Intelligent decompression noninvasive mechanical ventilation mask based on flexible pressure sensing technology

Abstract

The invention provides an intelligent pressure-reducing non-invasive mechanical ventilation mask based on a flexible pressure sensing technology, which comprises a mechanical ventilation mask, a display and alarm module and a mask state AI analysis system, and aims to solve the problem that the existing non-invasive mechanical ventilation mask is easy to cause pressure injury to the face of a patient in the use process. The flexible pressure sensing technology is combined with the non-invasive mechanical ventilation mask, the pressure magnitude and the pressure distribution condition of the mask and all contact parts of the face of a patient are accurately sensed, and a basis is provided for adjusting the mask wearing mode and pressure parameters; through pressure information fed back in real time, the wearing state of the mask is adjusted in time, pressure distribution is optimized, local pressure is prevented from being too high, and therefore pressure injury is effectively prevented. Flexible sensing and intelligent prevention are integrated, when it is monitored that the pressure exceeds a preset threshold value, the system automatically sends out an early warning prompt signal, meanwhile, prevention analysis is conducted according to the state of a patient, medical staff is reminded to adjust the face mask wearing state in time, and intelligent prevention is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent medical equipment, and in particular to an intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology, an application method, an electronic device and a computer-readable storage medium. Background Art

[0002] Non-invasive mechanical ventilation is an important means of respiratory support treatment, and it improves the comfort of patients with chronic obstructive pulmonary disease and sleep apnea. Flexible pressure sensor arrays are integrated in key areas where the mask contacts the face, such as the bridge of the nose, cheeks, and mandible. The sensor array consists of multiple miniature flexible pressure sensors, which can accurately stop hypoventilation syndrome, respiratory failure and other respiratory diseases and has been widely used in the treatment of various respiratory diseases. Compared with invasive ventilation, non-invasive mechanical ventilation avoids the infection risks, airway damage and other complications brought about by tracheal intubation or incision, and improves patient comfort and treatment compliance. With the aggravation of the aging population and the increase in the incidence of respiratory diseases, the number of patients receiving non-invasive mechanical ventilation treatment has increased year by year.

[0003] However, the existing non-invasive mechanical ventilation masks used in clinical practice (such as the attached Figure 1 During noninvasive mechanical ventilation, the following issues can arise: prolonged, close contact between the mask and the patient's face, resulting in uneven pressure distribution and a high risk of pressure injuries on the facial skin. These injuries not only cause pain and discomfort, hindering treatment progress, increasing medical expenses and hospitalization time, but can also lead to infection, further exacerbating the patient's condition. Statistics show that the incidence of pressure injuries among patients receiving noninvasive mechanical ventilation is as high as 5% to 50%, and there are currently no effective preventive measures.

[0004] In addition, although flexible pressure sensing technology has made significant progress in recent years, this technology can sense the size and distribution of pressure and convert it into electrical signals for real-time monitoring and analysis. Flexible pressure sensors have the advantages of good flexibility, high sensitivity, and fast response speed. They can fit the surface of the human body and achieve accurate measurement of pressure on complex curved surfaces. Applying flexible pressure sensing technology to non-invasive mechanical ventilation masks is expected to monitor the pressure distribution between the mask and the face in real time, providing effective technical support for preventing pressure injuries. However, the existing technical solutions for preventing pressure injuries do not integrate flexible sensing and intelligent prevention, and intelligent prevention cannot be achieved. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0006] On the one hand, an intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology is provided, including a mechanical ventilation mask, a display and alarm module, and an AI analysis system for mask status, wherein:

[0007] (1) The mechanical ventilation mask is integrated with:

[0008] Flexible pressure sensors are distributed on the mechanical ventilation mask at locations that contact the patient's face, and are used to sense the pressure and distribution signals at each location and provide real-time feedback to the signal acquisition and processing module.

[0009] The signal acquisition and processing module is used to receive the pressure size and distribution signals of various parts and perform signal preprocessing and digital-to-analog conversion to obtain the pressure size and distribution data of various parts and transmit them to the wireless module in real time;

[0010] A wireless module is used to communicate data with the mask status AI analysis system and upload the pressure size and distribution data of each part to the mask status AI analysis system in real time;

[0011] Power supply, used for power supply;

[0012] (2) Mask status AI analysis system, which is used to receive and record the pressure size and distribution data of various parts of the patient, and then perform pressure injury prevention analysis on the pressure size and distribution data of various parts of the patient through the preset pressure injury prevention analysis model. If any part is found to have a pressure value exceeding the standard, an early warning signal of the corresponding part will be issued and the corresponding wearing status adjustment strategy will be recommended to the display and alarm module;

[0013] (3) a display and alarm module, which is used to display the pressure size and distribution data of various parts of the patient's face through a split-screen technology; and when a warning prompt signal and a recommended wearing state adjustment strategy are received for a corresponding part, the split-screen of the corresponding part responds to the alarm and displays the wearing state adjustment strategy;

[0014] The mechanical ventilation mask is communicatively connected to the mask status AI analysis system via a wireless module;

[0015] The display and alarm module is in communication with the mask status AI analysis system.

