Method, system and equipment for determining breathing type during anesthesia, medium and product

Abstract

The invention discloses a respiration type determination method, system and device during anesthesia, a medium and a product, and belongs to the technical field of medical data processing. The method comprises the following steps: acquiring initial breath sound data of a target object in a general anesthesia state under a current time window, wherein the initial breath sound data is acquired by a breath sound acquisition device arranged in a first preset area of the chest of the target object or a sound sensor arranged in a second preset area of the back of the target object; performing noise reduction processing on the initial breath sound data to obtain target breath sound data, and determining a statistical distribution feature combination corresponding to the target breath sound data, the statistical distribution feature combination comprising statistical distribution feature data under at least two signal domains; inputting the statistical distribution feature combination into a predetermined diagnosis model to obtain an initial diagnosis result; and displaying at least one breath sound type identifier in the initial diagnosis result. According to the technical scheme, the breathing sound type identifier of the target object can be displayed in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular, to a method, system, device, medium and product for determining the respiratory type during anesthesia. Background Art

[0002] Currently, the devices and machines for routinely monitoring the respiratory type of patients during general anesthesia in clinical practice include pulse oximeters, ventilators, blood gas analysis examinations, etc. Although the pulse oximeter can provide real-time data on blood oxygen levels, its ability to detect apnea or hypoventilation events is limited. According to a study published in the Journal of Anesthesiology, the sensitivity of the pulse oximeter in detecting apnea events is only 60%, which means that 40% of apnea events may be missed. Arterial blood gas analysis not only increases the discomfort and infection risk of patients, but also is complex to operate and difficult to achieve continuous real-time monitoring. Tracheal intubation is an invasive detection method and has a greater impact on the patient's body.

[0003] In summary, there is a need to provide a non-invasive method that can real-time monitor the respiratory type of patients during general anesthesia to improve the user experience. Summary of the Invention

[0004] The present invention provides a method, system, device, medium and product for determining the respiratory type during anesthesia to solve the problem that the existing methods for determining the respiratory type cannot perform real-time monitoring of the respiratory type of patients under general anesthesia in a non-invasive manner.

[0005] According to one aspect of the present invention, there is provided a method for determining the respiratory type during general anesthesia, including:

[0006] Obtaining initial respiratory sound data of a target object in a general anesthesia state in a current time window, where the initial respiratory sound data is collected by a respiratory sound acquisition device disposed in a first predetermined area of the chest of the target object or by a sound sensor disposed in a second predetermined area of the back of the target object, and the cut-off time of the current time window is the current moment;

[0007] Performing noise reduction processing on the initial respiratory sound data to obtain target respiratory sound data, and determining a statistical distribution feature combination corresponding to the target respiratory sound data, where the statistical distribution feature combination includes statistical distribution feature data in at least two signal domains;

[0008] Inputting the statistical distribution feature combination into a predetermined diagnostic model to obtain an initial diagnostic result, where the initial diagnostic result includes at least one respiratory sound type identifier;

[0009] Displaying the at least one respiratory sound type identifier.

[0010] According to another aspect of the present invention, there is provided a respiratory type determination device during general anesthesia, including:

[0011] A data acquisition module, configured to acquire initial respiratory sound data of a target object in a general anesthesia state under a current time window, where the initial respiratory sound data is collected by a respiratory sound acquisition device disposed in a first predetermined area of the chest of the target object or by a sound sensor disposed in a second predetermined area of the back of the target object, and the cut-off time of the current time window is the current moment;

[0012] A feature determination module, configured to perform noise reduction processing on the initial respiratory sound data to obtain target respiratory sound data, and determine a statistical distribution feature combination corresponding to the target respiratory sound data, where the statistical distribution feature combination includes statistical distribution feature data in at least two signal domains;

[0013] A diagnosis result determination module, configured to input the statistical distribution feature combination into a predetermined diagnosis model to obtain an initial diagnosis result, where the initial diagnosis result includes at least one respiratory sound type identifier;

[0014] A display module, configured to display the at least one respiratory sound type identifier.

[0015] According to another aspect of the present invention, there is provided a respiratory type determination system during general anesthesia, including:

[0016] A display device;

[0017] A sound sensor, disposed in a first predetermined area of the chest of the target object or a second predetermined area of the back of the target object, configured to collect initial respiratory sound data of the target object in a general anesthesia state under a current time window;

[0018] A processor, configured to execute the respiratory type determination method during general anesthesia according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, there is provided an electronic device, where the electronic device includes:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the respiratory type determination method during general anesthesia according to any embodiment of the present invention.

