Monitoring method, system and equipment based on shared EIT wearable sensor and medium

Abstract

The invention provides a monitoring method, system and device based on a shared EIT wearable sensor and a medium, and the method comprises the steps: measuring the dynamic change of electrical impedance in a thoracic cavity through a sensor device attached to a chest region of a tested person, so as to collect signals related to pulmonary ventilation and blood flow; the collected signals related to lung ventilation and blood flow are subjected to signal processing, the pulmonary alveolar ventilation volume and the lung blood flow within unit time are calculated according to the signals so as to obtain the real-time ventilation / blood flow perfusion ratio, and regional analysis is carried out so that synchronous monitoring of the ventilation / blood flow perfusion ratios of different lung areas can be carried out. By sharing the EIT sensor array, synchronous monitoring of systemic circulation, pulmonary ventilation and the V / Q ratio is achieved, the number of used sensors is reduced, and the burden and medical cost of a patient are reduced. By combining an intelligent algorithm and a data fusion technology, comprehensive physiological information is provided, and a new solution is provided for personalized medical treatment and remote monitoring.

Description

Technical Field

[0001] The present application relates to the field of intelligent non-invasive monitoring technology, and in particular to a monitoring method, system, device and medium based on a shared EIT wearable sensor. Background Art

[0002] In the modern medical field, cardiac output monitoring and lung imaging play a vital role in the accurate diagnosis of patients' conditions and subsequent effective treatment. In the traditional medical model, cardiac output monitoring equipment and lung imaging equipment operate independently of each other, and there is a lack of effective linkage and integration mechanism between the two. This means that when the clinic needs to fully understand the cardiopulmonary function of patients, patients have to undergo independent tests for the heart and lungs respectively. Each test is accompanied by corresponding preparation processes, equipment connection and data collection, which not only greatly prolongs the patient's medical treatment time, making them wait and stress for a long time in the medical process, but also brings additional burden to the patient's body. Frequent transfers, multiple equipment contacts and adjustments to the body state under different testing environments may cause fatigue, discomfort and even increased psychological pressure on patients. From the perspective of medical costs, independently operated equipment means double equipment procurement and maintenance costs, double medical manpower investment and double consumables use, which undoubtedly increases the economic burden of the entire medical system and indirectly affects the efficient allocation of medical resources.

[0003] With the continuous advancement of science and technology, electrical impedance tomography (EIT) technology has emerged, bringing new opportunities to the field of medical imaging. With its significant advantages of being non-invasive and radiation-free, EIT technology has gradually emerged in the field of lung function monitoring. Its working principle is based on the precise placement of a series of electrodes at specific locations on the human body surface, which can apply weak and safe alternating currents to the body. When the current passes through human tissue, different tissues have different electrical impedance characteristics, such as the obvious difference in electrical impedance between the air-containing tissue and the blood-rich tissue in the lungs, which will produce different degrees of potential changes. By accurately measuring these potential changes through surface electrodes, the dynamic distribution of electrical impedance in the body can be reversely calculated, and then the pulmonary ventilation status, such as the in and out of gas, the filling and emptying of alveoli, and the distribution changes of pulmonary blood flow, can be monitored in real time and dynamically, and the real-time information of the physiological function of the lungs can be intuitively displayed.

[0004] Although EIT technology has shown great potential, it still has many limitations in clinical applications at this stage. Most of the existing medical devices developed based on the EIT principle focus on simple pulmonary ventilation function assessment. When faced with the critical need for synchronous monitoring of cardiac output and accurate calculation of ventilation / perfusion (V / Q) ratio, which is urgently needed in clinical practice, existing EIT devices seem to be unable to cope with it. On the one hand, cardiac output monitoring requires extremely accurate and stable hemodynamic signal acquisition and analysis, while EIT technology is susceptible to interference in complex blood flow environments, making it difficult to directly and accurately extract key features reflecting cardiac output; on the other hand, calculating the V / Q ratio requires high-precision, real-time synchronous measurement of ventilation and blood flow. The existing EIT device architecture, algorithm and data processing capabilities cannot meet this highly coordinated and accurate monitoring requirement, which has become a key technical bottleneck restricting the widespread application of EIT technology in the field of cardiopulmonary combined function monitoring. Summary of the invention

[0005] In view of the shortcomings of the prior art mentioned above, the purpose of this application is to provide a monitoring method, system, device and medium based on shared EIT wearable sensors, which is used to solve the problem that the existing EIT device architecture, algorithm and data processing capabilities cannot meet the needs of highly coordinated and accurate monitoring.

[0006] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides a monitoring method based on a shared EIT wearable sensor, comprising: measuring the dynamic changes of electrical impedance in the chest cavity by a sensor device attached to the chest area of ​​the subject to collect signals related to pulmonary ventilation and blood flow; performing signal processing on the collected signals related to pulmonary ventilation and blood flow, calculating the alveolar ventilation and pulmonary blood flow per unit time to obtain a real-time ventilation / blood perfusion ratio, and performing regional analysis to perform synchronous monitoring of the ventilation / blood perfusion ratio of different lung regions.