[0016] Preferably, the signal acquisition and processing module includes:

[0017] Signal acquisition port, used to obtain sampling signals from various parts;

[0018] a microprocessor for providing signal processing services;

[0019] The preprocessing module is used to provide signal preprocessing services, including an amplifier circuit, a filter circuit, and a noise reduction circuit, which respectively amplify, filter, and reduce noise on the signal;

[0020] A digital-to-analog conversion module is used to perform A / D digital-to-analog conversion on the signal;

[0021] A data encryption transmission port is used to transmit the processed pressure size and distribution data of each part to the wireless module after data encryption;

[0022] The signal acquisition port, preprocessing module, digital-to-analog conversion module, microprocessor and data encryption transmission port are electrically connected in sequence.

[0023] Preferably, the wireless module adopts one of the following wireless options:

[0024] Bluetooth, WiFi, 4 / 5G, Zigbee, LoRa or NB-IoT.

[0025] Preferably, the mask status AI analysis system includes:

[0026] The data encryption sampling port is used to receive the pressure size and distribution data of each part and perform decryption verification to determine whether the data has been tampered with: if it has not been tampered with, the data will be sent to the HIS system; otherwise, access will be denied;

[0027] The HIS system is used to construct and save the patient's electronic medical record file, and record and update the pressure size and distribution data of various parts of the patient's face into the electronic medical record file;

[0028] A traversal system is used to sequentially traverse the pressure magnitude and distribution data of various parts of the patient's face from the HIS system according to a preset time window and input the data into the preset pressure injury prevention and analysis model;

[0029] The AI ​​pressure injury prevention analysis model is used to perform pressure injury prevention analysis on the input pressure size and distribution data of various parts of the patient. If any part is found to have excessive pressure values, it will output a warning signal for the corresponding part and recommend a corresponding wearing status adjustment strategy. The HIS system will record and update it in the patient's electronic medical record;

[0030] The message middleware is used to send the early warning prompt signal of the corresponding part of the patient and recommend the corresponding wearing status adjustment strategy to the display and alarm module.

[0031] Preferably, the mask status AI analysis system further includes:

[0032] The terminal API port is used to provide a nursing terminal PDA / EDA access port, receive the pressure threshold of the corresponding part of the patient input by the nursing terminal PDA / EDA and write it into the patient's electronic medical record file in the HIS system.

[0033] Preferably, the method for generating the pressure injury AI prevention analysis model includes:

[0034] Collect historical intervention data from several patients wearing mechanical ventilation masks for respiratory therapy, including pressure and distribution data for various parts of the patient's body. The following risk factors were assessed for the patients: Braden score, basic patient factors, mask wearing factors, high-risk areas, and skin conditions, and the wearing status adjustment strategies implemented for the patients.

[0035] Characterizing the historical intervention big data, constructing a feature set consisting of the feature data of each patient, and dividing it into a training set and a validation set according to a preset ratio;

[0036] The training set is input into a preset Transformer-LSTM hybrid model to train and learn the characteristic data of each patient to generate the initial pressure injury AI prevention and analysis model;

[0037] The validation set was used to verify the performance of the pressure injury prevention analysis model in analyzing excessive pressure values ​​in corresponding parts and recommending corresponding wearing state adjustment strategies:

[0038] If the verification is passed, the pressure injury AI prevention analysis model is deployed and applied to the mask status AI analysis system;

[0039] On the contrary, the pressure injury AI prevention analysis model is reconstructed.

[0040] On the other hand, a method for applying an intelligent pressure-reducing non-invasive mechanical ventilation mask based on flexible pressure sensing technology is provided, the method comprising:

[0041] Put on a mechanical ventilation mask for the patient and activate it, establish wireless communication with the mask status AI analysis system, and bind the device ID of the mechanical ventilation mask and the patient's visit ID to the mask status AI analysis system;

[0042] The system issues a sampling instruction, notifying the mechanical ventilation mask to start sampling:

[0043] The flexible pressure sensor senses the pressure size and distribution signals of each part and feeds them back to the signal acquisition and processing module in real time;

[0044] The signal acquisition and processing module receives the pressure and distribution signals of each part and performs signal preprocessing and digital-to-analog conversion to obtain the pressure and distribution data of each part and transmit them to the wireless module in real time;

[0045] The pressure size and distribution data of each part are uploaded to the mask status AI analysis system in real time through the wireless module;

[0046] After receiving and recording the pressure size and distribution data of various parts of the patient, the mask status AI analysis system performs pressure injury prevention analysis on the pressure size and distribution data of various parts of the patient through the preset pressure injury prevention analysis model. If any part is found to have excessive pressure, it will issue a warning signal for the corresponding part and recommend the corresponding wearing status adjustment strategy to the display and alarm module;

[0047] The display and alarm module is used to display the pressure size and distribution data of various parts of the patient's face through split-screen technology; and when the early warning prompt signal and the recommended wearing status adjustment strategy of the corresponding part are received, the split screen of the corresponding part responds to the alarm and displays the said wearing status adjustment strategy.

[0048] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the methods of the intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology is implemented.

[0049] On the other hand, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement any one of the methods of the above-mentioned intelligent pressure-reducing non-invasive mechanical ventilation mask based on flexible pressure sensing technology.

