursing strategy feedback from the nursing station background and send it to the MCU.

[0144] interface:

[0145] Connect with MCU to receive and send data.

[0146] Connect to the nurse station backend via wireless network.

[0147] Implementation: Select a stable and reliable wireless communication module to ensure the timeliness and accuracy of data transmission.

[0148] 5. Electronic screen

[0149] Function:

[0150] Read and display the XY curve function image of the vibration frequency and vibration intensity sent by MCU.

[0151] Read and display the arterial vascular pre-diagnosis care strategy sent by MCU.

[0152] interface:

[0153] Connect to MCU and receive display data.

[0154] Implementation: Choose a high-resolution, color-rich display to ensure crisp, clear viewing.

[0155] 6. Control Panel

[0156] Function: Input control parameters such as sampling frequency, display settings, etc.

[0157] Interface: connect with MCU and send control parameters.

[0158] Implementation: Design a simple and easy-to-use control panel to ensure that users can easily set parameters.

[0159] Preferably, the calculation method of the tremor intensity is:

[0160] Collecting a plurality of original signal values ​​sampled at each of the tremor frequencies and performing spectrum analysis to obtain a plurality of corresponding tremor intensity values;

[0161] The maximum and minimum values ​​among several tremor intensity values ​​are removed, and the average of the remaining tremor intensity values ​​is calculated to produce the tremor intensity collected at the current tremor frequency.

[0162] Please refer to Example 2 for understanding the interaction between the terminal and the background.

[0163] In order to refine and implement your proposed solution, that is, to collect several original signal values ​​sampled at each tremor frequency, perform spectrum analysis to obtain several corresponding tremor intensity values, then remove the maximum and minimum values ​​of these tremor intensity values, and calculate the average of the remaining tremor intensity values ​​to obtain the tremor intensity at the current tremor frequency, follow the detailed steps below:

[0164] 1. Data collection and preprocessing

[0165] Target:

[0166] Collect the raw signal values ​​at each tremor frequency.

[0167] step:

[0168] Set the sampling parameters:

[0169] The sampling frequency is determined to ensure that the frequency range of arterial vascular tremors can be accurately captured.

[0170] The number of sampling points is set to ensure that there are enough raw signal values ​​at each tremor frequency for subsequent analysis.

[0171] Data collection:

[0172] Use an ultrasound module or other sensors to continuously collect raw signal data of arterial blood vessels according to set sampling parameters.

[0173] The original signal data is classified and stored according to the vibration frequency.

[0174] 2. Spectral analysis and tremor intensity extraction

[0175] Target:

[0176] Perform spectrum analysis on the original signal value at each tremor frequency to obtain the corresponding tremor intensity value.

[0177] step:

[0178] Spectrum Analysis:

[0179] Apply fast Fourier transform (FFT) or other spectrum analysis methods to the raw signal values ​​at each tremor frequency to convert the time domain signal into a frequency domain signal.

[0180] Peaks corresponding to the tremor frequencies are identified in the spectrogram; these peaks reflect the intensity of the tremor.

[0181] Tremor intensity extraction:

[0182] The size of each peak (i.e., amplitude) is measured or the energy near the peak is calculated as the tremor intensity value at the tremor frequency.

[0183] For each tremor frequency, the above process is repeated to obtain several tremor intensity values.

[0184] 3. Calculation of mean tremor intensity

[0185] Target:

[0186] Outliers were removed and the mean tremor intensity was calculated for each tremor frequency.

[0187] step:

[0188] Remove outliers:

[0189] For each set of tremor intensity values ​​at each tremor frequency, remove the maximum and minimum values. This is to remove outliers that may be caused by noise, interference or sampling errors.

[0190] Mean calculation:

[0191] The remaining tremor intensity values ​​are averaged to obtain the tremor intensity at the current tremor frequency.

[0192] The arithmetic mean, median, or other statistics can be used as representative values ​​for tremor intensity, depending on the distribution characteristics of the data and the needs of the analysis.

[0193] 4. Result output and storage

[0194] Target:

[0195] The tremor intensity value at each tremor frequency is output and stored.