[0007] In some embodiments of the first aspect of the present application, the process of calculating the alveolar ventilation per unit time includes: receiving electrical signals of impedance changes in different lung regions related to lung ventilation from a sensor device; transmitting the electrical signals of impedance changes in different lung regions to a signal processing unit; the signal processing unit performs deep processing and analysis on the received signals based on an imaging algorithm to reconstruct a corresponding lung ventilation image; based on the reconstructed lung ventilation image, identifying dynamic areas in the image that reflect alveolar filling and emptying, and calculating the alveolar ventilation per minute in combination with the respiratory frequency.

[0008] In some embodiments of the first aspect of the present application, the calculation process of pulmonary blood flow per unit time includes: extracting the electrical impedance change signal caused by cardiac beating from the original electrical signal related to blood flow collected by the sensor array; evaluating the pulmonary blood perfusion based on the extracted electrical impedance change signal caused by cardiac beating and the data monitored by the sensor array for different areas of the lungs; and calculating the pulmonary blood flow per minute based on the cardiac output data and the proportion of pulmonary blood perfusion in the cardiac output.

[0009] In some embodiments of the first aspect of the present application, the evaluation of pulmonary blood perfusion includes: judging the relative strength and uniformity of blood perfusion in various regions of the lungs through the amplitude of changes in the electrical impedance change signal caused by cardiac pulsation and its spatial distribution.

[0010] In some embodiments of the first aspect of the present application, after performing synchronous monitoring of the ventilation / perfusion ratio of different lung regions, the wearable intelligent monitoring method also includes: separating the alveolar ventilation signal and the pulmonary blood flow signal acquired by the sensor based on a signal decoupling algorithm; weightedly fusing the decoupled signals with one or more other physiological parameters based on a data fusion algorithm; and analyzing the fused data using an artificial intelligence model.

[0011] In some embodiments of the first aspect of the present application, the decoupled signal is fused with one or more other physiological parameters based on an adaptive multimodal fusion algorithm, and the process includes: identifying the patient's status; when a change in the patient's status is identified, automatically adjusting the weight distribution of different physiological parameters in the signal decoupling and data fusion process according to preset rules and real-time status data; based on the adjusted weights, performing signal decoupling and data fusion on various physiological data.

[0012] In some embodiments of the first aspect of the present application, the artificial intelligence model includes a heterogeneous neural network integration model, which integrates a convolutional neural network, a recurrent neural network and a generative adversarial network; the convolutional neural network is used to extract the spatial features of the signal, the recurrent neural network is used to capture time series information, and the generative adversarial network optimizes the model's learning ability for complex physiological signal patterns through a generative adversarial mechanism.

[0013] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides a monitoring system based on a shared EIT wearable sensor, including: a sensor module, which is attached to the chest area of ​​the subject and is used to measure the dynamic changes of electrical impedance in the chest cavity to collect signals related to pulmonary ventilation and blood flow; a synchronous monitoring module, which is electrically connected to the sensor module and is used to process the collected signals related to pulmonary ventilation and blood flow, calculate the alveolar ventilation and pulmonary blood flow per unit time to obtain a real-time ventilation / blood perfusion ratio, and perform regional analysis to perform synchronous monitoring of the ventilation / blood perfusion ratio of different lung regions.

[0014] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the monitoring method based on the shared EIT wearable sensor is implemented.

[0015] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer program product, which includes a computer program code. When the computer program code is run on a computer, the computer implements the monitoring method based on the shared EIT wearable sensor.

[0016] To achieve the above-mentioned purpose and other related purposes, the fifth aspect of the present application provides a computer device, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the monitoring method based on the shared EIT wearable sensor.

[0017] As described above, the monitoring method, system, device and medium based on shared EIT wearable sensors of the present application have the following beneficial effects: The present application realizes the synchronous monitoring of systemic circulation, pulmonary ventilation and V / Q ratio by sharing the EIT sensor array, reduces the number of sensors used, reduces the burden on patients and medical costs. Combined with intelligent algorithms and data fusion technology, it provides comprehensive physiological information and provides new solutions for personalized medicine and remote monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Shown is a flow chart of a monitoring method based on a shared EIT wearable sensor in one embodiment of the present application.

[0019] Figure 2 Shown is a schematic diagram of the calculation process of alveolar ventilation per unit time in one embodiment of the present application.

[0020] Figure 3 Shown is a schematic diagram of the calculation process of pulmonary blood flow per unit time in one embodiment of the present application.

[0021] Figure 4 Shown is a structural schematic diagram of a monitoring system based on a shared EIT wearable sensor in one embodiment of the present application.

[0022] Figure 5 Shown is a schematic diagram of the structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0023] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0024] The technical solution of the embodiment of the present application can be applied to various scenarios. The device is designed to be wearable and uses flexible biocompatible materials to ensure that users can get a comfortable wearing experience when performing daily activities or even sleeping. The technical solution of the present application can be applied to home self-testing, telemedicine and hospital monitoring, and supports integration with electronic health records and hospital information systems, providing continuous physiological monitoring for chronic disease management and postoperative rehabilitation.

[0025] In the home self-test scenario, the device is equipped with high-precision physiological parameter sensing technology, which can accurately measure key physiological indicators such as heart rate, blood pressure, blood oxygen saturation, etc. With the help of advanced wireless data transmission technology, the measured data will be transmitted to the paired smart terminal device in real time and accurately, and stored in the local database, so that users can call and view it at any time, so as to visualize the dynamic changes of their health status.