[0023] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the method for determining a respiratory type during general anesthesia according to any embodiment of the present invention when executed.

[0024] According to another aspect of the present invention, there is provided a computer program product including a computer program which implements the method for determining a respiratory type during general anesthesia according to any one of the above when executed by a processor.

[0025] In the technical solution provided by the embodiment of the present invention, the initial respiratory sound data is the respiratory sound data of a target object in a general anesthesia state in the current time window collected in real time, and the cut-off time of the current time window is the current moment. Therefore, the initial respiratory sound data can reflect the overall state of the target object in the current time window and the instantaneous state at the current moment. Denoising the initial respiratory sound can improve the data quality of the determined target respiratory sound data. By determining the statistical distribution feature combination corresponding to the target respiratory sound data, statistical distribution feature data describing the characteristics of the respiratory sound data from different levels or dimensions can be obtained, so that the statistical distribution feature combination can comprehensively reflect the current respiratory state of the target object, thereby ensuring the accuracy of the initial diagnosis result corresponding to the statistical distribution feature combination. Moreover, since the respiratory sound data is one-dimensional data, the speed of its denoising process and the determination of the statistical distribution feature combination is relatively fast, which can ensure the real-time determination of the initial diagnosis result. The real-time determination of the initial diagnosis result enables an anesthesiologist to effectively treat the target object in a timely manner.

[0026] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0028] Figure 1 is a schematic structural diagram of a system for determining a respiratory type during anesthesia according to an embodiment of the present invention;

[0029] Figure 2 is a flowchart of a method for determining a respiratory type during anesthesia according to an embodiment of the present invention;

[0030] Figure 3 is another flowchart of the method for determining the breathing type during anesthesia provided by an embodiment of the present invention;

[0031] Figure 4 is a schematic structural diagram of the device for determining the breathing type during anesthesia provided by an embodiment of the present invention;

[0032] Figure 5 is another schematic structural diagram of the device for determining the breathing type during anesthesia provided by an embodiment of the present invention;

[0033] Figure 6 is a schematic structural diagram of an electronic device for implementing the method for determining the breathing type during anesthesia according to an embodiment of the present invention. Detailed implementation manners

[0034] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0036] Figure 1 is a schematic structural diagram of the system for determining the breathing type during general anesthesia provided by an embodiment of the present invention. As Figure 1 shown, the system includes a display device, a breathing sound acquisition device and a processor; a sound sensor, which is arranged in a first predetermined area of the chest of the target object or a second predetermined area of the back of the target object, and is used to acquire the initial breathing sound data of the target object in a general anesthesia state in the current time window; a processor, which is configured to execute the method for determining the breathing type during general anesthesia described in the following embodiments.

[0037] In one embodiment, the breath sound acquisition device includes a plurality of sound sensors, which are distributed in a predetermined array on a strip surface and can be attached to the chest wall; when the breath sound acquisition device is disposed in a first predetermined area, the first predetermined area is the part from the midclavicular line to the anterior axillary line at the nipple horizontal plane of the chest; when the breath sound acquisition device is disposed in a second predetermined area, the second predetermined area is the part from the posterior axillary line to the scapular line within the subscapular region.

[0038] Specifically, the specific number of sound sensors can be determined according to actual situations. For example, the number of sound sensors included in the breath sound acquisition device for adults is more than that included in the breath sound acquisition device for children. Optionally, the plurality of sound sensors are fixedly distributed in the middle of a first surface and a second surface in a predetermined array form. The first surface is in contact with the skin of the target object, and at least the first surface of the first surface and the second surface is made of a flexible material, so that the breath sound acquisition device can be in close contact with the skin of the breath sound acquisition part and improve the sound quality of the collected breath sound.

[0039] It should be noted that in the scenario of thoracic surgery, the breath sound acquisition device needs to be attached to the part from the posterior axillary line to the scapular line within the scapular region of the target object; in the non-surgical scenario, the breath sound acquisition device can be attached to the part from the midclavicular line to the anterior axillary line at the nipple horizontal plane of the chest of the target object or the part from the posterior axillary line to the scapular line within the subscapular region.