[0050] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0051] This invention proposes an intelligent, pressure-reducing, non-invasive mechanical ventilation mask based on flexible pressure sensing technology. The mask comprises a mechanical ventilation mask, a display and alarm module, and an AI-powered mask status analysis system. This design aims to address the problem of existing non-invasive mechanical ventilation masks easily causing pressure injuries to the patient's face during use. By combining flexible pressure sensing technology with a non-invasive mechanical ventilation mask, the following objectives are achieved:

[0052] 1. Real-time monitoring of pressure distribution: Accurately sense the pressure size and distribution at each contact point between the mask and the patient's face, providing a basis for adjusting the mask wearing method and pressure parameters;

[0053] 2. Preventing pressure injuries: Through real-time pressure feedback, timely adjust the mask wearing status, optimize pressure distribution, avoid local excessive pressure, and thus effectively prevent the occurrence of pressure injuries;

[0054] 3. Improve treatment effect and comfort: Under the premise of ensuring treatment effect, improve the patient's comfort when wearing the mask, reduce treatment interruption due to discomfort, and improve treatment compliance.

[0055] 4. Integrating flexible sensing and intelligent prevention, combined with AI analysis technology, the system predicts and analyzes the pressure distribution of various parts of the mask. When the monitored pressure exceeds the preset threshold, the system automatically issues a warning signal (for example, when the risk of pressure injury is predicted, a red alarm signal is issued). At the same time, it conducts preventive analysis based on the patient's condition, reminding medical staff to adjust the mask wearing status in time to achieve intelligent prevention. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 This is a structural block diagram of an intelligent pressure-reducing non-invasive mechanical ventilation mask based on flexible pressure sensing technology provided by an embodiment of the present invention;

[0058] Figure 2 This is a schematic diagram of the structure of a mechanical ventilation mask currently used in clinical practice;

[0059] Figure 3 This is a structural diagram of a flexible pressure sensor currently available on the market;

[0060] Figure 4 This is a schematic diagram of the system composition structure of a mask status AI analysis system provided by an embodiment of the present invention;

[0061] Figure 5 1 is a schematic diagram of the training process of a pressure injury AI prevention and analysis model provided by an embodiment of the present invention;

[0062] Figure 6 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0064] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0065] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0066] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0067] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0068] The embodiment of the present invention provides an intelligent pressure-reducing non-invasive mechanical ventilation mask based on flexible pressure sensing technology, such as Figure 1 The block diagram of the intelligent pressure-reducing non-invasive mechanical ventilation mask based on flexible pressure sensing technology shown in the figure provides an intelligent pressure-reducing non-invasive mechanical ventilation mask based on flexible pressure sensing technology, including a mechanical ventilation mask, a display and alarm module, and an AI analysis system for mask status, wherein:

[0069] (1) The mechanical ventilation mask is integrated with:

[0070] Flexible pressure sensors are distributed on the mechanical ventilation mask at locations that contact the patient's face, and are used to sense the pressure and distribution signals at each location and provide real-time feedback to the signal acquisition and processing module.

[0071] The signal acquisition and processing module is used to receive the pressure size and distribution signals of various parts and perform signal preprocessing and digital-to-analog conversion to obtain the pressure size and distribution data of various parts and transmit them to the wireless module in real time;

[0072] A wireless module is used to communicate data with the mask status AI analysis system and upload the pressure size and distribution data of each part to the mask status AI analysis system in real time;

[0073] Power supply, used for power supply;

[0074] (2) Mask status AI analysis system, which is used to receive and record the pressure size and distribution data of various parts of the patient, and then perform pressure injury prevention analysis on the pressure size and distribution data of various parts of the patient through the preset pressure injury prevention analysis model. If any part is found to have a pressure value exceeding the standard, an early warning signal of the corresponding part will be issued and the corresponding wearing status adjustment strategy will be recommended to the display and alarm module;

[0075] (3) a display and alarm module, which is used to display the pressure size and distribution data of various parts of the patient's face through a split-screen technology; and when a warning prompt signal and a recommended wearing state adjustment strategy are received for a corresponding part, the split-screen of the corresponding part responds to the alarm and displays the wearing state adjustment strategy;

[0076] The mechanical ventilation mask is communicatively connected to the mask status AI analysis system via a wireless module;

[0077] The display and alarm module is in communication with the mask status AI analysis system.

[0078] like Figure 2 The figure shows the structure of a mechanical ventilation mask currently used in clinical practice. The specific structure can be determined according to hospital procurement or design. This embodiment does not limit the application structure and size of the mechanical ventilation mask.

[0079] The modules integrated into the mechanical ventilation mask can be configured based on their location, and the user can choose the integration structure. For example, the flexible pressure sensor's distribution and fixing method (adhesive fixation or other methods) can be determined. For example, the microprocessor and power supply can be integrated into the control box using waterproof materials and fixed to a fixed position on the outside of the mask. For example, the following Transformer-LSTM hybrid model form is used:

