A vital sign monitoring system and method during anesthesia

Abstract

The present invention relates to the technical field of anesthesia monitoring, and particularly to a vital sign monitoring system and method during anesthesia. The time series signals of the electroencephalogram of a pregnant woman and the time series data of various vital sign parameters are obtained. In view of the different fluctuation states of the vital sign parameters in different anesthesia stages, it is necessary to determine the corresponding anesthesia stage at each moment. Subsequently, the changes and fluctuations of each vital sign parameter and the data values at the historical moments in the same anesthesia stage are analyzed to determine the fluctuation index, and the weight of each vital sign parameter at each moment is dynamically calculated. Combining the change period, data value and weight of the vital sign parameters at the historical moments, the surgical anesthesia risk index is calculated. Finally, the vital signs are monitored based on the surgical anesthesia risk index at each moment. The present invention dynamically allocates the weights of the vital sign parameters in different anesthesia stages for parameter fusion, establishes an anesthesia risk model, obtains a more accurate surgical anesthesia risk index, ensures the accuracy of the monitoring results, and realizes the prediction of the risk trend.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthesia monitoring, and particularly to a vital sign monitoring system and method during anesthesia. Background Art

[0002] In general anesthesia surgeries involving pregnant patients, anesthesia management faces multi-dimensional clinical challenges. Due to the special physiological association of the maternal-fetal dual life system, it is often necessary to construct a dual safety monitoring system to ensure the safety of the mother and fetus.

[0003] During the surgical anesthesia of pregnant women, due to the action of anesthetic drugs, the time series signals of their electroencephalograms will change significantly, and these changes are closely related to the depth of anesthesia. At the same time, various physical sign parameters of pregnant women will also show different fluctuation characteristics with different anesthesia stages.

[0004] Traditional vital sign monitoring methods often use fixed fusion weights to perform fusion analysis on all types of physical sign parameters, so as to complete data integration for vital sign monitoring and early warning. However, due to the differences in the fluctuations of vital sign parameters at different anesthesia stages, and the fixed fusion weights cannot accurately reflect these subtle changes, and often lack multi-parameter coupling analysis, resulting in inaccurate and incomplete assessment of surgical anesthesia risks, which may cause misjudgment or false early warning. Summary of the Invention

[0005] In order to solve the technical problems that the fluctuations of vital sign parameters at different anesthesia stages will produce differences, and the fixed fusion weights cannot accurately reflect these subtle changes, and often lack multi-parameter coupling analysis, resulting in inaccurate and incomplete assessment of anesthesia risks, causing misjudgment or false early warning, the purpose of the present invention is to provide a vital sign monitoring system and method during anesthesia, and the specific technical solutions adopted are as follows:

[0006] Obtain the time series signal of the electroencephalogram of the pregnant woman and the time series data of various physical sign parameters;

[0007] At each moment, perform frequency domain analysis on the local data corresponding to each moment in the electroencephalogram time series signal, and based on the data change situation in the frequency domain data, determine the anesthesia stage corresponding to each moment;

[0008] In the time series data of each physical sign parameter, analyze the change and fluctuation situation of the data value at each moment and the data value at the historical moment in the same anesthesia stage, and determine the fluctuation index of each physical sign parameter at each moment; at each moment, comprehensively compare the fluctuation indexes of all types of physical sign parameters, and thus calculate the weight of each physical sign parameter;

[0009] In the time series data of multiple physiological sign parameters, for any given moment, by combining the change cycle, data value, and weight of each physiological sign parameter at historical moments in the same anesthesia stage as this moment, the surgical anesthesia risk index at this moment is obtained;

[0010] Vital sign monitoring is performed according to the surgical anesthesia risk index at each moment.

[0011] Furthermore, the method for determining the anesthesia stage includes:

[0012] In terms of time series, for any given moment, starting from this moment, a preset number of consecutive moments are selected from historical moments to obtain the time series data segment corresponding to this moment in the electroencephalogram time series signal;

[0013] Perform a fast Fourier transform on the time series data segment corresponding to this moment to obtain frequency domain data;

[0014] Based on a preset frequency, the frequency domain data corresponding to this moment is divided to obtain different frequency bands, and the frequency bands include the Alpha band, Beta band, Theta band, and Delta band;

[0015] In each frequency band, analyze the change and fluctuation of the frequency amplitude to obtain the intensity characteristic value of each frequency band;

[0016] In the frequency domain data corresponding to this moment, when the frequency band corresponding to the maximum intensity characteristic value is the Alpha band or Beta band, it is determined that this moment is in the anesthesia recovery stage; when the frequency band corresponding to the maximum intensity characteristic value is the Theta band, it is determined that this moment is in the anesthesia induction stage; when the frequency band corresponding to the maximum intensity characteristic value is the Delta band, it is determined that this moment is in the anesthesia maintenance stage.

