Ventilator adjustment method, apparatus, system, and medium based on electrical impedance tomography

Abstract

The application discloses a ventilator adjustment method, device, system and medium based on electrical impedance imaging. The method comprises the following steps: collecting chest electrical impedance data in real time by using an EIT device; obtaining impedance values of a target lung region image based on the chest electrical impedance data; obtaining ventilator parameters by using the ventilator; inputting the ventilator parameters and the impedance values of the target lung region image into a trained mathematical model to obtain a ventilation parameter prediction value output by the trained mathematical model; and adjusting parameters of the ventilator based on the ventilation parameter prediction value. By using the method, the accuracy of ventilator parameter adjustment can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of thoracic impedance tomography, in particular to a ventilator adjustment method, device, system and medium based on electrical impedance imaging. BACKGROUND

[0002] The ventilator plays a crucial role in acute and severe respiratory support, mainly providing effective life support for patients with acute respiratory failure and severe patients.

[0003] At present, during the use of the ventilator, the ventilator parameters are mainly adjusted by relying on the clinical experience of the doctor and the observation of the physiological characteristics of the patient. However, it is difficult for the doctor to accurately grasp the ventilation of each region of the lung by relying on experience and observation alone, so relying on the clinical experience of the doctor and the observation of the physiological characteristics of the patient cannot accurately adjust the ventilator parameters, which can easily lead to problems such as insufficient or excessive ventilation in some areas. SUMMARY

[0004] The present application provides a ventilator adjustment method, device, system and medium based on electrical impedance imaging, which can improve the accuracy of ventilator parameter adjustment.

[0005] In a first aspect, the present application provides a ventilator adjustment method based on electrical impedance imaging, which comprises:

[0006] Real-time acquisition of thoracic electrical impedance data by an EIT device;

[0007] Obtaining impedance values of a target lung region image based on the thoracic electrical impedance data;

[0008] Obtaining ventilator parameters by the ventilator;

[0009] Inputting the ventilator parameters and the impedance values of the target lung region image into a trained mathematical model to obtain a ventilation parameter prediction value output by the trained mathematical model;

[0010] Parameter adjustment of the ventilator based on the ventilation parameter prediction value.

[0011] Further technical solutions are as follows:

[0012] Reconstructing the thoracic electrical impedance data by a finite element method to generate a real-time lung ventilation distribution image;

[0013] Segmenting the lung ventilation distribution image to obtain a target lung region image;

[0014] Obtaining impedance values of the target lung region image based on the thoracic electrical impedance data.

[0015] Further, the method further comprises:

[0016] The lung ventilation distribution image is denoised to obtain a denoised lung ventilation distribution image.

[0017] The lung ventilation distribution image is segmented to obtain a target lung region image, comprising:

[0018] The denoised lung ventilation distribution image is segmented to obtain a target lung region image.

[0019] Further, the method further comprises:

[0020] It is judged whether the influence of the adjusted ventilator parameter on the lung ventilation state meets the expected requirement.

[0021] If the influence of the adjusted ventilator parameter on the lung ventilation state does not meet the expected requirement, the ventilator parameter is continuously adjusted within the preset range of the ventilation parameter prediction value until the expected requirement is met.

[0022] Further, the ventilator is used to obtain a ventilator parameter, comprising:

[0023] Real-time ventilation data is collected by the ventilator.

[0024] The ventilator parameter is obtained based on the real-time ventilation data.

[0025] Further, the ventilation data includes tidal volume and airway pressure, and the ventilator parameter includes respiratory cycle and mean airway pressure, and the ventilator parameter is obtained based on the real-time ventilation data, comprising:

[0026] Based on the changes of the airway pressure and / or the tidal volume, the time points of the start and end of respiration are obtained.

[0027] Based on the time points of the start and end of respiration, the respiratory cycle is obtained.

[0028] The airway pressure of all sampling points in the respiratory cycle is obtained.

[0029] The mean airway pressure is obtained by using integral or discrete average method to calculate the mean value of the airway pressure of all sampling points in the respiratory cycle.