[0080] Module ‌Device Model / Parameters‌ ‌Functional Description‌ Mechanical ventilation mask Philips Respironics V60 Flex (Customized Edition) Medical non-invasive ventilation mask with built-in flexible pressure sensor array, adaptable to the nose bridge / facial curve. Flexible pressure sensor Tekscan FlexiForce A401 (range 0-300 mmHg, accuracy ±1.5%, response time ≤5 ms) It covers six areas including nose, cheek, forehead and behind the ear, and monitors local pressure in real time. Signal acquisition and processing module STM32H7 microprocessor (480MHz, 2MB Flash) + ADI AD8237 instrumentation amplifier + AD7190 24-bit ADC Amplification (gain 100x), filtering (0.1-10Hz bandpass), analog-to-digital conversion (sampling rate 200Hz). Wireless module Nordic nRF52840 (Bluetooth 5.2 + Thread protocol, transmission rate 2Mbps) Encrypted transmission of pressure data to the AI ​​analysis system (AES-128 encryption). power supply Rechargeable lithium polymer battery (3.7V / 1000mAh, battery life ≥72h) Supports wireless charging (Qi standard), medical-grade packaging. Display and alarm module Advantech PPC-L157T medical split-screen monitor (15.6-inch, 1920×1080, touchscreen) The split screen displays 6-area pressure heat maps (color gradient: green <20mmHg, red >32mmHg) and adjustment strategies. ‌HIS system server (the hospital's existing one can be used)‌ Dell PowerEdge R750 (dual-socket Xeon Silver 4310, 64GB memory, 10TB NVMe storage) Stores patient electronic medical records and integrates stress data and risk factors (Braden score, subcutaneous fat thickness, etc.). ‌AI analysis server (can be deployed on the nurse station backend server)‌ NVIDIA DGX A100 (8x A100 GPUs, 1TB of memory) Deploy the Transformer-LSTM hybrid model to analyze stress risks in real time.

[0081] Flexible Pressure Sensing Mask: The mask body is made of soft, breathable medical silicone material to enhance patient comfort. Flexible pressure sensor arrays are integrated at key areas of contact between the mask and the face, such as the bridge of the nose, cheeks, and jaw. The sensor array, comprised of multiple miniature flexible pressure sensors, accurately senses pressure changes at different locations and converts the pressure signals into electrical signals.

[0082] like Figure 3As shown in the figure, the flexible pressure sensor is a new type of sensor that can sense pressure and convert it into an electrical signal. It has the characteristics of being soft, bendable, and stretchable. It is widely used in electronic skin, wearable devices, medical monitoring and other fields. The following is a detailed introduction:

[0083] like Figure 3 The structure and principle of a flexible pressure sensor currently available on the market (such as the Tekscan thin film pressure sensor and the Si4-G thin film pressure sensor) are as follows:

[0084] Structure: Usually composed of a flexible substrate, sensitive materials, and electrodes. The flexible substrate provides support and flexibility, the sensitive materials are responsible for sensing pressure changes, and the electrodes are used to transmit electrical signals.

[0085] Principle: Based on the piezoresistive effect, capacitive effect, or piezoelectric effect. When subjected to pressure, the resistance, capacitance, or polarization state of the sensitive material changes, and the pressure is detected by measuring these changes.

[0086] Material selection

[0087] Flexible substrate materials: such as polydimethylsiloxane (PDMS), polyimide (PI), etc., have good flexibility, chemical stability and biocompatibility.

[0088] Sensitive materials: including carbon nanotubes, graphene, conductive polymers, etc., which can produce obvious changes in electrical properties under the action of pressure.

[0089] Features

[0090] Good flexibility: It can adapt to various complex curved surfaces and irregular shapes, and can fit closely to the surface of the human body or other objects.

[0091] High sensitivity: It can sense tiny pressure changes and can detect pressures from a few Pascals to tens of kilopascals.

[0092] Fast response speed: It can quickly sense pressure changes and output electrical signals in a timely manner. The response time is usually in milliseconds.

[0093] Strong integrability: easy to integrate with other electronic components to form a multifunctional sensor system.

[0094] Application Areas

[0095] Wearable devices: used to monitor human movement and physiological signals such as heart rate and breathing, and can also realize touch interaction functions.

[0096] Medical field: It can be made into electronic skin to monitor patients' vital signs, wound healing, etc. It can also be used for pressure monitoring during rehabilitation treatment.

[0097] Robotics: Installed on the hand or body surface of the robot, it can sense contact force and pressure distribution, achieving more flexible and precise operation.

[0098] Industrial detection: used to detect pressure distribution and changes in industrial production to achieve quality control and fault diagnosis.

[0099] Signal Acquisition and Processing Module: This module collects the electrical signals output by the flexible pressure sensor array and performs amplification, filtering, and analog-to-digital conversion to convert them into digital signals. A microprocessor then analyzes and processes these digital signals to obtain information about the pressure level and distribution at each point of contact between the mask and the face.

[0100] AI analysis system: By adding high-risk factors, combining risk factors such as subcutaneous fat thickness, pressure value, and pressure maintenance duration (see the table below for details), and combining patient physical sensations (such as sound feedback microphones), risk prediction is made (see subsequent model training and application content for details).

[0101] The working principle of the device is as follows:

[0102] 1. Pressure Sensing: When a patient wears a flexible pressure-sensing mask for noninvasive mechanical ventilation, the mask creates pressure on the face. Each sensor in the flexible pressure sensor array senses this pressure change and converts it into an electrical signal for output.

[0103] 2. Signal Processing: The signal acquisition and processing module amplifies and filters the received electrical signals to remove noise and improve signal quality. It then converts the analog signals into digital signals via an analog-to-digital converter and transmits the digital signals to the microprocessor.

[0104] 3. Data Analysis and Decision-Making: The microprocessor analyzes the collected pressure data and calculates the pressure level and distribution at each point of contact between the mask and the face. Based on preset pressure thresholds and algorithms, it determines whether there are areas of excessive pressure. If excessive pressure is detected, the system issues an alarm and provides appropriate adjustments, such as adjusting the mask's position and tightness.