[0017] Furthermore, the method for obtaining the intensity characteristic value includes:

[0018] In the frequency domain data of this moment, in each frequency band, the cumulative value of the amplitudes at all frequencies is used as the first intensity factor of each frequency band;

[0019] In each frequency band, the mean value of the amplitudes at all frequencies is used as the intensity mean value, and the proportion of the intensity mean value of each frequency band in the intensity mean values of all frequency bands is used as the second intensity factor of each frequency band;

[0020] The value obtained by normalizing the product of the first intensity factor and the second intensity factor of each frequency band is used as the intensity characteristic value of each frequency band.

[0021] Furthermore, the method for obtaining the fluctuation index includes:

[0022] For any given moment, among the historical moments before this moment in time sequence, the historical moments in the same anesthesia stage as this moment are used as reference moments, and the values corresponding to this moment and all reference moments in the time sequence data of each physical sign parameter form the reference data segment of this moment;

[0023] In the reference data segment of each physical sign parameter at this moment, based on the distribution of the data, perform adaptive segmentation to obtain multiple segments, and analyze the segmentation situation of the reference data segment to determine the first fluctuation factor of each physical sign parameter at this moment;

[0024] In the reference data segment of each physical sign parameter at this moment, comprehensively analyze the fluctuation situation of the data values within all segments to determine the second fluctuation factor of each physical sign parameter at this moment;

[0025] The value obtained by normalizing the product of the first fluctuation factor and the second fluctuation factor of each physical sign parameter at this moment is used as the fluctuation index of each physical sign parameter at this moment.

[0026] Furthermore, the method for obtaining the first fluctuation factor includes:

[0027] For any given moment, in the reference data segment of each physical sign parameter at this moment, use the adaptive piecewise constant approximation method to segment the reference data segment to obtain multiple segments and the APCA approximation value of each segment;

[0028] Take the absolute value of the difference between the APCA approximation value of each segment and the mean value of the APCA approximation values of all segments as the deviation factor, and take the ratio of the deviation factor to the length of each segment as the first fluctuation coefficient of each segment;

[0029] Take the cumulative sum of the fluctuation coefficients of all segments as the first fluctuation factor of each physical sign parameter at this moment.

[0030] Furthermore, the method for obtaining the second fluctuation factor includes:

[0031] In each segment, calculate the absolute value of the difference between each data value and the mean value of all data values as the difference factor, and take the mean value of the difference factors of all data values as the second fluctuation coefficient of each segment;

[0032] Take the mean value of the fluctuation coefficients of all segments as the second fluctuation factor of each physical sign parameter at this moment.

[0033] Furthermore, the method for obtaining the weight includes:

[0034] At each moment, take the proportion of the fluctuation index of each physical sign parameter among the fluctuation indexes of all types of physical sign parameters as the weight of each physical sign parameter at each moment.

[0035] Furthermore, the method for obtaining the surgical anesthesia risk index includes:

[0036] The physical sign parameters include the pregnant woman's blood pressure, the pregnant woman's heart rate, and the fetal heart rate;

[0037] For any given moment, in the reference data segment of the pregnant woman's heart rate and the fetal heart rate at that moment, the minimum AMPD value in the reference data segment is obtained using the AMPD algorithm, and based on the time delay corresponding to the minimum AMPD value, the period value of the reference data segment of the pregnant woman's heart rate and the fetal heart rate at that moment is obtained;

[0038] The formula model of the surgical anesthesia risk index at this moment includes:

[0039] ;

[0040] Wherein, represents the surgical anesthesia risk index at this moment; represents the weight of the pregnant woman's heart rate at this moment; represents the period value of the reference data segment of the pregnant woman's heart rate at this moment; represents the value of the pregnant woman's heart rate at this moment; represents the weight of the fetal heart rate at this moment; represents the period value of the reference data segment of the fetal heart rate at this moment; represents the value of the fetal heart rate at this moment; represents the weight of the pregnant woman's blood pressure at this moment; represents the value of the pregnant woman's blood pressure at this moment; represents the natural constant; represents the normalization function.