[0196] step:

[0197] Result output:

[0198] The calculated tremor frequency and the corresponding tremor intensity value are sent to other devices, such as FPGA, electronic screen or nurse station background, through the communication interface of the MCU (such as UART, SPI, etc.).

[0199] The relationship graph of tremor frequency-tremor intensity can be displayed on an electronic screen, or used as basic data for subsequent analysis.

[0200] Data Storage:

[0201] The data such as tremor frequency, original tremor intensity value, tremor intensity value after removing abnormal values ​​and calculated mean tremor intensity are stored in the memory of MCU or uploaded to the cloud database for long-term storage and subsequent analysis.

[0202] Through the above detailed steps, the tremor intensity at each tremor frequency can be accurately collected, analyzed and calculated, providing strong data support for the diagnosis and treatment of arterial vascular diseases.

[0203] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0204] Example 2

[0205] like Figure 2 As shown, based on the implementation principle of Example 1, the present application, on the other hand, proposes a detection method of a nursing staff arterial blood vessel movement detection terminal, comprising the following steps:

[0206] Activate the nursing staff's arterial blood vessel mobile detection terminal, establish a communication link with the nurse station background, and bind the terminal number and medical staff information on the nurse station background;

[0207] Sending a sampling instruction to the nursing staff's arterial blood vessel mobile detection terminal through the nurse station background;

[0208] The nursing staff arterial blood vessel movement detection terminal receives and responds:

[0209] The wireless module receives and forwards the sampling instruction to the MCU;

[0210] The MCU controls the ultrasonic module to sample according to the preset sampling frequency, collects the original signal data of the arterial blood vessels, pre-processes the original signal data, separates the arterial blood vessel tremor audio signal, and performs spectrum analysis on the arterial blood vessel tremor audio signal based on the frequency domain analysis algorithm, extracts the corresponding tremor frequency and tremor intensity and sends them to the FPGA; at the same time, the tremor frequency and the tremor intensity are reported to the nurse station backstage through the wireless module;

[0211] The FPGA receives the tremor frequency and the tremor intensity in real time, and inputs the tremor frequency and the tremor intensity into a preset X function and a preset Y function, respectively, to generate an XY curve function corresponding to the tremor frequency and the tremor intensity by fitting;

[0212] The MCU forwards the XY curve function of the tremor frequency and the tremor intensity to the electronic screen, and the electronic screen reads the XY curve function of the tremor frequency and the tremor intensity and displays the XY curve function image of the tremor frequency and the tremor intensity in an XY coordinate system;

[0213] After receiving the tremor frequency and the tremor intensity, the nurse station backend writes them into the patient's electronic medical record, performs big data analysis on the tremor frequency and the tremor intensity, predicts and feeds back the corresponding arterial vascular pre-diagnosis nursing strategy and sends it to the wireless module, which is then forwarded to the MCU and sent to the electronic screen after being parsed and processed by the MCU;

[0214] The electronic screen reads and displays the arterial vascular pre-diagnosis care strategy.

[0215] Please understand the above interaction in conjunction with Example 1.

[0216] This embodiment mainly describes and implements the background intelligent prognostic analysis model and its application.

[0217] Combined with Figure 2As shown, the corresponding application system is deployed in the background. The background database is mainly used for background data storage; the data acquisition system is used for data acquisition, including the sending of some data, etc.; the processing system mainly provides data computing services based on the CPU; and the HIS electronic medical record system, please refer to the HIS system in the background of the existing hospital, which is mainly used to manage the patient's electronic medical record files, and is used to record the patient's corresponding clinical examination data and medical advice and other data information; and the API interface can be used to communicate with the terminal or with the nursing end, such as PDA or EDA terminal, etc., and the patient's corresponding prediction results, such as the corresponding abnormal symptoms of the patient's arterial blood vessels, the corresponding clinical vascular care strategies (such as vascular ice packs) predicted and output by the AI ​​model, can be sent to the PDA terminal to notify the nurse to provide care.

[0218] The present invention can simultaneously send down the nursing strategy generated by the model prediction and display it on the display screen at the middle end.