[0105] 4. Feedback and Adjustment: Based on information provided by the display and alarm module, medical staff can promptly adjust the mask fit to optimize pressure distribution and ensure even and appropriate pressure across the patient's face. Furthermore, the remote monitoring module can transmit adjusted pressure data in real time to a remote monitoring terminal, enabling medical staff to track and manage the patient's treatment progress.

[0106] The following describes in further detail:

[0107] 1. Mechanical ventilation mask module

[0108] 1. Flexible pressure sensor array

[0109] Model: Tekscan FlexiForce A401 (single-point measuring range 0-100N, accuracy ±2.5%)

[0110] Layout: 9 sensor nodes in the nose bridge area (2), cheekbone area (4), and mandibular area (3);

[0111] Sampling frequency: 10Hz, transmitted to the signal acquisition port via I2C bus,

[0112] 2. Calibration process:

[0113] Use the Biopac MP36 calibrator to input the standard pressure of 0-300 mmHg and record the sensor output voltage;

[0114] Fitting linear curve (R² ≥ 0.99) and writing to STM32H7 microcontroller;

[0115] Clinical measurement verification (n=20 cases), error ≤±2mmHg.

[0116] 3. Signal acquisition and processing module

[0117] Microprocessor: STM32H743 (dual-core Cortex-M7, main frequency 480MHz);

[0118] Real-time performance‌:

[0119] Sampling rate: 200Hz (pressure value updated every 5ms);

[0120] Transmission delay: ≤50ms (from acquisition to display reception).

[0121] Preprocessing process:

[0122] / / Signal processing pseudocode

[0123] raw_data = ADC_Read(sensor_port);

[0124] filtered_data = KalmanFilter(raw_data); / / Noise reduction

[0125] calibrated_data = PolynomialCalibration(filtered_data);

[0126] Encrypted transmission: AES-256 encryption is used to upload data via the ESP32-C3 WiFi module.

[0127] For example, after receiving pressure sensor data, the digital signature is compared through hash verification (SHA-256); if the verification passes, it is transmitted to the HIS system through the HTTPS protocol (TLS 1.3); otherwise, a blockchain evidence alarm is triggered.

[0128] Preferably, the signal acquisition and processing module includes:

[0129] Signal acquisition port, used to obtain sampling signals from various parts;

[0130] a microprocessor for providing signal processing services;

[0131] The preprocessing module is used to provide signal preprocessing services, including an amplifier circuit, a filter circuit, and a noise reduction circuit, which respectively amplify, filter, and reduce noise on the signal;

[0132] A digital-to-analog conversion module is used to perform A / D digital-to-analog conversion on the signal;

[0133] A data encryption transmission port is used to transmit the processed pressure size and distribution data of each part to the wireless module after data encryption;

[0134] The signal acquisition port, preprocessing module, digital-to-analog conversion module, microprocessor and data encryption transmission port are electrically connected in sequence.

[0135] The wireless module transmits pressure information to a remote monitoring terminal, such as a healthcare provider's phone or computer, using wireless communication technologies like Bluetooth and Wi-Fi. Healthcare providers can access patients' pressure data anytime, anywhere, enabling remote monitoring and management. Bluetooth is the preferred communication method.

[0136] Signal acquisition port: uses a 16-channel FlexiForce™ thin film pressure sensor (range 0-25N, accuracy ±1.5%), connected to the pre-processing module via an FPC cable.

[0137] Sampling frequency: 100Hz (configurable), supports dynamic range calibration.

[0138] Preprocessing module:

[0139] Amplifier circuit: TI INA333 instrumentation amplifier (gain 1000 times, CMRR ≥ 120dB);

[0140] Filter circuit: second-order Butterworth low-pass filter (cut-off frequency 50Hz, eliminating power frequency interference);

[0141] Noise reduction circuit: AD8237 common-mode noise suppression chip (SNR increased to 78dB).

[0142] Digital-to-analog conversion module: ADS1299 biopotential ADC (24-bit resolution, 8-channel synchronous sampling); conversion delay: <500μs, communicates with the microprocessor through the SPI interface.

[0143] Data encryption transmission: AES-256 hardware encryption engine (built-in in STM32U585 MCU).

[0144] 2. Display and alarm module

[0145] 1. Hardware composition

[0146] Display unit: 7-inch AMOLED split screen (1280×800), each zone displays a pressure heat map

[0147] Alarm logic: When the pressure is >32mmHg (4.3kPa) for 5 minutes, the sound and light alarm will be triggered (buzzer 85dB, LED red light flashing)

[0148] 2. Adjust strategy push

[0149] Dynamically generates elastic band adjustment suggestions (e.g., "Zygomatic area needs to be loosened 1 level")

[0150] The display interface highlights abnormal areas simultaneously (RGB color scale: green < 20mmHg → red > 32mmHg)

[0151] 3. Figure 4 As shown, the mask status AI analysis system

[0152] 1. AI-based pressure injury prevention analysis model

[0153] Dataset: Facial pressure dataset of 1,200 patients from a tertiary hospital over a two-year period (labeled with the gold standard: VISIA skin test), including:

[0154] Feature dimensions: pressure distribution (6 areas), Braden score, subcutaneous fat thickness (MRI measurement), RASS score, pain audio characteristics (MFCC coefficients).

[0155] ‌Label‌: Actual location of pressure injuries and effectiveness of adjustment strategies (23 strategies in total).