[0041] Furthermore, the vital sign monitoring based on the surgical anesthesia risk index at each moment includes:

[0042] When the surgical anesthesia risk index at a certain moment is greater than or equal to the preset risk threshold, it is prompted that there is a surgical anesthesia risk at this moment, and an alarm is given;

[0043] When the surgical anesthesia risk index at a certain moment is less than the preset risk threshold, it is prompted that there is no surgical anesthesia risk at this moment, and no alarm is required.

[0044] A vital sign monitoring system during anesthesia includes a processor and a memory. At least one instruction, at least one program, a code set, or an instruction set is stored in the memory. When at least one instruction, at least one program, a code set, or an instruction set is loaded and executed by the processor, the steps of the vital sign monitoring method during anesthesia are implemented.

[0045] The present invention has the following beneficial effects:

[0046] First, by acquiring the time series signals of the electroencephalogram of the pregnant woman and the time series data of various physical sign parameters, it is possible to comprehensively and meticulously reflect the changes in the physiological state of the pregnant woman during the anesthesia process. In different anesthesia stages, the fluctuation states of the physical sign parameters are different, so the weights will vary. Therefore, it is necessary to determine the anesthesia stage corresponding to each moment. Given that when in different anesthesia stages, the cerebral electrical activities of the pregnant woman usually exhibit different band changes, so at each moment, frequency domain analysis is performed on the local data segments in the electroencephalogram time series signal, and based on the data changes in the frequency domain data, the anesthesia stage corresponding to each moment is determined. Then, for each moment, in the time series data of each physical sign parameter, the change fluctuations between its data value and the data value of the historical moment in the same anesthesia stage are analyzed to determine the fluctuation index. This process can quantify the fluctuations of each physical sign parameter, which helps to comprehensively compare the fluctuation indexes of all types of physical sign parameters in the subsequent process and dynamically calculate the weight of each physical sign parameter at each moment; this dynamic weight allocation method is more in line with the physiological change characteristics in the actual anesthesia process. Further, by combining the change period, data value of the physical sign parameter and the weight of each physical sign parameter at the historical moment in the same anesthesia stage as the current moment, the surgical anesthesia risk index is calculated. Finally, vital sign monitoring is performed based on the surgical anesthesia risk index at each moment. In summary, the present invention can adaptively and dynamically set the fusion weight of each physical sign parameter at each moment according to the progress stage of the anesthesia process and in combination with the physiological condition of the pregnant woman itself. Through multi-parameter fusion, a more accurate surgical anesthesia risk index is obtained for vital sign monitoring, ensuring the accuracy of the monitoring result and realizing risk trend prediction. Description of the Drawings [[ID=⑧]]

[0047] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0048] Figure 1 It is a method flow chart of a vital sign monitoring method during anesthesia provided by an embodiment of the present invention;

[0049] Figure 2 It is an electroencephalogram time series signal during the anesthesia recovery stage provided by an embodiment of the present invention;

[0050] Figure 3 It is an electroencephalogram time series signal during the anesthesia induction stage provided by an embodiment of the present invention;

[0051] Figure 4 A brainwave time series signal during the anesthesia maintenance stage provided by an embodiment of the present invention;

[0052] Figure 5 A method flowchart of a method for determining an anesthesia stage provided by an embodiment of the present invention;

[0053] Figure 6 A method flowchart of a method for obtaining a fluctuation index provided by an embodiment of the present invention;

[0054] Figure 7 A system block diagram of a vital sign monitoring system during an anesthesia process provided by an embodiment of the present invention;

[0055] Figure 8 A system structure schematic diagram of a vital sign monitoring system during an anesthesia process provided by an embodiment of the present invention. Detailed implementation manners

[0056] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following combines the accompanying drawings and preferred embodiments to detail the specific implementation manners, structures, features and effects of a vital sign monitoring system and method during an anesthesia process proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0058] The following specifically describes the specific solutions of a vital sign monitoring system and method during an anesthesia process provided by the present invention with reference to the accompanying drawings.

[0059] Please refer to Figure 1 , which shows a method flowchart of a vital sign monitoring method during an anesthesia process provided by an embodiment of the present invention. The method includes the following steps:

[0060] Step S1: Obtain the brainwave time series signal of the pregnant woman and the time series data of various physical sign parameters.

