An intelligent respiratory support and airway clearance auxiliary system, method, device and storage medium

Abstract

The present invention discloses an intelligent respiratory support and airway clearance auxiliary system, method, device and storage medium, which relates to the field of medical data processing technology. The data acquisition module is used to obtain real-time parameter data; the respiratory analysis unit analyzes the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data; the lung image data analysis unit intelligently analyzes the lung auscultation image data to identify the lung sputum blockage; the ventilator waveform analysis unit identifies abnormal waveform data based on the waveform data of the ventilator; the airway clearance module is used to determine whether it is necessary to start the Ilohen expectoration breathing mode according to the intelligent analysis results. The present invention uses advanced data processing technology and algorithms to monitor the patient's breathing in real time, and promptly discover and deal with airway problems. Through systematic data collection and analysis, the efficiency and accuracy of airway clearance are improved, the patient's treatment effect is improved, and the patient can actively expectorate while using a ventilator.

Description

Technical Field

[0001] The present invention relates to the field of medical data processing technology, and more specifically to an intelligent respiratory support and airway clearance auxiliary system, method, device and storage medium. Background Art

[0002] Respiratory diseases are common and frequently occurring diseases, with the main lesions in the trachea, bronchi, lungs and chest cavity. Those with mild lesions often experience coughing, chest pain and affected breathing, while those with severe lesions may experience difficulty breathing, hypoxia, or even respiratory failure and death. Especially in elderly patients with a long course of illness, or even long-term bed rest, sputum can easily accumulate at the bottom of the lungs, making it more difficult to cough up the sputum, which can easily lead to secondary bacterial infection. In the later stages of the disease, patients cannot lie flat due to extremely poor cardiopulmonary function and can only sit upright or lie prone to relieve discomfort such as chest tightness and difficulty breathing. Usually, others are needed to help the patient pat his back to loosen the sputum, and then ask the patient to cough hard. However, patting the back all the time invisibly increases the workload of others, and when the patient coughs up the sputum, there is nowhere to store it, and spitting at will pollutes the environment.

[0003] However, when setting the gear of the sputum removal machine in the prior art, the doctor needs to set it according to the patient's vital sign data before each sputum removal care. The patient's vital sign data refers to the patient's weight, heart rate, blood pressure, respiratory rate, breathing depth and other data in multiple dimensions. It is overly dependent on the doctor's experience. It is easy for inexperienced doctors to make inaccurate judgments, which affects the patient's care effect, increases the workload of medical staff, and reduces care efficiency.

[0004] Therefore, how to provide an intelligent respiratory support and airway clearance auxiliary system, method, equipment and storage medium, using advanced data processing technology and algorithms to monitor the patient's breathing condition in real time, and promptly detect and deal with airway problems is an issue that technical personnel in this field urgently need to solve. Summary of the invention

[0005] In view of this, the present invention provides an intelligent respiratory support and airway clearance auxiliary system, method, device and storage medium, which uses advanced data processing technology and algorithms to monitor the patient's respiratory condition in real time, and promptly detect and deal with airway problems. Through systematic data collection and analysis, the efficiency and accuracy of airway clearance are improved, the treatment effect of patients is improved, and patients can actively expectorate while using a ventilator, which solves the problem of sputum stickiness and embolism during ventilation, and greatly reduces the risk of patients being stuck by sputum.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: an intelligent respiratory support and airway clearance auxiliary system, comprising:

[0007] A data acquisition module, used to acquire real-time parameter data; the real-time parameter data includes one or more of the patient type, the patient's blood oxygen saturation, oxygen partial pressure, carbon dioxide partial pressure data, lung auscultation image data, and ventilator waveform data; the patient type includes adults, children, and newborns;

[0008] An intelligent analysis module, used for analyzing the real-time parameter data according to the patient type;

[0009] The intelligent analysis module includes a breathing analysis unit, a lung image data analysis unit and a ventilator waveform analysis unit; the breathing analysis unit analyzes the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data to determine the patient's current breathing state; the lung image data analysis unit intelligently analyzes the lung auscultation image data to identify the lung sputum blockage; the ventilator waveform analysis unit identifies abnormal waveform data based on the waveform data of the ventilator and determines the current water accumulation in the pipeline; it helps medical staff to quickly and accurately assess the patient's breathing condition and detect abnormal conditions in time;

[0010] The airway clearance module is used to determine whether it is necessary to start the Ilohen expectoration breathing mode based on the intelligent analysis results;

[0011] The model prediction module is used to build a regression model based on the patient's current respiratory state, lung sputum blockage and current pipeline water accumulation, and to fuse the characteristics of various parameter data to obtain a comprehensive characteristic value;

[0012] The judgment module is used to judge whether the warning value is reached based on the comprehensive characteristic value, and when the warning value is reached, notify the medical staff to perform manual processing.