[0030] Further, the trained mathematical model is trained in the following way:

[0031] acquire a training set of ventilator parameters and thoracic electrical impedance data respectively by using the ventilator;

[0032] train a mathematical model to be trained by using the training set of ventilator parameters and thoracic electrical impedance data, to obtain a trained mathematical model.

[0033] In a second aspect, the present application provides a ventilator parameter adjustment device, which comprises a unit for executing any of the above methods.

[0034] In a third aspect, the present application provides a ventilator adjustment system, which comprises a memory and a processor, the memory is used to store program data, and the processor is used to execute the program data to realize the steps of any of the above methods.

[0035] In a fourth aspect, the present application provides a computer readable storage medium, which is used to store a computer program, the computer program is used to realize the steps of any of the above methods when executed by a processor.

[0036] The beneficial effects of the present application are: different from the prior art, the present application acquires thoracic electrical impedance data in real time by using an EIT device, so as to obtain impedance values of a target lung region image based on the thoracic electrical impedance data, and then inputs the impedance values of the target lung region and ventilator parameters into a trained mathematical model, uses the trained mathematical model to predict a ventilation parameter prediction value, and adjusts the ventilator based on the ventilation parameter prediction value. Since the ventilation parameter prediction value is predicted by the trained mathematical model based on the thoracic electrical impedance data acquired in real time by the EIT device, the ventilation parameter prediction value can be considered as the best ventilation parameter under the current breathing state, so that the accuracy of the ventilator parameter adjustment can be improved by adjusting the parameters of the ventilator according to the ventilation parameter prediction value. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0038] Figure 1 is a flowchart of a first embodiment of the ventilator adjustment method based on electrical impedance imaging provided by the present application;

[0039] Figure 2 is a structural schematic diagram of an embodiment of the computer readable storage medium provided by the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than limit the present application. In addition, it should be noted that, for the convenience of description, only parts related to the present application are shown in the drawings, rather than all structures. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0041] Reference to "embodiments" herein means that the specific features, structures, or characteristics described in combination with the embodiments can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily all refer to the same embodiments, nor is it necessarily independent or alternative embodiments to other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0042] The importance and clinical value of the ventilator are as follows:

[0043] 1. Importance of ventilator

[0044] a) Treatment of acute respiratory failure: Ventilator is the core means of treating acute respiratory distress syndrome (ARDS), severe pneumonia, acute lung injury and other acute respiratory failure, which can quickly restore the ventilation and oxygenation function of patients and save lives.

[0045] b) Maintain stable vital signs: In the intensive care unit (ICU), the vital signs of many critically ill patients are unstable, and the ventilator can provide continuous mechanical ventilation support to help maintain the stability of the patient's vital signs.

[0046] c) Assist anesthesia and surgery: In general anesthesia and complex surgery, the ventilator ensures the normal operation of the patient's respiratory function, reducing the risk of respiratory failure during anesthesia and surgery.

[0047] d) Treatment of acute exacerbation of chronic respiratory diseases: For patients with acute exacerbation of chronic obstructive pulmonary disease (COPD), neuromuscular diseases and other chronic respiratory diseases, the ventilator can effectively reduce the respiratory burden and improve symptoms.

[0048] 2. Clinical value

[0049] a) Efficient ventilation support: The ventilator can provide sufficient and controllable airway pressure and ventilation volume to ensure that the patient obtains sufficient oxygen supply and carbon dioxide discharge.

[0050] b) Precise control of respiratory parameters: tidal volume, respiratory rate, inspiratory pressure, and positive end-expiratory pressure (PEEP) can be precisely adjusted to meet the individual needs of different patients.

[0051] c) Stable airway management: through tracheal intubation or tracheostomy, ensure airway patency, effectively prevent upper airway obstruction and aspiration risk.

[0052] d) Real-time monitoring and alarm: modern ventilators are equipped with advanced monitoring and alarm systems, which can monitor respiratory parameters in real time, discover and alarm abnormal conditions in time, and ensure patient safety.

[0053] e) Assist in complex cases: in complex cases that require high-level respiratory support, ventilators can provide continuous and reliable ventilation support, which cannot be replaced by other respiratory support methods.