[0061] In general anesthesia surgeries involving pregnant patients, anesthesia management is crucial as it concerns the dual safety of the pregnant woman and the fetus. To ensure the safety and effectiveness of the surgical procedure, it is necessary to continuously monitor the vital signs of the mother and the fetal heart rate. By continuously monitoring various physiological parameter signals of the pregnant woman, targeted monitoring and management of the state changes during the surgical procedure can be carried out, which helps doctors promptly detect and handle potential risks, regulate the anesthesia process, and ensure the smooth progress of the surgery while guaranteeing the safety of the mother and baby.

[0062] Therefore, the acquisition and analysis of vital sign data are very important. The anesthesia process generally includes the following stages: anesthesia induction stage, anesthesia maintenance stage, and anesthesia recovery stage. Under the influence of anesthetic drugs, there are slight differences in physiological fluctuations at different stages. Therefore, in the embodiments of the present invention, when monitoring the vital signs during the anesthesia process, it is also necessary to determine which stage of the anesthesia process is currently in; in view of the fact that the electroencephalogram (EEG) activity of pregnant women usually shows different band changes at different anesthesia stages, when acquiring vital sign data, it is also necessary to acquire the EEG time series signal of the pregnant woman. It should be noted that the EEG time series data can specifically adopt the bispectral index (BIS) or the entropy index.

[0063] Specifically, before the start of the anesthesia surgery, a multi-parameter monitor and an electroencephalogram (EEG) device are placed in appropriate positions. The multi-parameter monitor is used to continuously collect the time series data of various physiological parameter signals of the pregnant woman, and the EEG device is used to continuously collect the EEG time series signal of the pregnant woman. In the embodiments of the present invention, the types of physiological parameter signals are set as the heart rate of the pregnant woman, the blood pressure of the pregnant woman, and the fetal heart rate; the sampling intervals of the EEG time series signal and the time series data of the physiological parameter signals are both set to 0.1 s. The specific time interval can be adjusted according to the implementation scenario and is not limited here. The time series data of the physiological parameter signals and the EEG time series signal are collected simultaneously and aligned in time.

[0064] In the embodiments of the present invention, the acquisition and obtaining of the physiological parameter data and EEG data of the pregnant woman are both authorized by relevant users, and the process does not violate relevant laws and regulations and does not violate public order and good customs.

[0065] Step S2: At each moment, perform frequency domain analysis on the local data corresponding to each moment in the EEG time series signal, and determine the anesthesia stage corresponding to each moment based on the data change situation in the frequency domain data.

[0066] When in different anesthesia stages, affected by anesthetic drugs, there will be subtle changes in the fluctuations of vital sign parameters. At the same time, brain waves will also exhibit different frequency characteristics. The frequency domain characteristics can provide intuitive information about the anesthesia state. For example, when in the anesthesia recovery stage, brain waves will be in the high-frequency Alpha wave (8 - 12 Hz) and Beta wave (12 - 30 Hz) intervals, as Figure 2 shown, which shows a brain wave time series signal in the anesthesia recovery stage; in the anesthesia induction stage, the mid-low frequency brain wave signals continuously increase, and Theta waves (4 - 8 Hz) appear, as Figure 3 shown, which shows a brain wave time series signal in the anesthesia induction stage; when entering the deep anesthesia state, that is, the anesthesia maintenance stage, Alpha waves completely disappear, and the brain wave signals mainly concentrate near Delta waves (0.5 - 4 Hz), as Figure 4 shown, which shows a brain wave time series signal in the anesthesia maintenance stage.

[0067] Since accurately judging the anesthesia stage helps doctors detect and handle any potential anesthesia risks in a timely manner, and can also more accurately identify the fluctuations of vital sign parameters in different anesthesia stages, which is helpful to improve the accuracy of vital sign monitoring during anesthesia. Therefore, at each moment, frequency domain analysis is performed on the local data corresponding to each moment in the brain wave time series signal, and based on the data changes in the frequency domain data, the anesthesia stage corresponding to each moment is determined.

[0068] Preferably, in an embodiment of the present invention, the method for determining the anesthesia stage includes:

[0069] Please refer to Figure 5 , which shows a flowchart of the method for determining the anesthesia stage in an embodiment of the present invention. The method includes the following steps:

[0070] Step S201: For any moment, determine the time series data segment corresponding to this moment in the brain wave time series signal.