[0013] Preferably, the breathing state includes normal breathing frequency and abnormal breathing frequency;

[0014] When the analysis determines that the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data are all within the normal range, the current patient's breathing state is normal breathing frequency;

[0015] When the analysis determines that any one of the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data is within the abnormal range, the current patient's respiratory state is an abnormal respiratory frequency; at this time, the Ilohen sputum removal breathing mode is started, and the ventilator parameters are adjusted according to the real-time acquired blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data.

[0016] Preferably, the lung image data analysis unit comprises:

[0017] A data acquisition subunit, used for acquiring the patient's lung imaging data in real time;

[0018] The data processing subunit is used to perform intelligent analysis and processing on the lung image data, determine the current bronchopulmonary obstruction rate, and when the bronchopulmonary obstruction rate is greater than a preset threshold, start the Ilohen expectoration breathing mode and adjust the ventilator parameters according to the real-time determined bronchopulmonary obstruction rate.

[0019] Preferably, intelligent analysis and processing of the lung image data to determine the current bronchopulmonary obstruction rate includes:

[0020] Obtaining an original pixel matrix according to the lung image data;

[0021] Determine the bronchopulmonary obstruction area in the lung image data based on the adjacency relationship of the four neighborhoods, mark the bronchopulmonary obstruction area, and obtain the obstruction area pixel matrix of the bronchopulmonary obstruction area;

[0022] The bronchopulmonary obstruction rate is calculated based on the original pixel matrix and the obstruction area pixel matrix.

[0023] Preferably, determining the bronchopulmonary obstruction region in the lung image data based on the adjacency relationship of the four neighborhoods and marking the bronchopulmonary obstruction region includes:

[0024] The patient's bronchial region is marked according to the lung imaging data of the patient in a normal state based on the adjacency relationship of the four neighbors;

[0025] Determine the similarity threshold range. For each pixel, traverse its four neighboring pixels and compare the grayscale values ​​with the current pixel respectively.

[0026] If the gray value difference between the current pixel and a neighboring pixel is within the similarity threshold, they are marked as the same area; if not, they are marked as different areas;

[0027] For the newly marked neighboring pixel, continue to traverse its four neighboring pixels and recursively compare the grayscale values ​​and mark the area;

[0028] Continue to repeat the above steps until all pixels are processed and the bronchial area of ​​the patient is determined;

[0029] Similarly, the bronchopulmonary obstruction areas in the bronchial region are determined and marked.

[0030] Preferably, the ventilator waveform analysis unit identifies abnormal waveform data based on the waveform data of the ventilator and determines the current water accumulation in the pipeline, including:

[0031] A waveform acquisition subunit, used to acquire respiratory waveform data of the patient;

[0032] The waveform processing subunit is used to perform intelligent analysis and processing on the respiratory waveform data, identify abnormal waveform data, and when abnormal waveform data is identified, start the Ilohen expectoration breathing mode and adjust the ventilator parameters according to the respiratory waveform data acquired in real time.

[0033] Preferably, the Ilohen expectoration breathing mode includes: superimposing high-frequency oscillation ventilation on the basis of the normal frequency positive pressure ventilation mode to form a new ventilation waveform with foam-driven expectoration; the new ventilation waveform can foam the sputum in the diseased alveoli, and the foam mucus is discharged from the alveoli along with the normal frequency positive pressure part;

[0034] The normal frequency positive pressure ventilation mode includes an intermittent command ventilation mode or a controlled command ventilation mode.

[0035] Preferably, an intelligent respiratory support and airway clearance auxiliary method comprises:

[0036] Acquire real-time parameter data; the real-time parameter data includes one or more of the patient type, the patient's blood oxygen saturation, oxygen partial pressure, carbon dioxide partial pressure data, lung auscultation image data, and ventilator waveform data;

[0037] Analyze the real-time parameter data according to the patient type: analyze the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data to determine the patient's current respiratory state; perform intelligent analysis on the lung auscultation image data to identify lung sputum blockage; based on the waveform data of the ventilator, identify abnormal waveform data and determine the current water accumulation in the pipeline;

[0038] According to the intelligent analysis results, determine whether it is necessary to start the Ilohen expectoration breathing mode;

[0039] A regression model based on the patient's current respiratory status, lung sputum blockage, and current water accumulation in the pipeline is constructed, and the characteristics of various parameter data are fused to obtain a comprehensive characteristic value;

[0040] Based on the comprehensive characteristic value, it is determined whether a warning value has been reached. When the warning value has been reached, medical personnel are notified to perform manual processing.