[0054] Currently, in the process of using the ventilator, it mainly depends on the doctor's own clinical experience and observation of the patient's physiological characteristics to adjust the ventilator parameters, but it is difficult for the doctor to accurately grasp the ventilation of each region of the lung by relying on experience and observation alone. Therefore, relying on the doctor's own clinical experience and observation of the patient's physiological characteristics cannot accurately adjust the ventilator parameters, which may lead to problems such as local hyperventilation or hyperinflation.

[0055] In addition, inaccurate adjustment of ventilator parameters may lead to the following possible clinical complications:

[0056] 1. Barotrauma: due to improper ventilator parameter settings (such as excessive tidal volume or pressure), leading to overinflation of alveoli.

[0057] 2. Volume injury: mechanical damage to lung tissue due to excessive ventilation.

[0058] 3. Atelectasis: partial collapse of alveoli, usually due to inadequate or uneven ventilation.

[0059] 4. Ventilator-associated pneumonia: bacterial infection caused by long-term use of a ventilator.

[0060] 5. Respiratory fatigue and ventilator dependence: improper ventilator parameter settings may lead to excessive or insufficient burden on respiratory muscles.

[0061] 5. Hemodynamic instability: inappropriate PEEP and tidal volume settings may affect intrathoracic pressure, affecting the function of the heart and large blood vessels.

[0062] Therefore, in order to solve the above technical problems, the present application provides a ventilator adjustment method based on electrical impedance imaging, which can improve the accuracy of ventilator parameter adjustment and help reduce the probability of complications. Please refer to the following embodiments for details.

[0063] Referring to Figure 1 , Figure 1 is a flowchart of a first embodiment of a ventilator adjustment method based on electrical impedance tomography provided by the present application. The method comprises:

[0064] Step 110: acquiring chest electrical impedance data in real time by using an EIT device.

[0065] Step 120: obtaining impedance values of a target lung region image based on the chest electrical impedance data.

[0066] Step 130: obtaining ventilator parameters by using the ventilator.

[0067] Step 140: inputting the ventilator parameters and the impedance values of the target lung region image into a trained mathematical model to obtain a ventilation parameter prediction value output by the trained mathematical model.

[0068] Step 150: adjusting parameters of the ventilator based on the ventilation parameter prediction value.

[0069] In this way, the embodiment acquires chest electrical impedance data in real time by using an EIT device, so as to obtain impedance values of a target lung region image based on the chest electrical impedance data, and then inputs the impedance values of the target lung region and ventilator parameters into a trained mathematical model to predict a ventilation parameter prediction value by using the trained mathematical model, and adjusts parameters of the ventilator based on the ventilation parameter prediction value. Since the ventilation parameter prediction value is predicted by the trained mathematical model based on chest electrical impedance data acquired in real time by the EIT device, the ventilation parameter prediction value can be considered as the best ventilation parameter under the current breathing state, so that adjusting parameters of the ventilator according to the ventilation parameter prediction value can improve the accuracy of ventilator parameter adjustment.

[0070] Referring to a second embodiment of a ventilator adjustment method based on electrical impedance tomography provided by the present application. The method comprises:

[0071] Step 210: acquiring chest electrical impedance data in real time by using an EIT device.

[0072] Step 220: reconstructing the chest electrical impedance data by using a finite element method to generate a real-time lung ventilation distribution image.

[0073] Step 230: segmenting the lung ventilation distribution image to obtain a target lung region image.

[0074] Wherein, different regions of the lung can be distinguished by image segmentation methods, such as ventilation areas, restricted areas, or front, back, left, right, up and down regions, and impedance value changes, ventilation uniformity and other index information of each region can be calculated according to the chest electrical impedance data collected in real time by the EIT device.

[0075] In some embodiments, before segmenting the lung ventilation distribution image, the lung ventilation distribution image can be denoised to obtain a denoised lung ventilation distribution image, and then the denoised lung ventilation distribution image is segmented to obtain a target lung region image.

[0076] For steps 220 and 230, reconstructing the chest electrical impedance data using the finite element method can include geometric modeling, boundary condition setting, forward problem solving, and inverse problem solving. By repeatedly optimizing the conductivity distribution, the lung ventilation distribution image of the target lung region can be finally reconstructed.