[0071] In terms of time sequence, for any moment, starting from this moment and looking back, that is, selecting a preset number of consecutive moments in historical moments to obtain the time series data segment corresponding to this moment in the brain wave time series signal. The reason for determining the time series data segment of each moment is to ensure that there is enough data for frequency domain analysis and to maintain the accuracy of the analysis.

[0072] It should be noted that the preset number is set to the number of sampling moments within one minute, and the specific value can be adjusted according to the implementation scenario and is not limited here.

[0073] Step S202: Obtain the frequency domain data of the time series data segment corresponding to this moment.

[0074] Perform a fast Fourier transform on the time-series data segment corresponding to this moment to obtain frequency-domain data. The frequency-domain data can reveal the intensity of different frequency components in the local data corresponding to each moment, which is an important basis for judging the anesthesia stage.

[0075] It should be noted that the fast Fourier transform is a well-known technology, and the specific process will not be elaborated here.

[0076] Step S203: Divide the frequency-domain data corresponding to this moment based on a preset frequency to obtain different frequency bands.

[0077] As can be seen from the foregoing analysis, the frequency-domain characteristics of the electroencephalogram signal will vary in different anesthesia stages, which can be specifically divided into Alpha wave (8 - 12Hz), Beta wave (12 - 30Hz), Theta wave (4 - 8Hz), Delta wave (0.5 - 4Hz), etc. Therefore, based on this division method, preset frequencies of 0.5Hz, 4Hz, 8Hz, 12Hz, and 30Hz are set to divide the frequency-domain data, obtaining different frequency bands, including Alpha band, Beta band, Theta band, and Delta band. Each band corresponds to the aforementioned Alpha wave, Beta wave, Theta wave, and Delta wave respectively.

[0078] Step S204: In each frequency band, analyze the change and fluctuation of the frequency amplitude to obtain the intensity characteristic value of each frequency band.

[0079] For any moment, in the frequency-domain data at this moment, in each frequency band, the cumulative value of the amplitudes at all frequencies is used as the first intensity factor of each frequency band. The first intensity factor reflects the total energy or intensity of the electroencephalogram signal in each frequency band, and the larger this value, the higher the signal intensity in the frequency band, indicating that the signal intensity in the frequency-domain data of the time-series data segment corresponding to this moment in this frequency band is greater.

[0080] In each frequency band, the mean value of the amplitudes at all frequencies is used as the intensity mean value. Then, calculate the sum value of the intensity mean values of all frequency bands, and use the ratio of the intensity mean value of each frequency band to the sum value of the intensity mean values of all frequency bands as the second intensity factor of each frequency band. The second intensity factor considers the relative position of the average intensity or energy of the electroencephalogram signal in each frequency band in all frequency bands. The larger this value, the more important the frequency band occupies in the whole, that is, the more significant the feature.

[0081] Based on the foregoing analysis, the larger the first intensity factor corresponding to a certain frequency band, the higher the signal intensity in that frequency band; the larger the second intensity factor, the more prominent the characteristics of that frequency band in the whole. Therefore, finally, the value obtained by normalizing the product of the first intensity factor and the second intensity factor of each frequency band is used as the intensity characteristic value of each frequency band. At this time, the larger the intensity characteristic value of a certain frequency band, the more dominant this frequency band can be regarded as in the frequency domain data. Among them, normalization is a well-known technical means to those skilled in the art. The choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0082] Step S205: Compare the intensity characteristic values of each frequency band in the frequency domain data of the time series data segment at this moment, so as to determine the anesthesia stage at this moment.

[0083] In the frequency domain data corresponding to this moment, when the frequency band corresponding to the maximum intensity characteristic value is the Alpha band or the Beta band, it means that these two frequency bands are dominant, that is, the data intensity in these two frequency bands is the largest in the frequency domain data corresponding to this moment. Then it can be regarded that this moment is in the anesthesia recovery stage; similarly, when the frequency band corresponding to the maximum intensity characteristic value is the Theta band, it is judged that this moment is in the anesthesia induction stage; when the frequency band corresponding to the maximum intensity characteristic value is the Delta band, it is judged that this moment is in the anesthesia maintenance stage.