[0041] Preferably, an electronic device comprises:

[0042] at least one processor; and,

[0043] a memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned intelligent breathing support and airway clearance assistance method.

[0045] Preferably, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned intelligent breathing support and airway clearance assistance method is implemented.

[0046] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses an intelligent respiratory support and airway clearance auxiliary system, method, device and storage medium, including: a data acquisition module, used to acquire real-time parameter data; the real-time parameter data includes one or more of the patient type, the patient's blood oxygen saturation, oxygen partial pressure, carbon dioxide partial pressure data, lung auscultation image data and ventilator waveform data; an intelligent analysis module, used to analyze the real-time parameter data according to the patient type; the intelligent analysis module includes a respiratory analysis unit, a lung image data analysis unit and a ventilator waveform analysis unit; the respiratory analysis unit analyzes the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data to determine the patient's current respiratory state; the lung The image data analysis unit performs intelligent analysis on the lung auscultation image data to identify the pulmonary sputum blockage; the ventilator waveform analysis unit identifies abnormal waveform data based on the waveform data of the ventilator and determines the current water accumulation in the pipeline; helps medical staff to quickly and accurately evaluate the patient's respiratory condition and find abnormal conditions in time; the airway clearance module is used to determine whether it is necessary to start the Ilohen expectoration breathing mode according to the intelligent analysis results; the model prediction module is used to construct a regression model based on the patient's current respiratory state, pulmonary sputum blockage and current water accumulation in the pipeline, and perform feature fusion on various parameter data to obtain a comprehensive feature value; the judgment module is used to judge whether the warning value is reached based on the comprehensive feature value, and when the warning value is reached, the medical staff is notified to perform manual processing. The present invention uses advanced data processing technology and algorithms to monitor the patient's respiratory condition in real time, and timely discover and deal with airway problems. Through systematic data collection and analysis, the efficiency and accuracy of airway clearance are improved, the treatment effect of the patient is improved, and the patient can actively expectorate while using the ventilator, which solves the problem of sputum viscosity embolism during the patient's ventilation and greatly reduces the risk of the patient being stuck by sputum. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0048] Figure 1 A schematic diagram of the structure of an intelligent respiratory support and airway clearance auxiliary system provided by the present invention.

[0049] Figure 2 A schematic flow chart of an intelligent respiratory support and airway clearance auxiliary method provided by the present invention.

[0050] FIG. 3( a ) is a schematic diagram of the necking separation mechanism—gas formation provided in an embodiment of the present invention.

[0051] FIG3( b ) is a schematic diagram of bubble formation in the necking separation mechanism provided in an embodiment of the present invention.

[0052] Figure 4 A schematic diagram of a Y-shaped network structure formed by the bronchi at various levels provided in an embodiment of the present invention.

[0053] Figure 5 A schematic diagram of the principle of generating microbubbles in a T-shaped microchannel provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] The embodiment of the present invention discloses an intelligent respiratory support and airway clearance auxiliary system, method, device and storage medium, which uses advanced data processing technology and algorithms to monitor the patient's respiratory condition in real time, and promptly discover and deal with airway problems. Through systematic data collection and analysis, the efficiency and accuracy of airway clearance are improved, the patient's treatment effect is improved, and the patient can actively expectorate while using a ventilator, which solves the problem of sputum viscosity and embolism during the patient's ventilation, and greatly reduces the risk of the patient being stuck by sputum.

[0056] The embodiment of the present invention discloses an intelligent respiratory support and airway clearance auxiliary system, such as Figure 1 As shown, including:

[0057] A data acquisition module, used to acquire real-time parameter data; the real-time parameter data includes one or more of the patient type, the patient's blood oxygen saturation, oxygen partial pressure, carbon dioxide partial pressure data, lung auscultation image data, and ventilator waveform data; the patient type includes adults, children, and newborns;

[0058] An intelligent analysis module, used for analyzing the real-time parameter data according to the patient type;