[0026] For telemedicine, the device integrates 4G / 5G communication modules and low-power Bluetooth technology to achieve high-speed and stable remote transmission of physiological data. Patients in remote areas or with limited mobility can upload their physiological data to the telemedicine platform in real time with simple operations.

[0027] In hospital monitoring scenarios, this device, as a powerful supplement to traditional large-scale monitoring equipment, adopts a distributed sensor network architecture and can be seamlessly connected with the hospital's existing medical information system. Through the hospital information management platform, medical staff can obtain various physiological data of patients outside the ward in real time, and realize all-round and all-time dynamic monitoring of patients.

[0028] In the field of chronic disease management, the device can accurately predict the development trend of chronic diseases through continuous physiological parameter monitoring, combined with time series data analysis algorithms and machine learning models. For patients recovering from surgery, the device can monitor the patient's physical function recovery indicators in real time and use data analysis technology to quantitatively evaluate the recovery process. Once abnormal data is found, the system will automatically trigger an early warning mechanism to remind medical staff to intervene in time to ensure the patient's recovery process is safe and efficient.

[0029] Figure 1 The flowchart of a monitoring method based on a shared EIT wearable sensor in an embodiment of the present invention is shown. The wearable intelligent monitoring method in this embodiment mainly includes the following steps:

[0030] Step S11: The dynamic changes of the electrical impedance in the chest cavity are measured by a sensor device attached to the chest area of ​​the test subject to collect signals related to lung ventilation and blood flow.

[0031] Preferably, the sensor device of the present application is configured with a flexible EIT sensor array. Through the multiple electrodes on the flexible EIT sensor array that fits tightly to the chest, it can accurately capture the subtle dynamic changes in electrical impedance caused by lung ventilation and blood flow and convert them into electrical signals.

[0032] Flexible EIT sensor array, this flexible material has many advantages. Compared with traditional rigid sensors, it can perfectly fit the complex curved contours of the human chest, ensuring close and stable contact between the electrode and the skin. Regardless of the patient's position, whether it is lying flat, lying on the side or semi-sitting, the flexible sensor array can adaptively adjust to minimize the poor contact caused by changes in body position, thereby ensuring the continuity and accuracy of signal acquisition. The workflow of the EIT sensor array starts with applying a weak current to the chest cavity. The current intensity has undergone rigorous medical safety demonstration to ensure that while achieving the detection function, it will not cause any adverse physiological stimulation or damage to the human body. When the weak current is injected into the chest cavity, because the chest cavity contains different structures such as lung tissue, heart and rich vascular network, each of these structures has unique electrical impedance characteristics. For example, during the ventilation process of the lungs, the in and out of gas causes the filling degree of the alveoli to change continuously, which in turn causes the local electrical impedance to show regular fluctuations; the periodic contraction and relaxation of the heart drives the blood flow, and the electrolyte-rich blood forms an electrical impedance performance that is completely different from static tissue when flowing.

[0033] The signals related to pulmonary ventilation referred to here mainly refer to: as the breathing movement proceeds, air enters and exits the lungs rhythmically. During the inhalation phase, a large amount of gas flows into the alveoli, causing the alveoli to fill and expand rapidly. This process causes the conductive environment of the local lung tissue to change, because gas is a low-conductivity medium compared to the lung parenchyma, so the impedance of the area increases. On the contrary, during exhalation, the alveoli shrink, the gas is discharged, and the impedance of the lung tissue decreases. This impedance fluctuation that changes regularly with the respiratory cycle is one of the key signals reflecting the state of pulmonary ventilation. Moreover, the order of alveolar ventilation in different regions, the amount of ventilation, and the speed of ventilation rate will cause differences in the amplitude, frequency, and temporal and spatial distribution of impedance changes. For example, when a healthy adult breathes calmly, the ventilation rates of the upper and lower lobes of the lungs may be slightly different. The sensor array can capture the subtle differences in the impedance changes in the corresponding regions, thereby reflecting the uniformity of lung ventilation.

[0034] The signals related to blood flow here mainly refer to: the heart, as the power core of human blood circulation, continuously contracts and relaxes. During the systolic period, the heart pumps blood rich in oxygen and nutrients to the whole body. At this time, the blood flow in the large blood vessels and microvascular beds in the chest cavity increases instantly, and the charged particles such as electrolytes and blood cells in the blood move rapidly, forming a relatively low impedance environment, because blood has better conductivity than the surrounding muscles, connective tissues, etc. During the diastolic period, the blood flow slows down, the pressure in the blood vessels decreases, and the impedance increases accordingly. In addition, the ejection function of different chambers of the heart, the elasticity of the blood vessels, and the pathological and physiological states of local blood vessel stenosis or dilation will leave a unique "mark" on the impedance signal related to blood flow. For example, patients with coronary heart disease have atherosclerotic plaques in the coronary arteries, which lead to local blood flow obstruction. The change pattern of blood flow impedance in the corresponding area will be different from that of healthy people, and there may be characteristics such as slowed blood flow and reduced blood flow fluctuations. These abnormal signals can be keenly captured by the EIT sensor array.

[0035] Step S12: Process the collected signals related to pulmonary ventilation and blood flow to calculate the alveolar ventilation and pulmonary blood flow per unit time to obtain a real-time ventilation / blood perfusion ratio, and perform regional analysis to synchronously monitor the ventilation / blood perfusion ratio of different lung regions.