[0084] Step S₃: In the time series data of each kind of physical sign parameter, analyze the change and fluctuation of the data value at each moment compared with the data value at the historical moment in the same anesthesia stage, and determine the fluctuation index of each kind of physical sign parameter at each moment; at each moment, comprehensively compare the fluctuation indexes of all kinds of physical sign parameters, so as to calculate the weight of each kind of physical sign parameter.

[0085] During the anesthesia of pregnant women, it is necessary to monitor the vital signs during anesthesia by combining multiple vital signs. Since the degree of change of vital sign data in different stages of the anesthesia process is different, fixed data fusion parameters will judge the physiological fluctuations caused by normal surgical procedures as abnormal, resulting in inaccurate anesthesia monitoring results. Therefore, in order to ensure that the contribution degree of different vital sign data to the monitoring results can accurately reflect the data fluctuations and make them fully integrated, it is necessary to analyze the change and fluctuation of the data at the moments in the same anesthesia stage, obtain the fluctuation index of each kind of physical sign parameter, and then quantify the weight of each kind of physical sign parameter.

[0086] Vital sign data often has a certain regularity. However, there are various unexpected factors during anesthesia surgery, which can cause abnormal fluctuations in vital sign data. By analyzing the change and fluctuation of the data value at each moment compared with the data value at the historical moment in the same anesthesia stage in the time series data of each sign parameter, the fluctuation characteristics that may lead to different data in different anesthesia stages can be captured in a timely manner, and the fluctuation index of each sign parameter at each moment can be determined.

[0087] Preferably, the method for obtaining the fluctuation index in an embodiment of the present invention includes:

[0088] Please refer to Figure 6 , which shows the flowchart of the method for obtaining the fluctuation index in an embodiment of the present invention. The method includes the following steps:

[0089] Step S301: For any moment, trace back in time series to determine the reference data segment at this moment.

[0090] For any moment, among the historical moments before this moment in time series, the historical moments in the same anesthesia stage as this moment are used as reference moments, and the numerical values corresponding to this moment and all reference moments in the time series data of each sign parameter are used to form the reference data segment at this moment. By determining the reference data segment, only the data in the same anesthesia stage needs to be considered in the subsequent calculation process, thereby excluding the interference of different anesthesia stages on the analysis of the data fluctuation of sign parameters and making the analysis result more accurate.

[0091] Step S302: In the reference data segment of each sign parameter at this moment, perform adaptive segmentation based on the data distribution to obtain multiple segments, and analyze the segmentation situation of the reference data segment to determine the first fluctuation factor of each sign parameter at this moment.

[0092] For any moment, in the reference data segment of each sign parameter at this moment, use the adaptive piecewise constant approximation method to segment the reference data segment to obtain multiple segments and the APCA approximation value of each segment. The adaptive piecewise constant approximation method can better capture the local characteristics of the data and make the data in each segment have relatively similar change characteristics, which is convenient for more accurate and detailed analysis of the change and fluctuation of sign parameters.

[0093] Take the absolute value of the difference between the APCA approximation value of each segment and the mean of the APCA approximation values of all segments as the deviation factor. The deviation factor measures the difference between the APCA approximation value of each segment and the mean of the APCA approximation values of all segments. This difference reflects the fluctuation degree of each segment of data relative to the average level of the overall data, and the larger the value, the greater the fluctuation.

[0094] The ratio of the deviation factor to the length of each segment is used as the first fluctuation coefficient of each segment. The first fluctuation coefficient reflects the degree of data fluctuation per unit length, making the comparison of fluctuation coefficients for segments of different lengths more fair. The larger the value, the more prominent the data fluctuation within a certain segment.

[0095] Finally, the sum of the fluctuation coefficients of all segments is used as the first fluctuation factor of each physical sign parameter at this moment. The first fluctuation factor comprehensively reflects the overall data fluctuation within the entire reference data segment. Through accumulation, the local fluctuation situation can be integrated into a global fluctuation index, facilitating subsequent analysis and decision-making. The larger the first fluctuation factor, the more obvious the fluctuation characteristics of the physical sign parameter at this moment.

[0096] It should be noted that the adaptive piecewise constant approximation method is a well-known technology, and the specific process will not be elaborated here.

[0097] Step S303: In the reference data segment of each physical sign parameter at this moment, comprehensively analyze the data value fluctuations within all segments to determine the second fluctuation factor of each physical sign parameter at this moment.