[0040] It can be understood that in addition to including a plurality of sound sensors, the breath sound acquisition device further includes a signal conversion circuit for converting a sound signal into an electrical signal, an amplification circuit for amplifying the electrical signal, and the like.

[0041] Figure 2 The figure is a flowchart of a method for determining a breathing type during general anesthesia provided by an embodiment of the present invention. This embodiment is applicable to the situation of using breath sounds to determine the breathing type of a patient during general anesthesia. This method can be executed by a device for determining a breathing type during general anesthesia. The device for determining a breathing type during general anesthesia can be implemented in the form of hardware and / or software. The device for determining a breathing type during general anesthesia can be configured in a processor of an electronic device, a system for determining a breathing type during general anesthesia, an anesthesia machine, or a monitor. When the device for determining a breathing type during general anesthesia is disposed in the anesthesia machine and the monitor, the anesthesia machine or the monitor is configured to obtain breath sound data of a target object during general anesthesia through a breath sound acquisition device. As Figure 2 shown, the method includes:

[0042] S110. Obtain initial breath sound data of the target object. The initial breath sound data is collected by a breath sound acquisition device disposed in a first predetermined area of the chest of the target object or by a sound sensor disposed in a second predetermined area of the back of the target object.

[0043] The target object is a patient receiving general anesthesia surgery. The characteristics of breath sounds are highly non-stationary.

[0044] S120, Denoise the initial breath sound data to obtain target breath sound data, and determine the statistical distribution feature combination corresponding to the target breath sound data. The statistical distribution feature combination includes statistical distribution feature data in at least two signal domains.

[0045] Since the target breath sound data is the denoising result of the initial breath sound data, the noise level in the target breath sound data is significantly lower than that in the initial breath sound data. Therefore, using the target breath sound data for subsequent breath sound recognition can improve the accuracy of the breath sound recognition result.

[0046] In one embodiment, the existing denoising method is used to denoise the initial breath sound data to obtain the target breath sound data, such as a pre-trained denoising model, which is not elaborated in this embodiment.

[0047] The statistical distribution feature refers to the statistic that describes the data distribution. These statistics can provide information about the shape, central position, dispersion degree, symmetry, etc. of the data distribution.

[0048] The statistical distribution feature combination includes statistical distribution feature data in at least two signal domains. The at least two signal domains include at least two of the frequency domain, time domain, time-frequency joint domain, and cepstrum domain; the statistical distribution feature data includes at least two of the mean, standard deviation, skewness, and peak value.

[0049] That is to say, the statistical distribution feature combination in this embodiment includes statistical distribution feature data in at least two signal domains, and the statistical distribution feature data in each signal domain includes at least two of the mean, standard deviation, skewness, and peak value.

[0050] In one embodiment, if the statistical distribution feature combination includes statistical distribution feature data in the time domain, the statistical distribution feature data of the target breath sound data in the current time window is determined based on a predetermined time-domain statistical distribution feature determination method; if the statistical distribution feature combination includes statistical distribution feature data in the frequency domain, when determining the statistical distribution feature data in the frequency domain, the frequency spectrum data of the target breath sound data in the current time window needs to be determined first, and then the statistical distribution feature of the frequency spectrum data is determined based on a predetermined frequency-domain statistical distribution feature determination method to obtain the statistical distribution feature data in the frequency domain corresponding to the current time window; and so on, to determine the statistical distribution feature data in other signal domains. Optionally, for the statistical distribution feature data in the frequency domain, the wavelet transform result of the target breath sound data is determined, and the mean and variance of the wavelet coefficients in the wavelet transform result are used as the statistical features of the target breath sound data; the skewness and kurtosis of the wavelet coefficients in the wavelet transform result are used as the distribution features of the target breath sound data.

[0051] S130. Input the statistical distribution feature combination into a predetermined diagnosis model to obtain an initial diagnosis result, and the initial diagnosis result includes at least one breath sound type identifier.

[0052] In one embodiment, the diagnosis model can be an optionally pre-trained machine learning classification algorithm, such as applying a support vector machine, a random forest, and a neural network model.

[0053] Clinically, the breath sound types include normal breath sound type, dry rales, wet rales, wheezing, etc.

[0054] In one embodiment, the diagnosis model includes at least two sub-models, and the at least two sub-models are different types of machine learning classification models. In this embodiment, the statistical distribution feature combination is input into the at least two different types of machine learning classification models to obtain sub-diagnosis results under each machine learning classification model; the initial diagnosis result is determined according to the pre-determined weights of each machine learning classification model, the sub-diagnosis results determined by each machine learning classification model, and the voting result selection strategy.