[0036] In some examples, the alveolar ventilation per unit time is calculated as follows Figure 2 As shown, the following steps are included:

[0037] Step S2a: receiving electrical signals of electrical impedance changes in different lung regions related to lung ventilation from the sensor device.

[0038] Specifically, the electrodes on the flexible EIT sensor array distributed on the chest capture the dynamic changes in electrical impedance in different areas of the lungs caused by breathing in real time and convert them into electrical signals. Since the ventilation of different areas of the lungs is not completely synchronized, for example, there may be differences in the start time and rate of ventilation between the edge and center areas of the lungs, the sensor array, with its high sensitivity and multi-electrode layout advantages, accurately records these subtle differences and ensures that all-round dynamic information of lung ventilation is obtained.

[0039] Step S2b: transmitting the electrical signals of the electrical impedance changes in different areas of the lung to a signal processing unit; the signal processing unit performs in-depth processing and analysis on the received signals based on an imaging algorithm to reconstruct a corresponding lung ventilation image.

[0040] Specifically, the collected electrical signals of impedance changes in different areas of the lungs are instantly transmitted to a high-performance signal processing unit. The imaging algorithm converts abstract impedance data into intuitive lung ventilation images. Different grayscale or color areas in the image accurately correspond to the ventilation status of each part of the lungs, clearly showing the filling and emptying process of the alveoli, the uniformity of lung ventilation, and the approximate distribution of ventilation, allowing medical staff to visually understand the overall picture of lung ventilation.

[0041] Further, the process of reconstructing the lung ventilation image using the imaging algorithm includes:

[0042] (1) De-noise and normalize the original electrical signal from the sensor.

[0043] Due to the bioelectric noise of the human body and the electromagnetic interference in the external environment, these noises may affect subsequent analysis. The purity of the electrical signal is ensured by adopting filtering algorithms, such as low-pass filtering to remove high-frequency noise and high-pass filtering to remove low-frequency drift. The signal is normalized because the signal amplitudes collected by different electrodes may be different. Normalization can unify all signals to the same numerical range, which is convenient for subsequent unified calculation and analysis, making the data of each electrode comparable.

[0044] (2) Based on the anatomical data of the human chest, a three-dimensional chest geometric model is constructed, and corresponding electrical impedance characteristic parameters are assigned to different tissues in the model.

[0045] The three-dimensional chest geometry model accurately depicts the position and shape of tissues such as the lungs, heart, ribs, and muscles, and determines their relative positional relationship in space. Different tissues in the model are assigned corresponding impedance characteristic parameters, such as the impedance value range of lung tissue under different ventilation states, and the specific impedance values ​​of other tissues such as blood, muscle, and bone. These parameters are the basis for subsequent calculations and determine the conduction path and distribution of current in chest tissue.

[0046] (3) Based on the chest geometry model, the conduction of current in the chest tissue is calculated, and the potential distribution of each point inside the chest is calculated.

[0047] Specifically, based on the established physical model of the chest, according to the known electrode positions and the applied current distribution, numerical calculation methods such as the finite element method or the boundary element method are used to calculate the conduction of current in the chest tissue. By solving the Maxwell equations or related electrical conduction equations, the potential distribution of each point inside the chest is obtained. This step simulates the actual current propagation process in the human chest, providing a theoretical basis for subsequent inversion calculations.

[0048] (4) According to the potential data actually measured by the sensor, the potential distribution in the chest model is adjusted so that the calculated potential distribution is as close as possible to the actual measured value.

[0049] Specifically, the potential data actually measured by the sensor is compared with the potential distribution calculated by the forward problem. Using optimization algorithms, such as the least squares method and the iteration method, the impedance distribution of each tissue in the chest model is continuously adjusted to make the potential distribution calculated by the model as close as possible to the actual measured value. After multiple iterative calculations, the internal impedance distribution of the chest with the highest fit to the actual measured potential data is finally obtained. This process is like using a known result (measured potential) to reversely infer the cause of the result (internal impedance distribution).

[0050] (5) According to the adjusted lung electrical impedance distribution, the electrical impedance value is mapped into a grayscale value or a color value of the image; according to the geometric structure of the chest model, these grayscale values ​​or color values ​​are arranged and composed to form a two-dimensional or three-dimensional lung ventilation image.

[0051] According to the distribution of electrical impedance of the lungs obtained by inversion calculation, the electrical impedance value is mapped to the grayscale value or color value of the image. For example, the high electrical impedance area is set to correspond to a brighter grayscale or a specific color, and the low electrical impedance area is set to correspond to a darker grayscale or another color. According to the geometric structure of the chest model, these grayscale values ​​or color values ​​are arranged and combined to form a two-dimensional or three-dimensional lung ventilation image. In the image, the difference in electrical impedance due to different ventilation states in different areas of the lungs can be clearly seen, thereby intuitively displaying the lung ventilation status information such as alveolar filling and emptying, ventilation uniformity, etc.

[0052] Step S2c: Based on the reconstructed lung ventilation image, the dynamic area reflecting alveolar filling and emptying in the image is identified, and the alveolar ventilation per minute is calculated in combination with the respiratory frequency.