[0059] The intelligent analysis module includes a breathing analysis unit, a lung image data analysis unit and a ventilator waveform analysis unit; the breathing analysis unit analyzes the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data to determine the patient's current breathing state; the lung image data analysis unit intelligently analyzes the lung auscultation image data to identify the lung sputum blockage; the ventilator waveform analysis unit identifies abnormal waveform data based on the waveform data of the ventilator and determines the current water accumulation in the pipeline; it helps medical staff to quickly and accurately assess the patient's breathing condition and detect abnormal conditions in time;

[0060] The airway clearance module is used to determine whether it is necessary to start the Ilohen expectoration breathing mode based on the intelligent analysis results;

[0061] The model prediction module is used to build a regression model based on the patient's current respiratory state, lung sputum blockage and current pipeline water accumulation, and to fuse the characteristics of various parameter data to obtain a comprehensive characteristic value;

[0062] The judgment module is used to judge whether the warning value is reached based on the comprehensive characteristic value, and when the warning value is reached, notify the medical staff to perform manual processing.

[0063] Specifically, feature extraction methods such as statistical features, frequency domain features, time domain features, etc. are used to convert raw data into feature vectors. These feature data are then input into the regression model for training to estimate target values ​​related to these parameters. When training the model, the correlation between features is considered, and feature fusion is performed to obtain more representative and efficient comprehensive feature values.

[0064] Specifically, the breathing state includes normal breathing frequency and abnormal breathing frequency;

[0065] When the analysis determines that the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data are all within the normal range, the current patient's breathing state is normal breathing frequency;

[0066] When the analysis determines that any one of the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data is within the abnormal range, the current patient's respiratory state is an abnormal respiratory frequency; at this time, the Ilohen sputum removal breathing mode is started, and the ventilator parameters are adjusted according to the real-time acquired blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data.

[0067] Normal breathing rate: Under normal circumstances, the transcutaneous oxygen saturation (SpO2) should be maintained at 93-97%. When SpO2 is greater than 97%, the system automatically adjusts down to the lowest oxygen concentration (FiO2) when maintaining 97%. The normal range of oxygen partial pressure (PaO2) is between 80-120 mmHg. The normal range of carbon dioxide partial pressure (PaCO2) is between 35-45 mmHg.

[0068] Abnormal breathing rate: Any breathing rate that is not within the normal breathing rate range is considered abnormal breathing rate.

[0069] Specifically, the lung image data analysis unit includes:

[0070] A data acquisition subunit, used for acquiring the patient's lung imaging data in real time;

[0071] The data processing subunit is used to perform intelligent analysis and processing on the lung image data, determine the current bronchopulmonary obstruction rate, and when the bronchopulmonary obstruction rate is greater than a preset threshold, start the Ilohen expectoration breathing mode and adjust the ventilator parameters according to the real-time determined bronchopulmonary obstruction rate.

[0072] Specifically, intelligently analyzing and processing the lung image data to determine the current bronchopulmonary obstruction rate includes:

[0073] Obtaining an original pixel matrix according to the lung image data;

[0074] Determine the bronchopulmonary obstruction area in the lung image data based on the adjacency relationship of the four neighborhoods, mark the bronchopulmonary obstruction area, and obtain the obstruction area pixel matrix of the bronchopulmonary obstruction area;

[0075] The bronchopulmonary obstruction rate is calculated based on the original pixel matrix and the obstruction area pixel matrix.

[0076] Specifically, the bronchopulmonary obstruction region in the lung image data is determined based on the adjacency relationship of the four neighborhoods, and the bronchopulmonary obstruction region is marked, including:

[0077] The patient's bronchial region is marked according to the lung imaging data of the patient in a normal state based on the adjacency relationship of the four neighbors;

[0078] Determine the similarity threshold range and judge whether the grayscale values ​​of two pixels are within the similarity threshold range; the selection of the similarity threshold is adjusted according to the grayscale value characteristics of the lung image data and the bronchial area, and a suitable grayscale value difference range is selected; for each pixel, traverse its four neighboring pixels and compare the grayscale values ​​with the current pixel respectively;

[0079] If the gray value difference between the current pixel and a neighboring pixel is within the similarity threshold, they are marked as the same area; if not, they are marked as different areas;

[0080] For the newly marked neighboring pixel, continue to traverse its four neighboring pixels and recursively compare the grayscale values ​​and mark the area;

[0081] Continue to repeat the above steps until all pixels are processed and the bronchial area of ​​the patient is determined;

[0082] Similarly, the bronchopulmonary obstruction areas in the bronchial region are determined and marked.