[0055] Exemplarily, the sub-diagnosis results determined by the first sub-model and the second sub-model both include 1 and 3, and the sub-diagnosis result determined by the second sub-model includes 1, where 1 corresponds to dry rales, 2 corresponds to wet rales, and 3 corresponds to wheezing. The weight of the first sub-model is 0.3, the weight of the second sub-model is 0.5, and the weight of the third sub-model is 0.2; the voting selection strategy is that for dry rales, if the voting probability exceeds 90%, it is determined that dry rales exist, otherwise it is determined that dry rales do not exist; for wet rales, if the voting probability exceeds 90%, it is determined that wet rales exist, otherwise it is determined that wet rales do not exist; for wheezing, if the voting probability exceeds 75%, it is determined that wheezing exists, otherwise it is determined that wheezing does not exist. In this way, the probability of dry rales is 0.3 + 0.5 + 0.2 = 1, the probability of wheezing is 0.3 + 0.5 = 0.8, and the probability of wet rales is zero. Therefore, the initial diagnosis result includes 1 and 3.

[0056] In one embodiment, the diagnostic model includes an odd number of different sub-models, and the number of sub-models is greater than or equal to 3. In this embodiment, the statistical distribution feature combination is input into the odd number of different types of machine learning classification models to obtain the sub-diagnosis results under each machine learning classification model; if among all the combinations of sub-diagnosis results, the number of the first breath sound type identifiers is greater than half of the number of sub-models, then the first breath sound type identifier is added to the initial diagnostic model, otherwise, it is not added to the initial diagnostic model.

[0057] S140. Display the at least one breath sound type identifier.

[0058] In one embodiment, the breath sound type identifier is an English character; in this way, after the initial diagnosis result is determined, the initial diagnosis result is displayed in the visualization interface. This embodiment can ensure the real-time display of the initial diagnosis result.

[0059] In one embodiment, the breath sound type identifier is a number; in this way, after the initial diagnosis result is determined, based on the pre-determined correspondence between the breath sound identifier and the breath type, the breath sound type corresponding to each breath sound identifier in the initial diagnosis result is determined; then the breath sound type corresponding to each breath sound identifier is displayed in the visualization interface. This embodiment helps to improve the readability of the breath sound types displayed in the visualization interface.

[0060] In one embodiment, in the case where the initial diagnosis result includes a breath sound type identifier corresponding to a predetermined complication, predetermined association information for the predetermined complication is output.

[0061] Exemplarily, in the case where the initial diagnosis result includes identification information corresponding to cardiogenic pulmonary edema, predetermined associated information corresponding to cardiogenic pulmonary edema is displayed in the visualization interface, and the predetermined associated information includes the name of cardiogenic pulmonary edema, or includes the name of cardiogenic pulmonary edema and the treatment strategy for cardiogenic pulmonary edema during general anesthesia.

[0062] In the technical solution provided by the embodiments of the present invention, the initial breath sound data is the breath sound data of the target object in the state of general anesthesia in the currently collected current time window, and the cut-off time of the current time window is the current moment. Therefore, the initial breath sound data can reflect the overall state of the target object in the current time window and the instantaneous state at the current moment; denoising the initial breath sound can improve the data quality of the determined target breath sound data; by determining the statistical distribution feature combination corresponding to the target breath sound data, statistical distribution feature data describing the breath sound data characteristics from different levels or dimensions can be obtained, so that the statistical distribution feature combination can comprehensively reflect the current breathing state of the target object, thereby ensuring the accuracy of the initial diagnosis result corresponding to the statistical distribution feature combination; moreover, since the breath sound data is one-dimensional data, the speed of its denoising process and the determination of the statistical distribution feature combination is relatively fast, which can ensure the real-time determination of the initial diagnosis result. The real-time determination of the initial diagnosis result enables the anesthesiologist to effectively treat the target object in the first time.

[0063] Figure 3 It is a flowchart of the method for determining the breathing type during general anesthesia provided by the embodiments of the present invention, and this embodiment is used to refine the noise reduction processing step in the foregoing embodiment. As Figure 3 shown, the method includes:

[0064] S210. Obtain the initial breath sound data of the target object in the state of general anesthesia in the current time window. The initial breath sound data is collected by a breath sound acquisition device arranged in the first predetermined area of the chest of the target object, or by a sound sensor arranged in the second predetermined area of the back of the target object. The cut-off time of the current time window is the current moment.