[0053] Based on the reconstructed lung ventilation images, further data quantitative analysis is performed with the help of a special software module. By identifying the dynamic areas in the image that reflect the filling and emptying of the alveoli, combined with the known respiratory rate (obtained by the sensor synchronously recording the respiratory cycle), a specific calculation formula is used to accurately calculate the alveolar ventilation per minute. For example, if the ventilation area change and respiratory rate of a certain area of ​​the lungs in a certain period of time are known, the alveolar ventilation value involved in gas exchange per unit time can be accurately obtained based on the gas exchange principle and mathematical derivation formula. This precisely quantified lung ventilation index provides key and reliable data support for the clinical evaluation of patients' respiratory function, diagnosis of lung diseases, and adjustment of treatment plans.

[0054] In some examples, the pulmonary blood flow per unit time is calculated as follows: Figure 3 As shown, the following steps are included:

[0055] Step S3a: extracting the electrical impedance change signal caused by the heart beat from the original electrical signal related to the blood flow collected by the sensor array.

[0056] It should be understood that the original electrical signal collected from the sensor array is actually a mixture of multiple physiological signals intertwined with each other. In order to obtain the heart beat-related signals that are crucial to the measurement of pulmonary blood flow, it is necessary to use advanced signal processing technology to carefully separate them. First, the bandpass filtering algorithm is used to filter out the frequency band of electrical signals that are highly correlated with the heart beat frequency. In this way, the impedance change signal caused by the heart beat can be extracted from the complex mixed signal. Secondly, in order to further explore the rich information contained in the signal, advanced signal processing methods such as spectrum analysis and wavelet transform can also be used to deeply analyze the various characteristic parameters of the signal, including the change law of signal amplitude, frequency characteristics and phase information. These parameters can reflect the strength of myocardial contractility, dynamic changes in cardiac chamber volume and changes in hemodynamics during each heart beat, providing a solid data foundation for the subsequent accurate evaluation of the heart's pumping function and pulmonary blood perfusion status.

[0057] Step S3b: Based on the extracted electrical impedance change signal caused by the heart beat and the data monitored by the sensor array for different areas of the lung, the pulmonary blood perfusion is evaluated.

[0058] Specifically, the relative strength and uniformity of blood perfusion in various regions of the lungs are determined by the amplitude of the impedance change signal caused by the heart beat and its spatial distribution. That is, based on the extracted impedance change signal caused by the heart beat and the data monitored by the sensor array for different regions of the lungs, combined with the conductivity model of the chest tissue and the basic principles of hemodynamics, a comprehensive assessment of the blood perfusion of the lungs is carried out. When the heart vigorously pumps blood into the lungs, the blood flow in the pulmonary blood vessels increases instantly, which causes the impedance of the local tissue to decrease accordingly. By conducting in-depth analysis of the impedance change amplitude and spatial distribution accurately measured by the sensor, the relative strength and uniformity of blood perfusion in various regions of the lungs can be accurately determined. For example, if the impedance change amplitude of a specific area of ​​the lungs is significantly smaller than that of other areas during a cycle of heart beat, this may indicate that there is a potential problem of insufficient blood perfusion in that area. In addition, by comparing the change patterns of lung impedance at different time points or under different physiological conditions, the changing trend of pulmonary blood perfusion can be dynamically and continuously monitored, providing a strong basis for clinicians to detect changes in the disease in a timely manner.

[0059] Step S3c: Calculate the pulmonary blood flow per minute based on the cardiac output data and the proportion of pulmonary blood perfusion in the cardiac output.

[0060] Cardiac output, as a key indicator to measure the total amount of blood pumped out by the heart per minute, can be obtained in advance through mature and reliable measurement technologies such as echocardiography and thermodilution. After obtaining the cardiac output data, the pulmonary blood perfusion information previously evaluated by EIT technology is closely combined with it. With the help of specially designed specific mathematical models and precise calculation formulas, the pulmonary blood flow per minute can be accurately calculated. For example, assuming that the cardiac output is X liters / minute, and through in-depth analysis of EIT technology, it is concluded that the proportion of pulmonary blood perfusion in cardiac output is Y%, then according to the formula, the pulmonary blood flow per minute Q = X × Y%. The result of this precise calculation provides a quantitative and intuitive indicator of pulmonary blood circulation.

[0061] After the alveolar ventilation per minute is calculated through steps S2a to S2c, and the pulmonary blood flow per minute is calculated through steps S3a to S3c, the ratio of pulmonary ventilation to pulmonary blood flow is calculated to obtain a real-time V / Q ratio, and regional analysis can be performed to evaluate the ventilation / perfusion matching of different lung regions.

[0062] In some preferred embodiments, after synchronously monitoring the ventilation / perfusion ratio of different lung regions, the method further performs the following: separating the alveolar ventilation signal and the pulmonary blood flow signal acquired by the sensor based on a signal decoupling algorithm; weightedly fusing the decoupled signals with one or more other physiological parameters based on a data fusion algorithm; and analyzing the fused data using an artificial intelligence model.

[0063] In the signals obtained by EIT (electrical impedance tomography) technology, ventilation and blood flow signals are intertwined. Therefore, it is necessary to use a signal decoupling algorithm to separate the mixed ventilation and blood flow signals based on the characteristic differences of the signals, such as frequency characteristics, phase characteristics, etc. For example, the independent component analysis (ICA) algorithm can be used to find independent source signals from the mixed signals without prior information, thereby achieving effective separation of ventilation and blood flow signals.