[0156] Hybrid model algorithm architecture (optimized design based on CNN+LSTM model structure):

[0157] Input layer: used to input the intervention big data of various dimensions collected from patients, including: Braden score, basic patient factors (including: (1) skin condition: dryness / shedding / discoloration / skin lesions / lesions (such as skin problems caused by pemphigus); (2) anatomical structure: nose bridge / face shape / nose shape; (3) history of pressure injury; (4) high-risk factors; (5) RASS score; (6) pain score (for awake patients, the patient's voice is collected through a microphone to conduct pain feedback assessment)), mask wearing factors (including: (1) connection interface type, model, new date; (2) wearing status: such as headband is too tight / knotted / flipped; (3) wearing time), high-risk factors. Location (including high-risk areas such as the nose, lips, forehead, cheeks, and behind the ears) and skin condition (including: (1) Content: skin color, skin tension, and skin integrity; (2) Frequency: 1) For patients who do not continuously (intermittently) use non-invasive ventilation devices, the skin condition should be checked before and after each wearing, and the patient's skin condition should be evaluated and recorded every 8 hours (per shift); 2) For patients who continuously use non-invasive ventilation devices, the skin integrity should be evaluated and recorded every 4 hours), and the wearing status adjustment strategy implemented for the patient). These data can be completed with the assistance of nurses. The evaluation of corresponding factors, such as the Braden score, can refer to the corresponding clinical scoring scale;

[0158] Structured data: Numerical features such as Braden score and RASS score are embedded through a fully connected layer (dimension 64);

[0159] Unstructured data:

[0160] Skin condition images are processed through ResNet-18 to extract visual features (output dimension 256);

[0161] For speech pain assessment, acoustic features were extracted using Wav2Vec 2.0 (output dimension 128).

[0162] Feature fusion module:

[0163] Transformer encoder (4 attention heads, 512 hidden layers) processes temporal pressure distribution data;

[0164] BiLSTM layer (number of units: 256) captures long-term dependencies;

[0165] Cross-modal attention mechanism aligns multi-source features;

[0166] The output layer adopts a dual-branch structure:

[0167] Classification branch: Softmax outputs damage risk level (low / medium / high);

[0168] Regression branch: Recommend a wearing status adjustment strategy that adapts to the pressure values ​​(mmHg) of various parts of the patient (the managing physician can pre-label the corresponding mechanical ventilation mask wearing strategy based on the pressure size and distribution data of various parts of the patient and the various risk factors assessed for the patient based on the above risk factors of the patient, so that the model can identify the pressure size and distribution data of various parts of the patient and the risk factors, and make strategy predictions).

[0169] The model architecture is as follows (pseudo code):

[0170] # Transformer-LSTM hybrid model (PyTorch implementation) class HybridModel(nn.Module):

[0171] def __init__(self):

[0172] super().__init__()

[0173] self.transformer = nn.Transformer(d_model=128, nhead=8)

[0174] self.lstm = nn.LSTM(input_size=128, hidden_size=64, batch_first=True)

[0175] self.fc = nn.Linear(64, 23) # Output 23 adjustment strategies

[0176] def forward(self, x):

[0177] x = self.transformer(x, x)

[0178] x, _ = self.lstm(x)

[0179] x = self.fc(x[:, -1, :])

[0180] return x .

[0181] ‌Training parameters‌:

[0182] Optimizer: AdamW (lr=1e-4, weight_decay=0.01);

[0183] Loss function: Focal Loss (γ=2, α=0.25);

[0184] Training period: 200 epochs (early stopping strategy: no improvement after 10 epochs).

[0185] like Figure 5 The training process shown:

[0186] 1. Data Preprocessing

[0187] The pressure distribution data is normalized to the interval [0,1];

[0188] Categorical variables are encoded using One-Hot encoding;

[0189] The time series data is divided into sequence segments at 4-hour intervals.

[0190] Feature construction: The patient's historical big data is extracted through multimodal features or statistical algorithms, such as using CNN to extract image features in skin images (such as dryness / shedding / discoloration / skin lesions / lesions, etc.). The user performs feature preprocessing in advance.

[0191] By extracting the data features of each patient and then annotating the corresponding mechanical ventilation mask wearing strategy, a feature set is constructed. It can be divided into a training set and a validation set in a 7:3 ratio.

[0192] The training set is input into the Transformer-LSTM hybrid model for feature training and learning, and then the validation set is input into the model for performance verification (see the following description for indicators and verification).

[0193] Verification and deployment: Models that pass performance verification will be deployed on the system backend and put into use after parameter adjustment.

[0194] 2. Evaluation Metrics

[0195] Indicator type specific indicator achievement threshold classification performance AUROC ≥0.920.90;

[0196] The clinical adoption rate of strategy recommendation compliance is ≥85%.

[0197] 3. Verify the results:

[0198] index ‌Training Set‌ Validation set standard Strategy recommendation accuracy 92% 88% ≥85% Pressure injury prediction AUC 0.96 0.91 ≥0.90 False alarm rate (false positive) 4% 7% ≤10%

[0199] 4. Failure handling mechanism

[0200] When AUROC is lower than 0.88 for 3 consecutive rounds:

[0201] Start feature importance analysis (SHAP value evaluation);

[0202] Expand the sample size of high-risk cases (oversampling).