[0065] S2201. Use a predetermined band-pass filter to perform noise reduction processing on the initial breath sound data to obtain intermediate breath sound data.

[0066] The upper cut-off frequency of the predetermined band-pass filter can be selected as 2000 Hz, and the lower cut-off frequency can be selected as 20 Hz. Through the band-pass filter, high-frequency noise other than the typical breath sound frequency band in the initial breath sound data can be filtered out.

[0067] S2202. Based on the empirical mode method, perform noise reduction processing on the intermediate breath sound data to obtain the target breath sound data.

[0068] The Empirical Mode Decomposition (EMD) method is an adaptive time-frequency analysis method for analyzing non-linear and non-stationary signals. Its core idea is to decompose a complex signal into a series of Intrinsic Mode Functions (IMFs) and a residual term. IMFs are the basic units of EMD decomposition and satisfy the following two conditions: within the entire data segment, the number of extreme points (maxima and minima) is equal to or at most differs by one from the number of zero-crossing points. At any given time, the mean of the upper envelope (obtained by interpolating the maxima) and the lower envelope (obtained by interpolating the minima) is zero.

[0069] Based on empirical mode decomposition, multiple intrinsic mode function components corresponding to the intermediate breath sound data are determined. Each intrinsic mode function component represents the characteristics of different frequencies and time scales in the signal. Generally, the high-frequency intrinsic mode function components mainly contain noise, while the low-frequency intrinsic mode function components contain the main characteristics of the signal. Therefore, by analyzing the frequency and amplitude characteristics of each intrinsic mode function component, it is possible to identify which components are noise and which components are the main characteristics.

[0070] In one embodiment, based on the Hilbert transform method, the instantaneous frequency and instantaneous amplitude corresponding to each intrinsic mode function component among the multiple intrinsic mode function components are determined; according to the instantaneous frequencies and instantaneous amplitudes corresponding to the multiple intrinsic mode function components respectively, the average spectrum of the intermediate breath sound data is determined; the intrinsic mode function components belonging to noise among the multiple intrinsic mode function components are determined, and according to the instantaneous frequencies and instantaneous amplitudes of all the intrinsic mode function components belonging to noise, the average noise spectrum of the intermediate breath sound data is determined; based on the average spectrum and the average noise spectrum of the intermediate breath sound data, the denoising process of the intermediate breath sound data is completed to obtain the target breath sound data.

[0071] Specifically, the intrinsic mode function components with frequencies higher than a predetermined frequency threshold and instantaneous amplitudes less than a predetermined amplitude threshold are regarded as the intrinsic mode function components belonging to noise; the mean value of the instantaneous amplitudes of all the intrinsic mode function components belonging to noise is determined to obtain the average noise spectrum. The average spectrum of the intermediate breath sound data is subtracted by the average noise spectrum to obtain a difference spectrum, and the signal corresponding to this difference spectrum is used as the target breath sound data. By using the combination of empirical mode decomposition and Hilbert transform, the noise in the intermediate breath sound data can be well removed, and the signal quality of the target breath sound data can be improved.

[0072] S2203. Determine the statistical distribution feature combination corresponding to the target breath sound data. The statistical distribution feature combination includes statistical distribution feature data in at least two signal domains.

[0073] S230. Input the statistical distribution feature combination into a predetermined diagnostic model to obtain an initial diagnostic result, where the initial diagnostic result includes at least one respiratory sound type identifier.

[0074] S240. Display the at least one respiratory sound type identifier.

[0075] Based on the foregoing embodiments, the embodiments of the present invention complete the denoising process of the initial respiratory sound data in a manner combining band - pass filtering and empirical mode decomposition method to obtain high - quality target respiratory sound data, ensuring the accuracy of the statistical distribution feature data of at least two signal domains determined in the subsequent steps, and thus ensuring the correctness of the initial diagnostic result based on the statistical distribution feature data in the at least two signal domains.