[0064] In addition to the ventilation and blood flow signals obtained by EIT, the embodiments of the present application will also combine other physiological parameters, such as heart rate, blood pressure, blood oxygen saturation, etc. The role of the data fusion algorithm is to integrate these data from different sensors and different types, eliminate redundancy and contradictions between the data, and form a more comprehensive and accurate data set. For example, a weighted average fusion algorithm is used to assign different weights according to the importance of different physiological parameters to the monitoring results, and then fuse them together. It should be understood here that physiological parameters such as heart rate, blood pressure, and blood oxygen saturation can reflect the physiological state of the human body from different angles. Taking heart rate as an example, when pulmonary ventilation or blood flow is abnormal, the heart rate may change in order to maintain normal blood circulation. Combining these parameters with the ventilation and blood flow signals obtained by EIT can provide more abundant information for subsequent analysis and avoid the one-sidedness that may be caused by single parameter analysis.

[0065] Preferably, the decoupled signals are fused with one or more other physiological parameters based on an adaptive multimodal fusion algorithm, and the process includes: identifying the patient's status; when a change in the patient's status is identified, automatically adjusting the weight distribution of different physiological parameters in the signal decoupling and data fusion process according to preset rules and real-time status data; based on the adjusted weights, performing signal decoupling and data fusion on various physiological data.

[0066] Specifically, the algorithm automatically identifies the patient's status, such as determining whether the patient is in motion or other complex situations, in order to determine whether the signal decoupling and data fusion strategies need to be adjusted. When a change in the patient's status is identified, the algorithm automatically adjusts the weight distribution of different physiological parameters in the signal decoupling and data fusion process according to preset rules and real-time status data. For example, when the patient is in motion, the weights of certain physiological parameters that are greatly affected by motion will be reduced, while the weights of relatively stable parameters will be increased. Based on the adjusted weights, signal decoupling and data fusion are performed on various physiological data to ensure that data from different sources and modalities can be accurately fused together even in complex situations to form a more comprehensive and accurate data set, providing a reliable data foundation for subsequent analysis.

[0067] In the embodiments of the present application, using an artificial intelligence model to analyze the fused data means inputting the decoupled and fused data into the artificial intelligence model and utilizing the model's powerful learning and analysis capabilities to improve the accuracy and reliability of monitoring.

[0068] Preferably, a heterogeneous neural network integration model is constructed, which combines the advantages of convolutional neural network (CNN), recurrent neural network (RNN) and generative adversarial network (GAN). CNN is used to extract the spatial features of the signal, RNN captures the time series information, and GAN optimizes the model's learning ability for complex physiological signal patterns through the mechanism of generative adversarial. This collaborative working mode of multiple network structures can analyze physiological data more comprehensively and accurately, and has a significant performance improvement compared to a single type of neural network model.

[0069] The construction and training process of CNN includes: constructing a convolutional neural network (CNN), designing appropriate convolutional layers, pooling layers, and fully connected layer structures. The parts of the preprocessed physiological data related to spatial features (such as the spatial distribution features in EIT image data) are input into CNN for training. By continuously adjusting the network parameters, CNN can effectively extract the spatial features of the signal, such as the spatial distribution patterns of ventilation and blood flow in different parts.

[0070] The construction and training process of RNN includes: building a recurrent neural network (RNN), selecting appropriate RNN variants such as long short-term memory network (LSTM) or gated recurrent unit (GRU) according to the time series characteristics of physiological data. Inputting physiological data with time series characteristics (such as heart rate and blood pressure change data over a period of time) into RNN for training, so that it can capture the trend and dependency of data over time, such as analyzing the dynamic change rules of ventilation and blood flow signals over a period of time.

[0071] The construction and training process of GAN includes: constructing a generative adversarial network (GAN), including a generator and a discriminator. The task of the generator is to generate simulated physiological signal data, and the discriminator is used to determine whether the input data is real physiological data or generated by the generator. The real physiological data and the data generated by the generator are simultaneously input into the discriminator for adversarial training. During the training process, the generator continuously optimizes the quality of the generated data to make it closer to the real data, and the discriminator continuously improves the ability to distinguish between true and false data. Through this adversarial mechanism, GAN can optimize the ability to learn complex physiological signal patterns, such as learning the subtle differences between normal and abnormal physiological signal patterns.

[0072] In the process of integrating heterogeneous networks, the trained CNN, RNN and GAN are integrated. There are many ways to integrate, such as inputting the output results of CNN and RNN into GAN as feature vectors, or fusing the outputs of the three networks through a fusion layer. In the integration process, the connection weights and parameters between the networks need to be adjusted to ensure that they can work together to conduct a comprehensive and accurate analysis of the physiological data. After the model is built, the integrated heterogeneous neural network model is evaluated using a test data set, and the performance of the model in analyzing physiological data is measured by calculating indicators such as accuracy, recall, and mean square error. Based on the evaluation results, the model is further optimized, such as adjusting the network structure, parameters, or training methods, to improve the performance and stability of the model.

[0073] Preferably, a reinforcement learning mechanism is introduced during the model training process, so that the model can continuously optimize its own analysis strategy in the process of interacting with the simulated physiological data environment. For example, the model receives reward or penalty feedback based on the monitoring results of the simulated patient's condition changes, thereby adjusting its own parameters and decision logic to achieve better monitoring accuracy.