[0083] Specifically, for each pixel, check whether its four neighboring pixels have similar grayscale values ​​(expressed as a similarity threshold). If the similarity passes the threshold, they are considered to belong to the same area. By traversing all pixels, pixels belonging to the same area are continuously merged until all pixels are processed. According to the merged pixel area, the position and size of the bronchopulmonary obstruction area are determined. Determine whether it is a bronchopulmonary obstruction area based on the area of ​​the area. Mark the pixels in the bronchopulmonary obstruction area with a specific value, such as 255 (white), and the remaining pixels retain the original grayscale value. Finally, the pixel matrix of the obstruction area of ​​the bronchopulmonary obstruction area is obtained, and the shape and position of the bronchopulmonary obstruction area can be viewed by displaying the marked pixel matrix. The bronchopulmonary obstruction area and the bronchial area are marked with different values.

[0084] Specifically, when the bronchopulmonary obstruction rate is ≥40%, the system starts the Ilohen expectoration breathing mode, which is a normal frequency positive pressure ventilation superimposed with a low amplitude high frequency oscillation ventilation mode, and has the function of foaming and then discharging sputum; at the same time, the valve of the expectoration pipeline is opened, and the oscillation amplitude is increased by ±2cmH2O for every 10% increase according to the degree of obstruction, up to ±30cmH2O; when the bronchopulmonary obstruction rate is greater than 30%, the ventilator automatically starts the Ilohen expectoration breathing mode by default, and automatically opens the valve of the expectoration pipeline 15 minutes after the Ilohen expectoration breathing mode is turned on;

[0085] Specifically, the combination of respiratory support modes with expectoration function in Ilohen expectoration breathing mode is mainly: high-frequency oscillation ventilation (HFOV) is superimposed on the normal frequency positive pressure ventilation mode without triggering state; the normal frequency positive pressure ventilation mode mainly includes intermittent mandatory ventilation mode (IPPV mode) / and controlled mandatory ventilation mode (CMV mode). A protective lung ventilation strategy is adopted to limit the maximum pressure to prevent ventilator-related lung injury and large airway air leakage.

[0086] This breathing mode provides constant frequency positive pressure expiratory and inspiratory pressure airflow to open the patient's small airways and alveoli, achieve basic ventilation, and expel CO2; at the same time, high-frequency oscillating airflow with a superimposed small tidal volume enters and exits the alveoli. Due to the decrease in alveolar compliance in the inflamed area, the time constant (τ) decreases, and the frequency is close to that of the high-frequency oscillating airflow with a small tidal volume, so resonance occurs and a larger amplitude is achieved; the minute ventilation of this part of the alveoli is increased, improving alveolar ventilation in the inflamed area; at the same time, the high-frequency oscillating airflow mixes with the exudate mucus in the alveoli and small airways, and a large amount of foam is generated through mechanisms such as necking separation, as shown in Figures 3(a) and 3(b), which are schematic diagrams of the formation of foam by airflow through the alveolar orifice in the necking separation mechanism. The holes in the figure are a model diagram of the alveolar epithelium and the alveolar opening, with gas passing through the alveolar opening. The scattered areas are areas containing mucus in the diseased alveoli. The mucus volume (V) expands and moves in the alveoli, and the density (ρ) and viscosity of the mixed mucus decrease (μ). It can be expelled under the action of the lower expiratory pressure of the ventilator's normal frequency positive pressure. Since the inhalation time is short and the exhalation time is long, the sputum is gradually discharged from the alveoli-small airways-large airways with breathing. In this way, the normal respiratory cycle is changed from two strokes of inspiration-exhalation to four strokes of inspiration-compression-foaming oscillation-expiration and sputum removal. The process of the ventilator removing mucus in the diseased alveoli is completed. Figure 4 As shown in the figure, since the pulmonary lobule is gathered into a T-shaped tube above the alveolar duct, both high-frequency and normal-frequency airflows participate in the formation of mucus foam in the T-shaped tube or Y-shaped tube; at the same time, they resonate with high-frequency cilia to assist in expectoration; Figure 5 As shown, Figure 5 This is a schematic diagram of the generation of microbubbles in a T-shaped microchannel. The T-tube is a simplified local diagram. Mucus flows on one side of the T-tube, and air flows into the other side to generate bubbles. At this time, the bubbles are affected by the combined effects of gas dynamics, surface tension, liquid thrust, and inertial force. Driven by exhalation, mucus migrates further. In the large airways, it is the last "kilometer" of sputum migration. Under non-invasive conditions, mucus migration uses the three-way structure of the throat, nose, and throat, and is coughed out through assisted coughing; under invasive conditions, the improvement of the tracheal tube pipeline is used to add a positioning sputum tube, shorten the migration distance, and achieve liquid-gas separation and sputum removal in the tracheal tube. Combined with technical techniques such as the leak compensation mechanism of the ventilator, the pressure in the lungs is maintained to prevent the collapse of diseased alveoli.