[0203] 5. Clinical workflow closed-loop verification

[0204] Scenario simulation (n=50 patients):

[0205] The patient wears a mask, and the flexible sensor monitors pressure in real time;

[0206] The AI ​​model analyzes data every 15 minutes and triggers an alert if the pressure in a certain area is >32 mmHg for 30 minutes.

[0207] The display splits the screen to highlight the alarm area and pushes policies such as "loosen the left headband and adjust the angle of the nose bridge pad";

[0208] After the medical staff performed the adjustments, the uniformity of pressure distribution improved to a standard deviation of <5 mmHg.

[0209] This solution achieves accurate prediction of mechanical ventilation mask-related pressure injuries through the coordinated optimization of multimodal feature fusion and time series modeling. Once deployed, the model will monitor patient data in real time and generate preventive adjustment recommendations.

[0210] (2) After the backend receives the data, it enters the data verification process:

[0211] The encrypted sampling port uses SHA-3 hash verification, with a tamper detection sensitivity of 99.7%

[0212] The HIS system interface complies with the HL7 FHIR R5 standard, and pressure data is stored in JSON format.

[0213] Administrators can input warning thresholds for various parts of the patient through the PDA: dynamic adjustment (e.g., base value 15kPa, ±20% based on patient risk assessment).

[0214] Terminal interaction design:

[0215] The API port supports the RESTful protocol, with a response time of <200ms;

[0216] The PDA client displays a three-dimensional pressure heat map and marks high-risk areas (red warning).

[0217] (3) Message middleware, used to send warning signals of corresponding parts of the patient and recommend corresponding wearing status adjustment strategies to the display and alarm module. Kafka message middleware can be used for message sending.

[0218] On the basis of the above application, another aspect provides an application method of an intelligent pressure-reducing non-invasive mechanical ventilation mask based on flexible pressure sensing technology, the method comprising:

[0219] Put on a mechanical ventilation mask for the patient and activate it, establish wireless communication with the mask status AI analysis system, and bind the device ID of the mechanical ventilation mask and the patient's visit ID to the mask status AI analysis system;

[0220] The system issues a sampling instruction, notifying the mechanical ventilation mask to start sampling:

[0221] The flexible pressure sensor senses the pressure size and distribution signals of each part and feeds them back to the signal acquisition and processing module in real time;

[0222] The signal acquisition and processing module receives the pressure and distribution signals of each part and performs signal preprocessing and digital-to-analog conversion to obtain the pressure and distribution data of each part and transmit them to the wireless module in real time;

[0223] The pressure size and distribution data of each part are uploaded to the mask status AI analysis system in real time through the wireless module;

[0224] After receiving and recording the pressure size and distribution data of various parts of the patient, the mask status AI analysis system performs pressure injury prevention analysis on the pressure size and distribution data of various parts of the patient through the preset pressure injury prevention analysis model. If any part is found to have excessive pressure, it will issue a warning signal for the corresponding part and recommend the corresponding wearing status adjustment strategy to the display and alarm module;

[0225] The display and alarm module is used to display the pressure size and distribution data of various parts of the patient's face through split-screen technology; and when the early warning prompt signal and the recommended wearing status adjustment strategy of the corresponding part are received, the split screen of the corresponding part responds to the alarm and displays the said wearing status adjustment strategy.

[0226] Please understand the specific method steps in conjunction with the description of the previous device, which will not be repeated here.

[0227] Figure 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, such as Figure 6 As shown, the electronic device 410 may include a first processor 2001 .

[0228] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0229] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0230] The following combination Figure 6 The components of the electronic device 410 are described in detail.

[0231] The first processor 2001 is the control center of the electronic device 410 and can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs).

[0232] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0233] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 6 CPU0 and CPU1 are shown in FIG.

[0234] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 6 1 and 2. The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). A processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0235] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled by the first processor 2001 for execution. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0236] Alternatively, the memory 2002 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001 or exist independently and accessed through the interface circuit ( Figure 6 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0237] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0238] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 6 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0239] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 6 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0240] It should be noted that Figure 6 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0241] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology described in the above method embodiment, and will not be repeated here.

[0242] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc.

[0243] It should also be understood that the memory in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0244] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0245] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0246] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0247] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0248] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0249] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0250] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0251] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0252] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0253] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks.

[0254] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology, characterized in that: It includes a mechanical ventilation mask, a display and alarm module, and an AI analysis system for mask status, including: (1) The mechanical ventilation mask is integrated with: Flexible pressure sensors are distributed on the mechanical ventilation mask at locations that contact the patient's face, and are used to sense the pressure and distribution signals at each location and provide real-time feedback to the signal acquisition and processing module. The signal acquisition and processing module is used to receive the pressure size and distribution signals of various parts and perform signal preprocessing and digital-to-analog conversion to obtain the pressure size and distribution data of various parts and transmit them to the wireless module in real time; A wireless module is used to communicate data with the mask status AI analysis system and upload the pressure size and distribution data of each part to the mask status AI analysis system in real time; Power supply, used for power supply; (2) Mask status AI analysis system, which is used to receive and record the pressure size and distribution data of various parts of the patient, and then perform pressure injury prevention analysis on the pressure size and distribution data of various parts of the patient through the preset pressure injury prevention analysis model. If any part is found to have a pressure value exceeding the standard, an early warning signal of the corresponding part will be issued and the corresponding wearing status adjustment strategy will be recommended to the display and alarm module; (3) a display and alarm module, which is used to display the pressure size and distribution data of various parts of the patient's face through a split-screen technology; and when a warning prompt signal and a recommended wearing state adjustment strategy are received for a corresponding part, the split-screen of the corresponding part responds to the alarm and displays the wearing state adjustment strategy; The mechanical ventilation mask is communicatively connected to the mask status AI analysis system via a wireless module; The display and alarm module is in communication with the mask status AI analysis system.