[0074] Specifically, the model training process based on the strong learning mechanism includes:

[0075] Step (1) Define the state space: Determine the state space during model training, that is, the various features that can describe the simulated physiological data environment. This includes the current physiological data value, the patient's state information (such as whether he is exercising, whether he is in the onset of the disease, etc.), and the analysis results of the previous model. Encode this information to form a state representation that the model can understand.

[0076] Step (2) Define the action space: clarify the actions that the model can take when facing different states. For example, the model can adjust the attention weights of different physiological parameters, change the parameter settings of the analysis algorithm, or make different classification decisions on the monitoring results. Each action corresponds to an analysis strategy adjustment of the model to physiological data.

[0077] Step (3) Initialize the model and environment: Initialize the parameters of the artificial intelligence model and create a simulated physiological data environment. This environment can be simulated according to the distribution and change rules of real physiological data, including generating physiological data samples under different states and setting corresponding disease changes.

[0078] Step (4) Model-environment interaction: In each training step, the model selects an action from the action space based on the current state. This action is then applied to the simulated environment, which returns a new state and corresponding reward or penalty feedback based on the model's action. For example, if the model accurately predicts changes in the patient's condition, a positive reward is given; if the prediction is wrong, a negative reward is given.

[0079] Step (5) Model learning and updating: Based on the rewards and new states fed back by the environment, the model uses reinforcement learning algorithms (such as Q-learning, deep Q network DQN, etc.) to update its own parameters and decision logic. The model learns how to choose the optimal analysis strategy in different states to maximize the long-term cumulative rewards by constantly trying different actions.

[0080] Step (6) Training iteration and optimization: Repeat steps (4) and (5) for multiple training iterations. During the iteration process, gradually adjust the model's learning rate, exploration and utilization balance and other hyperparameters to optimize the model's training effect. At the same time, the model can be evaluated regularly to monitor its performance on the validation data set. When the model performance reaches a certain standard or no longer improves, stop training.

[0081] Step (7) Practical application deployment: Deploy the trained model to the actual medical monitoring system to perform real-time analysis and monitoring of the physiological data of real patients. In actual applications, the model can dynamically adjust the analysis strategy based on the real-time acquired physiological data to improve the accuracy and reliability of monitoring.

[0082] The technical solution provided in this application realizes the synchronous monitoring of systemic circulation, pulmonary ventilation and V / Q ratio by sharing the EIT sensor array, reduces the number of sensors used, reduces the burden on patients and medical costs. Combined with intelligent algorithms and data fusion technology, it provides comprehensive physiological information and provides new solutions for personalized medicine and remote monitoring.

[0083] Figure 4 The structure diagram of a monitoring system based on a shared EIT wearable sensor in an embodiment of the present invention is shown. The wearable intelligent monitoring system in this embodiment includes: a sensor module 401 and a synchronous monitoring module 402.

[0084] The sensor module 401 is attached to the chest area of ​​the subject and is used to measure the dynamic changes of the electrical impedance in the chest cavity to collect signals related to pulmonary ventilation and blood flow. The synchronous monitoring module 402 is electrically connected to the sensor module 401 and is used to perform signal processing on the collected signals related to pulmonary ventilation and blood flow, calculate the alveolar ventilation and pulmonary blood flow per unit time to obtain a real-time ventilation / blood perfusion ratio, and perform regional analysis to perform synchronous monitoring of the ventilation / blood perfusion ratio of different lung regions.

[0085] In an embodiment of the present application, the wearable intelligent monitoring system also includes: a heterogeneous model construction module 403, which is used to separate the alveolar ventilation signal and the pulmonary blood flow signal acquired by the sensor based on a signal decoupling algorithm; based on a data fusion algorithm, the decoupled signals are weightedly fused with one or more other physiological parameters; and an artificial intelligence model is used to analyze the fused data.

[0086] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here. In addition, the division of modules in the embodiment of the present application is schematic, which is only a logical function division, and there may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application can be integrated in a processor, or it can exist physically separately, or two or more modules can be integrated in one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0087] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0088] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "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 represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0089] Figure 5 is a schematic block diagram of a computer device / equipment / system provided in an embodiment of the present application. Figure 5 As shown in FIG. 1 , the computer device includes: at least one processor 501, a memory 502, at least one network interface 503, and a user interface 505. The various components in the device are coupled together via a bus system 504. It can be understood that the bus system 504 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 504 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 504 is not described in detail. Figure 5 In the specification, various buses are labeled as bus systems.

[0090] The user interface 505 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0091] It is understood that the memory 502 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable categories of memory.

[0092] The memory 502 in the embodiment of the present invention is used to store various types of data to support the operation of the electronic terminal 500. Examples of these data include: any executable program used to operate on the electronic terminal 500, such as an operating system 5021 and an application 5022; the operating system 5021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 5022 can include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The XX method provided by the embodiment of the present invention can be included in the application 5022.

[0093] The method disclosed in the above embodiment of the present invention can be applied to the processor 501, or implemented by the processor 501. The processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 501 or the instruction in the form of software. The above processor 501 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 501 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general processor 501 may be a microprocessor or any conventional processor, etc. In combination with the steps of the accessory optimization method provided in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0094] In an exemplary embodiment, the electronic terminal 500 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0095] According to the method provided in the embodiments of the present application, the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes the monitoring method based on a shared EIT wearable sensor of any embodiment.