[0219] The medical and patient management system is mainly used to manage the relative information between patients and medical staff. For example, it can record the patient's basic information, status, etc., and can also record and bind the information of the nursing staff who provide care for the patient.

[0220] The blood abnormality monitoring system deploys an AI model, which is built and generated based on big data training. Please refer to the subsequent description.

[0221] Preferably, a big data analysis is performed on the tremor frequency and the tremor intensity to predict and provide feedback on the corresponding arterial vascular pre-diagnosis nursing strategy, including:

[0222] Based on the historical data set of arterial tremor diagnosis, an arterial pre-diagnosis analysis AI model is trained and constructed and deployed on the backend of the nurse station;

[0223] The nurse station backend inputs the patient's tremor frequency and tremor intensity into the arterial vascular pre-diagnosis analysis AI model, and the arterial vascular pre-diagnosis analysis AI model identifies the characteristic values ​​of the tremor frequency and the tremor intensity, and outputs the arterial vascular pre-diagnosis nursing strategy that matches the characteristic values ​​of the tremor frequency and the tremor intensity;

[0224] The arterial vascular pre-diagnosis care strategy is written into the patient's electronic medical record.

[0225] Please combine the following model training and application principles.

[0226] like Figure 3 As shown, preferably, the method for generating the arterial vascular pre-diagnosis analysis AI model includes:

[0227] The arterial tremor diagnosis history data of several patients are collected and preprocessed to construct the arterial tremor diagnosis history data set, wherein the arterial tremor diagnosis history data includes:

[0228] The patient's vascular ultrasound images, vascular tremor data, vascular abnormality symptom information, and corresponding nursing strategy information prescribed by medical staff based on the vascular ultrasound images, vascular tremor data, and / or vascular abnormality symptom information;

[0229] Perform feature engineering to extract relevant features of vascular abnormalities in the arterial tremor diagnosis history data of each patient: image spectrum image features related to vascular abnormalities (this model outputs, but is mainly used to output tremor frequency and intensity values), feature values ​​in the vascular tremor data and / or vascular abnormality symptom feature keywords;

[0230] Performing feature annotation on the associated features of vascular abnormalities in the arterial vascular fibrillation diagnosis history data of each patient, wherein the annotation information includes: nursing strategy information corresponding to the associated features;

[0231] The annotated associated features are combined into a feature set, and the feature set is divided into a training set and a validation set according to a preset ratio;

[0232] Input the training set into a preset random deep forest model to perform feature training and learning, thereby generating a method for generating the arterial vascular pre-diagnosis analysis AI model;

[0233] The recognition performance of the generation method of the arterial vascular pre-diagnosis analysis AI model was verified using a validation set:

[0234] If the verification is passed, the method for generating the arterial vascular pre-diagnosis analysis AI model is deployed in the background of the nurse station;

[0235] On the contrary, the above steps are repeated to reconstruct the generation method of the arterial vascular pre-diagnosis analysis AI model.

[0236] To build a model that uses big data technology to train and identify abnormal vascular symptoms of different vascular tremor frequencies and intensities and recommend nursing strategies corresponding to abnormal symptoms, you can follow the following steps:

[0237] Step 1: Data collection and preparation

[0238] Collect data:

[0239] Medical imaging equipment, such as ultrasound equipment, is used to collect large amounts of data on the frequency and intensity of tremors in blood vessels.

[0240] Collect information on abnormal vascular symptoms related to the frequency and intensity of vascular tremors, including medical images, diagnostic reports, medical records, etc.

[0241] Collect information on nursing strategies for these abnormal symptoms, which may include medication, lifestyle interventions, psychological care, etc.

[0242] Data cleaning and preprocessing:

[0243] The collected data is cleaned to remove noise and outliers.

[0244] Label the data to make it clear which data are normal vascular tremors and which data are abnormal vascular tremors, and mark the corresponding abnormal symptoms.

[0245] Organize nursing strategy data into a structured data format.

[0246] Step 2: Feature extraction and data representation

[0247] Feature extraction:

[0248] Extract useful features from vascular tremor data, such as tremor frequency, intensity, duration, etc.

[0249] Extract key information from vascular abnormality symptom data, such as symptom type, severity, etc.