[0077] Specifically, it can include the following processes:

[0078] 1) Create a geometric model of the target lung region. For example, a two-dimensional or three-dimensional grid can be defined, where the nodes and elements of the grid will be used to discretize the target lung region.

[0079] 2) Divide the geometric model into a finite number of elements (such as triangles or tetrahedrons). These elements form a finite element mesh.

[0080] 3) Place electrodes on the boundaries of the geometric model and define the positions of the applied current and measured voltage.

[0081] 4) Apply boundary conditions, including electrode positions, current injection, and voltage measurement modes.

[0082] 5) Define an objective function to measure the difference between the measured voltage and the calculated voltage.

[0083] 6) Select an appropriate optimization algorithm to minimize the objective function. Common optimization algorithms include gradient descent, Newton's method, conjugate gradient method, etc.

[0084] 7) Using the final inversion of the conductivity distribution σ, reconstruct the electrical impedance image of the target lung region, and generate the EIT image, i.e. the lung ventilation distribution image, by visualizing the conductivity distribution, to display the internal structure and features.

[0085] 8) Through the optimization process, the conductivity distribution σ is continuously adjusted to reduce the value of the objective function.

[0086] 9) Repeat the iteration until the objective function converges to an allowable error range, and obtain the final conductivity distribution map.

[0087] Thus, the ventilation state of the lung of the patient can be more intuitively understood by the doctor, so as to optimize the ventilator parameters, reduce the occurrence of complications, and improve the treatment effect.

[0088] Step 240: obtaining an impedance value of the target lung region image based on the thoracic electrical impedance data.

[0089] Step 250: obtaining ventilator parameters by using the ventilator.

[0090] In some embodiments, the ventilation data includes tidal volume and airway pressure, and the ventilator parameters include respiratory cycle and mean airway pressure.

[0091] Step 251: collecting real-time ventilation data by using the ventilator.

[0092] Step 252: obtaining ventilator parameters based on the real-time ventilation data.

[0093] In some embodiments, the ventilation data includes tidal volume and airway pressure, and the ventilator parameters include respiratory cycle and mean airway pressure.

[0094] The step of obtaining ventilator parameters based on the real-time ventilation data can include the following steps:

[0095] Step 2521: obtaining the time points of the beginning and end of respiration based on the changes of the airway pressure and / or the tidal volume.

[0096] In some embodiments, the tidal volume can represent the amount of gas inhaled or exhaled per breath, and the airway pressure can represent the pressure measured in the airway.

[0097] Because the airway pressure will increase at the beginning of inspiration, and the tidal volume will also increase, and the airway pressure will return to the PEEP level at the end of expiration, and the tidal volume will return to zero, the time points of the beginning and end of respiration can be obtained based on the changes of the airway pressure and / or the tidal volume.

[0098] Step 2522: obtaining the respiratory cycle based on the time points of the beginning and end of respiration.

[0099] In some embodiments, the respiratory cycle refers to the time required for one complete breathing process, including one inspiration and one expiration, and can be measured by measuring the time interval between the beginning of two adjacent inspirations or the end of two adjacent expirations, which can be considered as the respiratory cycle.

[0100] Step 2523: obtaining the airway pressure of all sampling points in the respiratory cycle.

[0101] Step 2524: calculating the mean value of the airway pressure of all sampling points in the respiratory cycle using the integral or discrete average method to obtain the mean airway pressure.

[0102] wherein the mean airway pressure (MAP) is an average value of the airway pressure in a breathing cycle.

[0103] In other embodiments, the ventilation data can further include positive end-expiratory pressure, and the ventilator parameters can further include peak pressure.

[0104] wherein the peak pressure is a maximum value of the airway pressure in a breathing cycle.

[0105] Step 260: inputting the ventilator parameters and the impedance value of the target lung region image into the trained mathematical model to obtain a ventilation parameter prediction value output by the trained mathematical model.

[0106] wherein a parameter feature vector can be established by chest electrical impedance data acquired by an EIT device and real-time ventilation parameters acquired by a ventilator to represent a current breathing state, and a ventilation parameter prediction value corresponding to the current breathing state is output by the trained mathematical model.

[0107] Step 270: adjusting parameters of the ventilator based on the ventilation parameter prediction value.