[0098] In each segment, calculate the absolute value of the difference between each data value and the mean of all data values as the difference factor. The difference factor can be used to reflect the degree of dispersion between data. The larger the difference factor, the higher the degree of deviation between data and the greater the degree of dispersion.

[0099] The mean of the difference factors of all data values is used as the second fluctuation coefficient of each segment. The second fluctuation coefficient reflects the overall data fluctuation degree within each segment. The larger the value, the more dispersed the data and the greater the fluctuation; conversely, the smaller the value, the more concentrated the data and the smaller the fluctuation.

[0100] Finally, the mean of the fluctuation coefficients of all segments is used as the second fluctuation factor of each physical sign parameter at this moment. The second fluctuation factor integrates the discrete fluctuation degree of data in all segments. The larger the value, the greater the data volatility of the physical sign parameter at this moment.

[0101] Step S304: Under each physical sign parameter, fuse the first fluctuation factor and the second fluctuation factor at this moment to obtain the fluctuation index of each physical sign parameter at this moment.

[0102] Based on the foregoing analysis, the larger the first fluctuation factor, the more obvious the fluctuation characteristics of the physiological sign parameters at that moment; the second fluctuation factor integrates the discrete fluctuation degree of the data in all segments, and the larger the value, the greater the volatility of the data of the physiological sign parameters at that moment. Therefore, the value obtained by normalizing the product of the first fluctuation factor and the second fluctuation factor of each physiological sign parameter at that moment is used as the fluctuation index of each physiological sign parameter at that moment. At this time, the larger the fluctuation index, the more obvious the fluctuation of the physiological sign parameter at that moment, and the higher the possibility of abnormality. Among them, normalization is a well-known technical means to those skilled in the art. The choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0103] During the anesthesia process, the state of the pregnant woman is comprehensively reflected by a variety of physiological sign parameters, and each physiological sign parameter reflects the physiological state of the pregnant woman from different angles. By comprehensively comparing the fluctuation indexes of all types of physiological sign parameters, the overall state of the patient can be evaluated more comprehensively and accurately, so as to avoid the one-sidedness that may be brought by single-parameter evaluation. And the importance of different physiological sign parameters in evaluating the patient's state is different. Some parameters may be more sensitive and can reflect the physiological changes of the pregnant woman earlier; while some parameters may be more stable, but also have important reference value. Therefore, by calculating the weight of each physiological sign parameter, reasonable weight allocation can be carried out according to its importance and volatility in actual application. This can not only improve the accuracy of the evaluation, but also make the evaluation result more in line with the clinical reality.

[0104] Preferably, in an embodiment of the present invention, the method for obtaining the weight includes:

[0105] At each moment, the proportion of the fluctuation index of each physiological sign parameter in the fluctuation indexes of all types of physiological sign parameters is used as the weight of each physiological sign parameter at each moment. At this time, the larger the weight of a certain physiological sign parameter, the greater the fluctuation degree of this physiological sign parameter during the operation, so the attention should be increased, and thus it should have a higher proportion in the final fusion process.

[0106] Step S4: In the time-series data of multiple physiological sign parameters, for any moment, combine the change period, data value of the physiological sign parameters at the historical moment in the same anesthesia stage as this moment, and the weight of each physiological sign parameter to obtain the surgical anesthesia risk index at this moment.

[0107] In general anesthesia surgeries involving pregnant patients, the anesthesia process goes through multiple stages, and different stages of anesthesia may lead to different fluctuation characteristics in vital sign data. During the anesthesia induction stage, general anesthetic drugs (such as propofol and remifentanil) can cause vasodilation and myocardial depression, easily triggering hypotension and bradycardia. The fluctuations in blood pressure and heart rate are often greater than those of the fetal heart rate. During the anesthesia maintenance stage, the physiological responses of the pregnant woman gradually stabilize, and the state of the fetus is affected by the state of the pregnant woman, with certain fluctuations possible; during the anesthesia recovery stage, pain or stress reactions may cause a sudden increase in blood pressure and a rapid increase in heart rate, and there are often significant fluctuations in the vital signs of the mother and the fetal heart rate. Therefore, during the process of monitoring vital signs, for any given moment, the change cycle and data values of the vital sign parameters at historical moments in the same anesthesia stage as that moment are combined to characterize the change fluctuations of the vital sign parameters; and, because the importance of different types of vital sign parameters is different, the weights of each type of vital sign parameter are combined to ensure the accuracy of the monitoring results, thereby obtaining the surgical anesthesia risk index at that moment.