[0076] Figure 4 It is a schematic structural diagram of a respiratory type determination device during general anesthesia provided by an embodiment of the present invention. As Figure 4 shown, the device includes:

[0077] A data acquisition module 31, configured to acquire initial respiratory sound data of a target object in a general anesthesia state in a current time window, where the initial respiratory sound data is collected by a respiratory sound acquisition device disposed in a first predetermined area of the chest of the target object or by a sound sensor disposed in a second predetermined area of the back of the target object, and the cut - off time of the current time window is the current moment;

[0078] A feature determination module 32, configured to perform noise reduction processing on the initial respiratory sound data to obtain target respiratory sound data, and determine a statistical distribution feature combination corresponding to the target respiratory sound data, where the statistical distribution feature combination includes statistical distribution feature data in at least two signal domains;

[0079] A diagnostic result determination module 33, configured to input the statistical distribution feature combination into a predetermined diagnostic model to obtain an initial diagnostic result, where the initial diagnostic result includes at least one respiratory sound type identifier;

[0080] A display module 34, configured to display the at least one respiratory sound type identifier.

[0081] In one example, as Figure 5 shown, the device further includes a complication determination module 35, and the complication determination module 35 is configured to:

[0082] Output predetermined association information for the predetermined complication in the case where the initial diagnostic result includes a respiratory sound type identifier corresponding to a predetermined complication.

[0083] In one embodiment, the feature determination module 32 includes:

[0084] The first noise reduction unit is configured to perform noise reduction processing on the initial breath sound data by using a predetermined band-pass filter to obtain intermediate breath sound data;

[0085] The second noise reduction unit is configured to perform noise reduction processing on the intermediate breath sound data based on the empirical mode method to obtain target breath sound data.

[0086] In one embodiment, the second noise reduction unit is specifically configured to:

[0087] Determine a plurality of intrinsic mode function components corresponding to the intermediate breath sound data based on the empirical mode method;

[0088] Determine the instantaneous frequency and instantaneous amplitude corresponding to each of the intrinsic mode function components among the plurality of intrinsic mode function components based on the Hilbert transform method;

[0089] Determine the average spectrum of the intermediate breath sound data according to the instantaneous frequency and instantaneous amplitude corresponding to the plurality of intrinsic mode function components respectively;

[0090] Determine the intrinsic mode function components belonging to noise among the plurality of intrinsic mode function components, and determine the average noise spectrum of the intermediate breath sound data according to the instantaneous frequency and instantaneous amplitude of all the intrinsic mode function components belonging to noise;

[0091] Complete the denoising process of the intermediate breath sound data according to the average spectrum and average noise spectrum of the intermediate breath sound data to obtain target breath sound data.

[0092] In one embodiment, the statistical distribution feature combination includes at least one of the mean, standard deviation, skewness, and kurtosis of the breath sound statistical distribution features.

[0093] In one embodiment, the shape of the breath sound acquisition device is strip-shaped and can be attached to the chest wall;

[0094] When the breath sound acquisition device is disposed in a first predetermined area, the first predetermined area is the part from the midclavicular line to the anterior axillary line at the nipple horizontal plane of the chest;

[0095] When the breath sound acquisition device is disposed in a second predetermined area, the second predetermined area is the part from the posterior axillary line to the scapular line within the subscapular region.

[0096] In the technical solution provided by the embodiment of the present invention, the initial breath sound data is the breath sound data of the target object in the general anesthesia state under the current time window collected in real time, and the cut-off time of the current time window is the current moment. Therefore, the initial breath sound data can reflect the overall state of the target object under the current time window and the instantaneous state at the current moment. Denoising the initial breath sound can improve the data quality of the determined target breath sound data. By determining the statistical distribution feature combination corresponding to the target breath sound data, statistical distribution feature data describing the breath sound data characteristics from different levels or dimensions can be obtained, so that the statistical distribution feature combination can comprehensively reflect the current breathing state of the target object, thereby ensuring the accuracy of the initial diagnosis result corresponding to the statistical distribution feature combination. Moreover, since the breath sound data is one-dimensional data, the speed of its denoising process and the determination of the statistical distribution feature combination is relatively fast, which can ensure the real-time determination of the initial diagnosis result. The real-time determination of the initial diagnosis result enables the anesthesiologist to provide effective treatment to the target object in a timely manner.

[0097] The breathing type determination device during general anesthesia provided by the embodiment of the present invention can execute the breathing type determination method during general anesthesia provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0098] Figure 6 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0099] As Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0100] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0101] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining the breathing type during general anesthesia.