[0250] Extract characteristics such as nursing measures and expected effects from nursing strategy data.

[0251] Data representation:

[0252] Convert text data into numerical data using appropriate data representation methods such as one-hot encoding, word embedding, etc.

[0253] A feature vector was constructed to integrate the features of vascular tremor, abnormal symptoms, and nursing strategies.

[0254] Step 3: Model selection and construction

[0255] Choose the appropriate model:

[0256] Select appropriate machine learning or deep learning models based on the complexity of the problem and the characteristics of the data, such as convolutional neural network (CNN), recurrent neural network (RNN), decision tree, random forest, etc.

[0257] Consider using a multi-task learning model to simultaneously handle the vascular tremor identification task and the care strategy recommendation task.

[0258] Build the model:

[0259] According to the selected model, the corresponding network structure is constructed.

[0260] Set the model's hyperparameters, such as learning rate, batch size, etc.

[0261] Step 4: Model training and optimization

[0262] Data partitioning:

[0263] Divide the dataset into training set, validation set and test set (for example, 7:3).

[0264] Model training:

[0265] The model is trained using the training set data and the model parameters are adjusted using the back propagation algorithm.

[0266] During the training process, the validation set data is used to validate the model (indicators include accuracy, recall, F1 score, etc.), and the model parameters and structure are adjusted according to the validation results.

[0267] Prevent overfitting:

[0268] Use regularization, dropout and other techniques to prevent model overfitting.

[0269] Try different data augmentation methods to improve the generalization ability of the model.

[0270] Step 5: Model evaluation and testing

[0271] Test model:

[0272] The model was tested using clinically collected test set data to evaluate the performance of the model.

[0273] The performance of the model in identifying vascular tremor and recommending nursing strategies was evaluated using performance indicators such as precision, recall, and F1 score. The administrator completed the validation results on his own.

[0274] Step 6: Model deployment and application

[0275] Deploy the model:

[0276] Deploy the trained model to actual application scenarios, such as medical diagnosis systems, nursing guidance systems, etc.

[0277] Continuous monitoring and optimization:

[0278] Continuously monitor the model and collect feedback data.

[0279] Case Study:

[0280] Clinical case: Using the AI ​​model for pre-diagnosis analysis of arterial vessels to assist in the diagnosis of patients with tremor-related vascular abnormalities Background:

[0281] Patient: Mr. Zhang, 65 years old, has a history of hypertension and recently developed hand tremors.

[0282] Diagnostic process:

[0283] Data collection:

[0284] The nurse used the terminal to collect the tremor signal from Mr. Zhang's hand.

[0285] The collected signals are preprocessed, including filtering and denoising, to improve signal quality.

[0286] Feature extraction:

[0287] The preprocessed signal is subjected to spectrum analysis, and the tremor frequency and tremor intensity are extracted as feature values.

[0288] In this case, assume that the extracted tremor frequency is 5 Hz and the tremor intensity is 0.2 g (unit of gravity acceleration).

[0289] AI model analysis:

[0290] The tremor frequency and tremor intensity are used as input into the pre-trained arterial vascular pre-diagnosis analysis AI model.

[0291] The AI ​​model uses a deep learning algorithm to automatically identify the characteristic values ​​of tremor frequency and tremor intensity, and match them with known vascular abnormality symptom characteristics.

[0292] Diagnostic result output:

[0293] The AI ​​model outputs vascular abnormality symptom characteristics that match Mr. Zhang’s tremor frequency and tremor intensity characteristic values, such as “possible vascular stenosis” or “increased risk of vascular sclerosis.”

[0294] At the same time, the AI ​​model also provides corresponding recommendations for arterial vascular pre-diagnosis care measures, such as "further vascular examination is recommended (such as ultrasonic angiography)", "adjust the dosage of antihypertensive drugs" and "regularly monitor hand tremors".

[0295] Clinical Application:

[0296] Physician decision support: Doctors can make more accurate diagnoses and develop appropriate treatment plans based on the output of the AI ​​model, combined with the patient's medical history, physical examination, and other examination results.