[0108] Referring to a third embodiment of the ventilator adjustment method based on electrical impedance imaging provided in the present application. The method comprises:

[0109] Step 310: acquiring chest electrical impedance data in real time by using an EIT device.

[0110] Step 320: obtaining an impedance value of a target lung region image based on the chest electrical impedance data.

[0111] Step 330: acquiring ventilator parameters by using the ventilator.

[0112] Step 340: inputting the ventilator parameters and the impedance value of the target lung region image into the trained mathematical model to obtain a ventilation parameter prediction value output by the trained mathematical model.

[0113] Step 350: adjusting parameters of the ventilator based on the ventilation parameter prediction value.

[0114] Step 360: determining whether an influence of the adjusted ventilator parameters on a lung ventilation state reaches an expected requirement.

[0115] Step 370: if the influence of the adjusted ventilator parameters on the lung ventilation state does not reach the expected requirement, continuously adjusting the ventilator parameters within a preset range of the ventilation parameter prediction value until the expected requirement is reached.

[0116] Wherein, the ventilator parameters can be adjusted according to the ventilation parameter prediction value first, and if the influence of the adjusted ventilator parameters on the lung ventilation state does not meet the expected requirement, the ventilation parameter prediction value can be gradually increased or reduced within a preset range, so as to make fine adjustment to the ventilator parameters.

[0117] Wherein, the expected requirement can be to maintain the lung conductivity distribution within a certain range or to minimize the airway pressure fluctuation, etc.

[0118] Since the physical conditions of each patient are different, after the ventilation parameter prediction value is determined, the EIT image (i.e. the lung ventilation distribution image) can be fed back on the basis of the ventilation parameter prediction value, and the adaptive control algorithm is used to adjust the ventilator parameters in real time to obtain the optimal ventilation parameter value, so that the lung conductivity distribution meets the expected requirement, that is, a personalized respiratory support plan can be provided according to the specific situation of each patient to optimize the treatment effect, thereby reducing the probability of complications such as barotrauma, volutrauma, atelectasis and ventilator-associated pneumonia.

[0119] Wherein, the adaptive control algorithm can be a recursive least squares method, Kalman filtering, etc. In this way, the model parameters can be continuously optimized by using the recursive least squares method, Kalman filtering, etc.

[0120] Since the EIT device can provide real-time and dynamic lung ventilation information, the application can help doctors accurately adjust the ventilator parameters and optimize the respiratory support strategy in the process of using the ventilator for treatment in combination with the use of the EIT device, thereby reducing the occurrence of complications and improving the treatment effect.

[0121] Wherein, the steps 310, 320, 330, 340 and 350 have the same or similar technical solutions as the above embodiments, which will not be repeated here.

[0122] In some embodiments, the trained mathematical model mentioned in the above embodiments can be trained in the following way:

[0123] 1) Obtain the training set of ventilator parameters and chest electrical impedance data by using the ventilator respectively;

[0124] 2) Train the mathematical model to be trained by using the training set of ventilator parameters and chest electrical impedance data, to obtain the trained mathematical model.

[0125] Based on the above embodiments, the application can be provided with EIT devices, ventilators, data processing units, display and control interfaces, etc. in terms of hardware. The data processing unit can be a high-performance computer or an embedded system for data processing and algorithm operation.

[0126] In terms of software, the present application can include a data acquisition module, an image reconstruction and processing module, an intelligent control algorithm module, and a user interface module.

[0127] The data acquisition module is configured to acquire EIT and ventilator data and perform synchronization processing.

[0128] The image reconstruction and processing module is configured to perform EIT image reconstruction, noise filtering, and image analysis.

[0129] The intelligent control algorithm module is configured to implement adaptive control and feedback control to optimize ventilator parameters.

[0130] The user interface module is configured to provide a real-time data display and control interface for medical personnel to view and operate.

[0131] Corresponding to the EIT-based ventilator adjustment method of the above embodiments, the present application also provides a ventilator parameter adjustment device, which includes units for implementing the technical solutions of any of the embodiments of the present application.

[0132] The present application also provides a ventilator adjustment system, which includes a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the EIT-based ventilator adjustment method provided by any of the method embodiments.