[0102] In some embodiments, the method for determining the breathing type during general anesthesia can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the breathing type during general anesthesia described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for determining the breathing type during general anesthesia by any other appropriate means (e.g., by means of firmware).

[0103] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0104] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0105] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0106] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0107] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0108] A computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship between the client and the server is created by computer programs that run on respective computers and have a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0109] An embodiment of the present invention also provides a computer program product, including a computer program which, when executed by a processor, implements the method for determining the respiratory type during general anesthesia provided in any embodiment of the present application.

[0110] In the process of implementing the computer program product, computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network - including a local area network (LAN) or a wide area network (WAN) - or, alternatively, can be connected to an external computer (e.g., by connecting through the Internet using an Internet service provider).

[0111] It should be understood that the various forms of the process shown above can be used, steps can be reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0112] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining breathing type during general anesthesia, characterized in that: include: Acquire initial breathing sound data of a target object in a state of general anesthesia in a current time window, wherein the initial breathing sound data is collected by a breathing sound collection device disposed in a first predetermined area of ​​the chest of the target object, or by a sound sensor disposed in a second predetermined area of ​​the back of the target object, and the end time of the current time window is the current moment; Performing noise reduction processing on the initial breath sound data to obtain target breath sound data, and determining a statistical distribution feature combination corresponding to the target breath sound data, wherein the statistical distribution feature combination includes statistical distribution feature data in at least two signal domains; Inputting the statistical distribution feature combination into a predetermined diagnostic model to obtain an initial diagnostic result, wherein the initial diagnostic result includes at least one respiratory sound type identifier; The at least one breath sound type identifier is displayed.

2. The method according to claim 1, characterized in that: After displaying the at least one respiratory sound type identifier, the method further includes: In a case where the initial diagnosis result includes a breath sound type identifier corresponding to a predetermined complication, predetermined associated information for the predetermined complication is output.

3. The method according to claim 1, characterized in that The performing noise reduction processing on the initial breath sound data to obtain target breath sound data includes: Using a predetermined bandpass filter to perform noise reduction processing on the initial breath sound data to obtain intermediate breath sound data; The intermediate breath sound data is subjected to noise reduction processing based on an empirical mode method to obtain target breath sound data.

4. The method according to claim 3, characterized in that The step of performing noise reduction processing on the intermediate breath sound data based on the empirical mode method to obtain target breath sound data includes: Determining a plurality of intrinsic mode function components corresponding to the intermediate breath sound data based on an empirical mode method; Determine the instantaneous frequency and instantaneous amplitude corresponding to each of the plurality of intrinsic mode function components based on the Hilbert transform method; Determining an average frequency spectrum of the intermediate breath sound data according to the instantaneous frequencies and instantaneous amplitudes respectively corresponding to the plurality of intrinsic mode function components; Determine an intrinsic mode function component belonging to noise among the multiple intrinsic mode function components, and determine an average noise spectrum of the intermediate breath sound data according to the instantaneous frequency and instantaneous amplitude of all the intrinsic mode function components belonging to the noise; According to the average spectrum and the average noise spectrum of the intermediate breath sound data, the denoising process of the intermediate breath sound data is completed to obtain the target breath sound data.

5. The method according to claim 1, characterized in that The statistical distribution characteristic data includes at least two of mean, standard deviation, skewness and kurtosis.

6. The method according to claim 1, characterized in that The respiratory sound collecting device includes a plurality of sound sensors, which are distributed on a strip surface in a predetermined array and can be attached to the chest wall; When the respiratory sound collecting device is set in the first predetermined area, the first predetermined area is the area from the midclavicular line to the anterior axillary line at the level of the nipple of the chest; When the respiratory sound collecting device is arranged in the second predetermined area, the second predetermined area is the area from the posterior axillary line to the scapular line in the subscapular region.

7. A system for determining breathing type during general anesthesia, characterized in that: include: Display device; A breathing sound collection device is arranged at a first predetermined area on the chest of the target object or a second predetermined area on the back of the target object, and is used to collect initial breathing sound data of the target object in a general anesthesia state in a current time window; A processor configured to execute the method for determining the breathing type during general anesthesia according to any one of claims 1-6.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for determining the breathing type during general anesthesia according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the breathing type during general anesthesia according to any one of claims 1 to 7 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the method for determining the breathing type during general anesthesia according to any one of claims 1 to 7.

Images