2. The intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology according to claim 1 is characterized in that: The signal acquisition and processing module includes: Signal acquisition port, used to obtain sampling signals from various parts; a microprocessor for providing signal processing services; The preprocessing module is used to provide signal preprocessing services, including an amplifier circuit, a filter circuit, and a noise reduction circuit, which respectively amplify, filter, and reduce noise on the signal; A digital-to-analog conversion module is used to perform A / D digital-to-analog conversion on the signal; A data encryption transmission port is used to transmit the processed pressure size and distribution data of each part to the wireless module after data encryption; The signal acquisition port, preprocessing module, digital-to-analog conversion module, microprocessor and data encryption transmission port are electrically connected in sequence.

3. The intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology according to claim 1 is characterized in that: The wireless module adopts one of the following wireless options: Bluetooth, WiFi, 4 / 5G, Zigbee, LoRa or NB-IoT.

4. The intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology according to claim 2 is characterized in that: The mask status AI analysis system includes: The data encryption sampling port is used to receive the pressure size and distribution data of each part and perform decryption verification to determine whether the data has been tampered with: if it has not been tampered with, the data will be sent to the HIS system; otherwise, access will be denied; The HIS system is used to construct and save the patient's electronic medical record file, and record and update the pressure size and distribution data of various parts of the patient's face into the electronic medical record file; A traversal system is used to sequentially traverse the pressure magnitude and distribution data of various parts of the patient's face from the HIS system according to a preset time window and input the data into the preset pressure injury prevention and analysis model; The AI ​​pressure injury prevention analysis model is used to perform pressure injury prevention analysis on the input pressure size and distribution data of various parts of the patient. If any part is found to have excessive pressure values, it will output a warning signal for the corresponding part and recommend a corresponding wearing status adjustment strategy. The HIS system will record and update it in the patient's electronic medical record; The message middleware is used to send the early warning prompt signal of the corresponding part of the patient and recommend the corresponding wearing status adjustment strategy to the display and alarm module.

5. The intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology according to claim 4 is characterized in that: The mask status AI analysis system further includes: The terminal API port is used to provide a nursing terminal PDA / EDA access port, receive the pressure threshold of the corresponding part of the patient input by the nursing terminal PDA / EDA and write it into the patient's electronic medical record file in the HIS system.

6. The intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology according to claim 4 is characterized in that: The method for generating the pressure injury AI prevention analysis model includes: Collect historical intervention data from several patients wearing mechanical ventilation masks for respiratory therapy, including pressure and distribution data for various parts of the patient's body. The following risk factors were assessed for the patients: Braden score, basic patient factors, mask wearing factors, high-risk areas, and skin conditions, and the wearing status adjustment strategies implemented for the patients. Characterizing the historical intervention big data, constructing a feature set consisting of the feature data of each patient, and dividing it into a training set and a validation set according to a preset ratio; The training set is input into a preset Transformer-LSTM hybrid model to train and learn the characteristic data of each patient to generate the initial pressure injury AI prevention and analysis model; The validation set was used to verify the performance of the pressure injury prevention analysis model in analyzing excessive pressure values ​​in corresponding parts and recommending corresponding wearing state adjustment strategies: If the verification is passed, the pressure injury AI prevention analysis model is deployed and applied to the mask status AI analysis system; On the contrary, the pressure injury AI prevention analysis model is reconstructed.

7. A method for using the intelligent decompression non-invasive mechanical ventilation mask based on flexible pressure sensing technology according to any one of claims 1 to 6, characterized in that: The method comprises: Put on a mechanical ventilation mask for the patient and activate it, establish wireless communication with the mask status AI analysis system, and bind the device ID of the mechanical ventilation mask and the patient's visit ID to the mask status AI analysis system; The system issues a sampling instruction, notifying the mechanical ventilation mask to start sampling: The flexible pressure sensor senses the pressure size and distribution signals of each part and feeds them back to the signal acquisition and processing module in real time; The signal acquisition and processing module receives the pressure and distribution signals of each part and performs signal preprocessing and digital-to-analog conversion to obtain the pressure and distribution data of each part and transmit them to the wireless module in real time; The pressure size and distribution data of each part are uploaded to the mask status AI analysis system in real time through the wireless module; After receiving and recording the pressure size and distribution data of various parts of the patient, the mask status AI analysis system performs pressure injury prevention analysis on the pressure size and distribution data of various parts of the patient through the preset pressure injury prevention analysis model. If any part is found to have excessive pressure, it will issue a warning signal for the corresponding part and recommend the corresponding wearing status adjustment strategy to the display and alarm module; The display and alarm module is used to display the pressure size and distribution data of various parts of the patient's face through split-screen technology; and when the early warning prompt signal and the recommended wearing status adjustment strategy of the corresponding part are received, the split screen of the corresponding part responds to the alarm and displays the said wearing status adjustment strategy.

8. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to claim 7 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, which can be called by a processor to execute the method according to claim 7.

Images