[0087] Specifically, during the operation of the embodiment of the present invention, the system measures, controls and calculates the following parameters of the ventilator in real time:

[0088] Output gas flow [QV(t)], ventilator circuit Y-end pressure (calculated value) P(t), leakage flow [QMLEAK(t)], respiratory gas flow of the ventilation object [Q(t)], inspiratory time (Ti), expiratory time (Te), number of breaths per minute (Breaths Per Minute, BPM), real-time inspiratory pressure [IPAP(t)], real-time expiratory pressure [EPAP(t)], etc.

[0089] IPAP(t) and EPAP(t) are the real-time output pressures of the ventilator at a certain moment t, which are the oscillatory pressure POSC superimposed on IPAP and EPAP. The total airway resistance R is generally expressed as Z(R, I, C), which is the airway impedance (including viscous air resistance R, inertial air resistance I and compliance C). The calculation methods of the respiratory ratio I:E, respiratory cycle T, tidal volume (inhalation and exhalation) VT, and minute ventilation MV are as follows:

[0090] I:E=Ti:Te;

[0091] T=Ti+Te;

[0092]

[0093]

[0094] Based on the design of the corresponding IPPV / CMV superimposed HFOV Elohim MODE, in order to achieve the sinusoidal oscillation air pressure P EW The output of the oscillation signal is realized by using the iterative algorithm shown below (including two multiplications and one subtraction operation), and the ratio of the inhalation time to the exhalation time of the oscillation is 1:1.

[0095] Y [n] =A sin B;

[0096] Y [n] =2A cosB×Y [n-1] -Y [n-2] ;

[0097]

[0098] PEW=Y [n] ;

[0099] Among them, A is the amplitude of the sine wave oscillation, f s is the sampling frequency (step frequency, the embodiment of the present invention is designed to be 2ms (500Hz)), f o is the output sine wave frequency, n is the step count, Y[n] , Y [n-1] and Y [n-2] They represent the outputs of the nth step, the n-1th step, and the n-2th step, respectively. In order to further improve the resource utilization of the calculation, when the step frequency f s and signal frequency f o After confirmation, the program calculates and outputs the Y of one oscillation cycle according to the above formula in advance. [n] The data table is stored in the memory, and then the data table lookup algorithm is used during the oscillation output process to avoid multiplication operations.

[0100] Specifically, during operation, the tidal volume and ventilation frequency of normal frequency ventilation are dynamically adjusted by measuring the end-tidal CO2 partial pressure. In normal frequency ventilation, the carbon dioxide clearance rate (DCO2) is proportional to the minute ventilation (MV).

[0101] Since a new ventilation waveform is formed after IPPV / CMV is superimposed with a lower amplitude HFOV below 15cmH2O, it has the function of foaming the sputum in the diseased alveoli, and the foamy mucus is discharged from the alveoli along with the normal frequency positive pressure part, the embodiment of the present invention is called the Elohim sputum expulsion breathing mode (ELOHIM Mode). In addition to the above situation, DCO2 is also related to the frequency (f) and tidal volume (V) of HFOV. tHF ) is proportional to the square of . The specific algorithm is as follows:

[0102] In IPPV / CMV mode:

[0103] In ELOHIM mode:

[0104] Where A1 is the correlation coefficient of DCO2 for IPPV / CMV; A2 is the correlation coefficient of DCO2 for HFOV.

[0105] Specifically, the ventilator waveform analysis unit identifies abnormal waveform data based on the waveform data of the ventilator and determines the current water accumulation in the pipeline, including:

[0106] A waveform acquisition subunit, used to acquire respiratory waveform data of the patient;

[0107] The waveform processing subunit is used to perform intelligent analysis and processing on the respiratory waveform data, identify abnormal waveform data, and when abnormal waveform data is identified, start the Ilohen expectoration breathing mode and adjust the ventilator parameters according to the respiratory waveform data acquired in real time.

[0108] Specifically, real-time respiratory waveform data is received from ventilator sensors or other monitoring devices, the waveform data is converted into digital signals, and stored or sent to the waveform processing subunit for subsequent processing, ensuring the accuracy and reliability of the data.