[0096] According to the method provided in an embodiment of the present application, the present application also provides a computer-readable storage medium, which stores a program code. When the program code is run on a computer, the computer executes the above-mentioned monitoring method based on a shared EIT wearable sensor.

[0097] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program and / or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may communicate, for example, through local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0098] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in 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. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0100] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0101] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] In addition, each functional unit in each embodiment of the present application 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.

[0103] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When loading and executing computer program instructions (programs) on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media integrations. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs), etc.).

[0104] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0106] In summary, the present application provides a monitoring method, system, device and medium based on shared EIT wearable sensors. The present application realizes the synchronous monitoring of systemic circulation, pulmonary ventilation and V / Q ratio by sharing the EIT sensor array, reduces the number of sensors used, and reduces the burden on patients and medical costs. Combined with intelligent algorithms and data fusion technology, it provides comprehensive physiological information and provides new solutions for personalized medicine and remote monitoring. Therefore, the present application effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0107] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A monitoring method based on a shared EIT wearable sensor, characterized in that: include: The dynamic changes of electrical impedance in the chest cavity are measured by a sensor device attached to the chest area of ​​the subject to collect signals related to lung ventilation and blood flow; The collected signals related to pulmonary ventilation and blood flow are processed to calculate the alveolar ventilation and pulmonary blood flow per unit time to obtain the real-time ventilation / blood perfusion ratio, and regional analysis is performed to synchronously monitor the ventilation / blood perfusion ratio of different lung regions.

2. The monitoring method based on shared EIT wearable sensor according to claim 1, characterized in that: The calculation process of alveolar ventilation per unit time includes: receiving electrical signals from a sensor device indicating changes in electrical impedance of different regions of the lungs associated with lung ventilation; The electrical signals of the electrical impedance changes in different areas of the lungs are transmitted to a signal processing unit; the signal processing unit performs in-depth processing and analysis on the received signals based on an imaging algorithm to reconstruct a corresponding lung ventilation image; Based on the reconstructed lung ventilation image, the dynamic area reflecting alveolar filling and emptying in the image is identified, and the alveolar ventilation per minute is calculated in combination with the respiratory rate.

3. The monitoring method based on shared EIT wearable sensor according to claim 1, characterized in that: The calculation process of pulmonary blood flow per unit time includes: Extracting electrical impedance change signals caused by cardiac pulsation from raw electrical signals related to blood flow collected by the sensor array; The pulmonary blood perfusion is evaluated based on the extracted electrical impedance change signal caused by the heart beat and the data monitored by the sensor array in different areas of the lungs; The pulmonary blood flow per minute was calculated based on the cardiac output data and the proportion of pulmonary blood perfusion in the cardiac output.

4. The monitoring method based on shared EIT wearable sensor according to claim 3 is characterized in that: The evaluation of the pulmonary blood perfusion includes: judging the relative strength and uniformity of the blood perfusion in each area of ​​the lung by the variation amplitude and spatial distribution of the electrical impedance variation signal caused by the heart beat.

5. The monitoring method based on shared EIT wearable sensor according to claim 1, characterized in that: After performing synchronous monitoring of the ventilation / perfusion ratios of different lung regions, the wearable intelligent monitoring method further includes: Based on the signal decoupling algorithm, the alveolar ventilation signal and the pulmonary blood flow signal obtained by the sensor are separated; based on the data fusion algorithm, the decoupled signals are weightedly fused with one or more other physiological parameters; and the fused data are analyzed using an artificial intelligence model.

6. The monitoring method based on shared EIT wearable sensor according to claim 5, characterized in that: Based on the adaptive multimodal fusion algorithm, the decoupled signal is fused with one or more other physiological parameters respectively. The process includes: identifying the patient's status; when the patient's status change is identified, the weight distribution of different physiological parameters in the signal decoupling and data fusion process is automatically adjusted according to preset rules and real-time status data; based on the adjusted weights, signal decoupling and data fusion of various physiological data are performed.

7. The monitoring method based on shared EIT wearable sensor according to claim 5, characterized in that: The artificial intelligence model includes a heterogeneous neural network integration model, which integrates a convolutional neural network, a recurrent neural network and a generative adversarial network; the convolutional neural network is used to extract the spatial features of the signal, the recurrent neural network is used to capture time series information, and the generative adversarial network optimizes the model's learning ability for complex physiological signal patterns through a generative adversarial mechanism.

8. A monitoring system based on shared EIT wearable sensors, characterized in that: include: The sensor module is attached to the chest area of ​​the subject and is used to measure the dynamic changes of electrical impedance in the chest cavity to collect signals related to lung ventilation and blood flow; The synchronous monitoring module is electrically connected to the sensor module and is used to process the collected signals related to pulmonary ventilation and blood flow, calculate the alveolar ventilation and pulmonary blood flow per unit time to obtain a real-time ventilation / blood perfusion ratio, and perform regional analysis to synchronously monitor the ventilation / blood perfusion ratio of different lung regions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the monitoring method based on a shared EIT wearable sensor according to any one of claims 1 to 7 is implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the monitoring method based on the shared EIT wearable sensor according to any one of claims 1 to 7.

Images