[0297] Patient education and management: The doctor explained the AI ​​model’s diagnostic results and nursing measures to Mr. Zhang, raised the patient’s health awareness, and guided the patient in self-management.

[0298] Continuous monitoring and follow-up: Based on the recommendations of the AI ​​model, the doctor arranged regular vascular examinations and tremor monitoring for Mr. Zhang, and adjusted the treatment plan in a timely manner to ensure that the disease was effectively controlled.

[0299] Case summary:

[0300] Through this clinical case, we can see that inputting the patient's tremor frequency and tremor intensity into the arterial vascular pre-diagnosis analysis AI model can assist doctors in identifying the symptoms and characteristics of vascular abnormalities more quickly and accurately, and formulate corresponding nursing measures. This not only improves the accuracy and efficiency of diagnosis, but also provides patients with more personalized and precise treatment plans, which helps to improve patients' prognosis and quality of life.

[0301] The modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0302] Example 3

[0303] like Figure 4 As shown, further, in another aspect, the present application also proposes an electronic device, including:

[0304] processor;

[0305] a memory for storing processor-executable instructions;

[0306] Wherein, the processor is configured to implement the detection method when executing the executable instructions.

[0307] The electronic device according to the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to implement any of the above-mentioned detection methods when executing the executable instructions.

[0308] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device in the embodiment of the present disclosure may also include an input device and an output device. Among them, the processor, memory, input device and output device may be connected through a bus or in other ways, which are not specifically limited here.

[0309] The memory is a computer-readable storage medium that can be used to store software programs, computer executable programs, and various modules, such as the program or module corresponding to the detection method of the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0310] The input device can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output device can include a display device such as a display screen.

[0311] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A nursing staff arterial blood vessel mobile detection terminal, including a mobile carrier, characterized in that: The mobile carrier is integrated with: Ultrasound module, used to collect raw signal data of arterial blood vessels and feed it back to MCU; MCU, used to control the ultrasound module to sample according to a preset sampling frequency, pre-process the raw signal data, separate the arterial vascular tremor audio signal, and perform spectrum analysis on the arterial vascular tremor audio signal based on a frequency domain analysis algorithm, extract the corresponding tremor frequency and tremor intensity therein, and send them to the FPGA; FPGA, used for receiving the tremor frequency and the tremor intensity in real time, and inputting the tremor frequency and the tremor intensity into a preset X function and a Y function respectively, and fitting and generating an XY curve function corresponding to the tremor frequency and the tremor intensity; The wireless module is used to upload the tremor frequency and the tremor intensity to the nurse station backend, and after the nurse station backend performs big data analysis, the corresponding arterial vascular pre-diagnosis nursing strategy is fed back and sent to the wireless module, and the wireless module is forwarded to the MCU, and then sent to the electronic screen after being parsed and processed by the MCU; An electronic screen, used for reading the XY curve function of the tremor frequency and the tremor intensity and displaying the XY curve function image of the tremor frequency and the tremor intensity in an XY coordinate system; and / or reading and displaying the arterial vascular pre-diagnosis care strategy; A control panel for inputting control parameters; Power supply, used for power supply; The ultrasound module, FPGA, wireless module, electronic screen, control panel and power supply are electrically connected to the MCU respectively.

2. A nursing staff arterial blood vessel movement detection terminal according to claim 1, characterized in that: The mobile carrier is a bracelet or a wristband.

3. The nursing staff arterial blood vessel movement detection terminal according to claim 1, characterized in that: The calculation method of the tremor intensity is: Collecting a plurality of original signal values ​​sampled at each of the tremor frequencies and performing spectrum analysis to obtain a plurality of corresponding tremor intensity values; The maximum and minimum values ​​among several tremor intensity values ​​are removed, and the average of the remaining tremor intensity values ​​is calculated to produce the tremor intensity collected at the current tremor frequency.