[0109] The waveform processing subunit analyzes the respiratory waveform data, detects abnormal waveform features, and identifies possible abnormal conditions, such as apnea, dyspnea, etc. When abnormal waveform data is identified, the Ilohen expectoration breathing mode is activated according to the preset processing strategy to assist ventilation;

[0110] The patient's respiratory waveform data is monitored in real time and compared with the preset reference values. The ventilator parameters (such as respiratory rate, tidal volume, etc.) are adjusted according to the real-time data to ensure that the patient receives appropriate ventilation support.

[0111] Specifically, the waveform processing subunit analyzes the respiratory waveform data and detects abnormal waveform features, including:

[0112] Calculating the fluctuation rate according to the respiratory waveform data, wherein the respiratory waveform data is a respiratory waveform of a preset time length for the patient, and the fluctuation rate is used to indicate the degree of fluctuation of the respiratory waveform data, wherein the fluctuation rate is obtained by caching the respiratory waveform data for a period of time, and making a comprehensive judgment based on the number of rise and fall changes of the waveform during the period of time, the unidirectional jump amplitude, the number of occurrences of each jump amplitude, and the respiratory change rate.

[0113] Detecting abnormal waveform features of the respiratory waveform based on the respiratory waveform data and the fluctuation rate;

[0114] If the value of the fluctuation rate is determined to be 1, it means that the fluctuation degree of the respiratory waveform data is large, and it is detected as an abnormal waveform feature;

[0115] If it is determined that the value of the fluctuation rate is 0, it means that the fluctuation degree of the respiratory waveform data is small, and the waveform characteristics are normal at this time.

[0116] Specifically, the Ilohen expectoration breathing mode includes: superimposing high-frequency oscillation ventilation on the basis of the normal frequency positive pressure ventilation mode to form a new ventilation waveform with foam-driven expectoration; the new ventilation waveform can foam the sputum in the diseased alveoli, and the foamy mucus is discharged from the alveoli along with the normal frequency positive pressure part;

[0117] The normal frequency positive pressure ventilation mode includes an intermittent command ventilation mode or a controlled command ventilation mode.

[0118] The embodiment of the present invention also discloses an intelligent respiratory support and airway clearance auxiliary method, such as Figure 2 As shown, including:

[0119] Acquire real-time parameter data; the real-time parameter data includes one or more of the patient type, the patient's blood oxygen saturation, oxygen partial pressure, carbon dioxide partial pressure data, lung auscultation image data, and ventilator waveform data;

[0120] Analyze the real-time parameter data according to the patient type: analyze the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data to determine the patient's current respiratory state; perform intelligent analysis on the lung auscultation image data to identify lung sputum blockage; based on the waveform data of the ventilator, identify abnormal waveform data and determine the current water accumulation in the pipeline;

[0121] According to the intelligent analysis results, determine whether it is necessary to start the Ilohen expectoration breathing mode;

[0122] A regression model based on the patient's current respiratory status, lung sputum blockage, and current water accumulation in the pipeline is constructed, and the characteristics of various parameter data are fused to obtain a comprehensive characteristic value;

[0123] Based on the comprehensive characteristic value, it is determined whether the warning value has been reached. When the warning value has been reached, the medical staff is notified to perform manual treatment. The comprehensive characteristic value can make a comprehensive judgment on the patient's respiratory condition. When the patient's respiratory condition is unstable, an early warning is issued in time to notify the medical staff, helping the medical staff to respond and handle the patient's condition more promptly and accurately. By integrating data analysis, feature extraction and early warning systems, an intelligent medical assistance system is realized.

[0124] The embodiment of the present invention further discloses an electronic device, the electronic device comprising:

[0125] at least one processor; and,

[0126] a memory communicatively connected to the at least one processor; wherein,

[0127] The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned intelligent breathing support and airway clearance assistance method.

[0128] The embodiment of the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the above-mentioned intelligent respiratory support and airway clearance auxiliary method is implemented.