[0133] Referring to Figure 2 , Figure 2 is a structural diagram of an embodiment of the computer-readable storage medium provided by the present application, which is configured to store a computer program 71, and the computer program 71, when executed by a processor, is configured to implement the following method steps:

[0134] acquiring chest electrical impedance data in real time using an EIT device;

[0135] obtaining impedance values of a target lung region image based on the chest electrical impedance data;

[0136] obtaining ventilator parameters using the ventilator;

[0137] inputting the ventilator parameters and the impedance values of the target lung region image into a trained mathematical model to obtain a ventilation parameter prediction value output by the trained mathematical model;

[0138] adjusting the parameters of the ventilator based on the ventilation parameter prediction value.

[0139] It can be understood that the computer program 71, when executed by the processor, is also configured to implement the technical solutions of any of the embodiments of the present application.

[0140] In several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other manners. For example, the above described device embodiments are merely illustrative, and the division of modules or units can be different, for example, two or more units can be combined or integrated into one unit, or some features can be ignored or not executed. In this way, the internal structure of the device is not limited to the above.

[0141] 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, i.e., they can be located in one place or distributed on two network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0142] In addition, the functional units in each embodiment of the present application can be integrated into one processing unit, or each unit can be physically present alone, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0143] The integrated unit in the above other embodiments, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0144] The above is only an embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation using the contents of the present application specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A device for adjusting parameters of a breathing machine, characterized in that, The adjusting device of ventilator parameters comprises a unit for executing a ventilator adjusting method based on electrical impedance tomography, the adjusting system of ventilator comprises a ventilator and an EIT device, and the method comprises: acquiring chest electrical impedance data in real time by using the EIT device; obtaining impedance values of a target lung region image based on the chest electrical impedance data; obtaining ventilator parameters by using the ventilator; inputting the ventilator parameters and the impedance values of the target lung region image into a trained mathematical model to obtain a ventilation parameter prediction value output by the trained mathematical model; adjusting the ventilator based on the ventilation parameter prediction value; wherein the obtaining of the impedance values of the target lung region image based on the chest electrical impedance data comprises: reconstructing the chest electrical impedance data by using a finite element method to generate a real-time lung ventilation distribution image; segmenting the lung ventilation distribution image to obtain a target lung region image; obtaining the impedance values of the target lung region image based on the chest electrical impedance data; wherein, before the segmentation of the lung ventilation distribution image, the method further comprises: performing denoising processing on the lung ventilation distribution image to obtain a denoised lung ventilation distribution image; the segmentation of the lung ventilation distribution image to obtain a target lung region image comprises: segmenting the denoised lung ventilation distribution image to obtain a target lung region image; wherein, after the adjustment of the ventilator based on the ventilation parameter prediction value, the method further comprises: judging whether the influence of the adjusted ventilator parameters on the lung ventilation state meets the expected requirement; if the influence of the adjusted ventilator parameters on the lung ventilation state does not meet the expected requirement, the ventilator parameters are continuously adjusted within a preset range of the ventilation parameter prediction value until the expected requirement is met.

2. The apparatus of claim 1, wherein, the obtaining of the ventilator parameters by using the ventilator comprises: acquiring real-time ventilation data by using the ventilator; obtaining ventilator parameters based on the real-time ventilation data.

3. The apparatus of claim 2, wherein, The ventilation data comprises tidal volume and airway pressure, the ventilator parameters comprise respiratory cycle and mean airway pressure, and the obtaining of the ventilator parameters based on the real-time ventilation data comprises: obtaining the time points of the beginning and end of respiration based on the changes of the airway pressure and / or the tidal volume; obtaining the respiratory cycle based on the time points of the beginning and end of respiration; obtaining the airway pressure of all sampling points in the respiratory cycle; calculating the mean value of the airway pressure of all sampling points in the respiratory cycle by using the integral or discrete average method to obtain the mean airway pressure.

4. The apparatus of claim 1, wherein, The trained mathematical model is trained in the following manner: respectively obtaining a training set of ventilator parameters and chest electrical impedance data by using the ventilator; training a to-be-trained mathematical model by using the training set of ventilator parameters and chest electrical impedance data to obtain the trained mathematical model.

Images