4. A detection method based on the nursing staff arterial blood vessel movement detection terminal according to any one of claims 1 to 3, characterized in that: The steps include: Activate the nursing staff's arterial blood vessel mobile detection terminal, establish a communication link with the nurse station background, and bind the terminal number and medical staff information on the nurse station background; Sending a sampling instruction to the nursing staff's arterial blood vessel mobile detection terminal through the nurse station background; The nursing staff arterial blood vessel movement detection terminal receives and responds: The wireless module receives and forwards the sampling instruction to the MCU; The MCU controls the ultrasonic module to sample according to the preset sampling frequency, collects the original signal data of the arterial blood vessels, pre-processes the original signal data, separates the arterial blood vessel tremor audio signal, and performs spectrum analysis on the arterial blood vessel tremor audio signal based on the frequency domain analysis algorithm, extracts the corresponding tremor frequency and tremor intensity and sends them to the FPGA; at the same time, the tremor frequency and the tremor intensity are reported to the nurse station backstage through the wireless module; The FPGA receives the tremor frequency and the tremor intensity in real time, and inputs the tremor frequency and the tremor intensity into a preset X function and a preset Y function, respectively, to generate an XY curve function corresponding to the tremor frequency and the tremor intensity by fitting; The MCU forwards the XY curve function of the tremor frequency and the tremor intensity to the electronic screen, and the electronic screen reads the XY curve function of the tremor frequency and the tremor intensity and displays the XY curve function image of the tremor frequency and the tremor intensity in an XY coordinate system; After receiving the tremor frequency and the tremor intensity, the nurse station backend writes them into the patient's electronic medical record, performs big data analysis on the tremor frequency and the tremor intensity, predicts and feeds back the corresponding arterial vascular pre-diagnosis nursing strategy and sends it to the wireless module, which is then forwarded to the MCU and sent to the electronic screen after being parsed and processed by the MCU; The electronic screen reads and displays the arterial vascular pre-diagnosis care strategy.

5. The detection method according to claim 4, characterized in that: The tremor frequency and the tremor intensity are analyzed by big data to predict and provide feedback on corresponding arterial vascular pre-diagnosis and nursing strategies, including: Based on the historical data set of arterial tremor diagnosis, an arterial pre-diagnosis analysis AI model is trained and constructed and deployed on the backend of the nurse station; The nurse station backend inputs the patient's tremor frequency and tremor intensity into the arterial vascular pre-diagnosis analysis AI model, and the arterial vascular pre-diagnosis analysis AI model identifies the characteristic values ​​of the tremor frequency and the tremor intensity, and outputs the arterial vascular pre-diagnosis nursing strategy that matches the characteristic values ​​of the tremor frequency and the tremor intensity; The arterial vascular pre-diagnosis care strategy is written into the patient's electronic medical record.

6. The detection method according to claim 5, characterized in that: The method for generating the arterial vascular pre-diagnosis analysis AI model comprises: The arterial tremor diagnosis history data of several patients are collected and preprocessed to construct the arterial tremor diagnosis history data set, wherein the arterial tremor diagnosis history data includes: The patient's vascular ultrasound images, vascular tremor data, vascular abnormality symptom information, and corresponding nursing strategy information prescribed by medical staff based on the vascular ultrasound images, vascular tremor data, and / or vascular abnormality symptom information; Perform feature engineering to extract relevant features related to vascular abnormalities in the arterial vascular tremor diagnosis history data of each patient: image spectrum image features related to vascular abnormalities, feature values ​​in the vascular tremor data and / or vascular abnormality symptom feature keywords; Performing feature annotation on the associated features of vascular abnormalities in the arterial vascular fibrillation diagnosis history data of each patient, wherein the annotation information includes: nursing strategy information corresponding to the associated features; The annotated associated features are combined into a feature set, and the feature set is divided into a training set and a validation set according to a preset ratio; Input the training set into a preset random deep forest model to perform feature training and learning, thereby generating a method for generating the arterial vascular pre-diagnosis analysis AI model; The recognition performance of the generation method of the arterial vascular pre-diagnosis analysis AI model was verified using a validation set: If the verification is passed, the method for generating the arterial vascular pre-diagnosis analysis AI model is deployed in the background of the nurse station; On the contrary, the above steps are repeated to reconstruct the generation method of the arterial vascular pre-diagnosis analysis AI model.

7. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement a nursing staff arterial blood vessel movement detection terminal and detection method as described in any one of claims 4-6 when executing the executable instructions.

Images