[0129] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0130] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent respiratory support and airway clearance auxiliary system, characterized in that: include: A data acquisition module, used to acquire real-time parameter data; The real-time parameter data includes one or more of the patient type, the patient's blood oxygen saturation, oxygen partial pressure, carbon dioxide partial pressure data, lung auscultation image data, and ventilator waveform data; An intelligent analysis module, used for analyzing the real-time parameter data according to the patient type; The intelligent analysis module includes a breathing analysis unit, a lung image data analysis unit and a ventilator waveform analysis unit; the breathing analysis unit analyzes the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data to determine the patient's current breathing state; The lung image data analysis unit intelligently analyzes the lung auscultation image data to identify the lung sputum blockage situation; the ventilator waveform analysis unit identifies abnormal waveform data based on the waveform data of the ventilator and determines the current pipeline water accumulation situation; The airway clearance module is used to determine whether it is necessary to start the Ilohen expectoration breathing mode based on the intelligent analysis results; The model prediction module is used to build a regression model based on the patient's current respiratory state, lung sputum blockage and current pipeline water accumulation, and to fuse the characteristics of various parameter data to obtain a comprehensive characteristic value; The judgment module is used to judge whether the warning value is reached based on the comprehensive characteristic value, and when the warning value is reached, notify the medical staff to perform manual processing.

2. An intelligent respiratory support and airway clearance auxiliary system according to claim 1, characterized in that: The respiratory state includes normal respiratory rate and abnormal respiratory rate; When the analysis determines that the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data are all within the normal range, the current patient's breathing state is normal breathing frequency; When the analysis determines that any of the blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data is within an abnormal range, the current patient's respiratory state is an abnormal respiratory frequency; At this time, start the Ilohen expectoration breathing mode and adjust the ventilator parameters according to the real-time blood oxygen saturation, oxygen partial pressure and carbon dioxide partial pressure data.

3. An intelligent respiratory support and airway clearance auxiliary system according to claim 1, characterized in that: The lung image data analysis unit comprises: A data acquisition subunit, used for acquiring the patient's lung imaging data in real time; The data processing subunit is used to perform intelligent analysis and processing on the lung image data, determine the current bronchopulmonary obstruction rate, and when the bronchopulmonary obstruction rate is greater than a preset threshold, start the Ilohen expectoration breathing mode and adjust the ventilator parameters according to the real-time determined bronchopulmonary obstruction rate.

4. An intelligent respiratory support and airway clearance assistance system according to claim 3, characterized in that: Intelligently analyzing and processing the lung image data to determine the current bronchopulmonary obstruction rate includes: Obtaining an original pixel matrix according to the lung image data; Determine the bronchopulmonary obstruction area in the lung image data based on the adjacency relationship of the four neighborhoods, mark the bronchopulmonary obstruction area, and obtain the obstruction area pixel matrix of the bronchopulmonary obstruction area; The bronchopulmonary obstruction rate is calculated based on the original pixel matrix and the obstruction area pixel matrix.

5. An intelligent respiratory support and airway clearance auxiliary system according to claim 4, characterized in that: The bronchopulmonary obstruction area in the lung image data is determined based on the adjacency relationship of the four neighborhoods, and the bronchopulmonary obstruction area is marked, including: The patient's bronchial region is marked according to the lung imaging data of the patient in a normal state based on the adjacency relationship of the four neighbors; Determine the similarity threshold range. For each pixel, traverse its four neighboring pixels and compare the grayscale values ​​with the current pixel respectively. If the gray value difference between the current pixel and a neighboring pixel is within the similarity threshold, they are marked as the same area; if not, they are marked as different areas; For the newly marked neighboring pixel, continue to traverse its four neighboring pixels and recursively compare the grayscale values ​​and mark the area; Continue to repeat the above steps until all pixels are processed and the bronchial area of ​​the patient is determined; Similarly, the bronchopulmonary obstruction areas in the bronchial region are determined and marked.

6. The intelligent respiratory support and airway clearance auxiliary system according to claim 1, characterized in that: The ventilator waveform analysis unit identifies abnormal waveform data based on the waveform data of the ventilator and determines the current water accumulation in the pipeline, including: A waveform acquisition subunit, used to acquire respiratory waveform data of the patient; The waveform processing subunit is used to perform intelligent analysis and processing on the respiratory waveform data, identify abnormal waveform data, and when abnormal waveform data is identified, start the Ilohen expectoration breathing mode and adjust the ventilator parameters according to the respiratory waveform data acquired in real time.

7. The intelligent respiratory support and airway clearance auxiliary system according to claim 1, characterized in that: The Ilohen expectoration breathing mode includes: superimposing high-frequency oscillation ventilation on the basis of the normal frequency positive pressure ventilation mode to form a new ventilation waveform with foam-driven expectoration; the new ventilation waveform can foam the sputum in the diseased alveoli, and the foamy mucus is discharged from the alveoli along with the normal frequency positive pressure part; The normal frequency positive pressure ventilation mode includes an intermittent command ventilation mode or a controlled command ventilation mode.

Images