[0108] Preferably, in an embodiment of the present invention, the method for obtaining the surgical anesthesia risk index includes:

[0109] In an embodiment of the present invention, the vital sign parameters include the blood pressure of the pregnant woman, the heart rate of the pregnant woman, and the fetal heart rate.

[0110] Monitoring the blood pressure, heart rate, and fetal heart rate of the pregnant woman can timely detect abnormal data changes during the surgery. When the heart rate of the pregnant woman is abnormal or the fetus is hypoxic, the monitoring results of the heart rate of the pregnant woman and the fetal heart rate will change abnormally, thereby causing a relatively obvious change in the period and data trend of the data within the current anesthesia stage. And when the period of the data becomes smaller and the data trend becomes smaller, it usually means that the vital signs are gradually deteriorating, indicating an increased risk during the surgery and should attract attention; during the surgery, due to factors such as the effect of anesthetic drugs, the blood pressure data of the pregnant woman will show a decaying trend. When the value is large, it indicates that the blood pressure is relatively stable, and the surgical anesthesia risk is considered small. On the contrary, if the value is small, it may indicate that the physiological state of the pregnant woman is rapidly deteriorating, and the surgical anesthesia risk increases, which also requires attention.

[0111] Therefore, for any given moment, in the reference data segment of the heart rate of the pregnant woman and the fetal heart rate at that moment (the reference data segment refers to the data segment in the same anesthesia stage, and the specific acquisition method is recorded in step S3), the minimum AMPD value in the reference data segment of the heart rate of the pregnant woman and the fetal heart rate is respectively obtained using the AMPD algorithm, and the period value of the reference data segment of the heart rate of the pregnant woman and the fetal heart rate corresponding to that moment is obtained based on the time delay corresponding to the minimum AMPD value.

[0112] Based on the foregoing analysis, a formula model for constructing the surgical anesthesia risk index at that moment is:

[0113] ;

[0114] Wherein, represents the surgical anesthesia risk index at this moment; represents the weight of the pregnant woman's heart rate at this moment; represents the period value of the reference data segment of the pregnant woman's heart rate at this moment; represents the value of the pregnant woman's heart rate at this moment; represents the weight of the fetal heart rate at this moment; represents the period value of the reference data segment of the fetal heart rate at this moment; represents the value of the fetal heart rate at this moment; represents the weight of the pregnant woman's blood pressure at this moment; represents the value of the pregnant woman's blood pressure at this moment; represents the natural constant; represents the normalization function.

[0115] In the formula model of the surgical anesthesia risk index, when the period value and the value of the pregnant woman's heart rate decrease, it is considered that the vital signs are gradually deteriorating and the intraoperative risk increases. Therefore, both the period value and the value of the pregnant woman's heart rate are negatively correlated with the surgical anesthesia risk index. Therefore, in the formula model, the product of the period value and the value of the pregnant woman's heart rate is subjected to a negative correlation mapping to correct the logical relationship and obtain the first risk factor , the larger this value, the greater the surgical anesthesia risk at this moment; the analysis of the fetal heart rate is the same, so as to obtain the second risk factor at the current moment; Similarly, since the smaller the attenuation of the pregnant woman's blood pressure data, the more stable the blood pressure is considered and the smaller the surgical anesthesia risk is, the value of the pregnant woman's blood pressure is subjected to a negative correlation mapping to correct the logical relationship, so as to obtain the third risk factor at the current moment, the larger this value, the greater the surgical anesthesia risk at the current moment. Finally, it is necessary to integrate the surgical anesthesia risk degrees characterized by the three physical sign parameters. Based on the analysis in step S3, when the weight of a certain physical sign parameter is larger, it means that the fluctuation degree of this physical sign parameter during the operation is larger, then the attention should be improved and it should have a higher proportion in the final fusion process. Therefore, the weights calculated by each physical sign parameter are used to weight the risk factors to increase the proportion of more important physical sign parameters, and the corresponding weighted risk factors are obtained. Finally, the normalized value of the sum of the weighted risk factors is used as the surgical anesthesia risk index at this moment, and the larger the value of the surgical anesthesia risk index, the higher the anesthesia risk, and the doctor should be reminded to conduct an examination in time.

[0116] It should be noted that the AMPD algorithm is a well-known technology, and the specific process will not be elaborated here.

[0117] Thus, the surgical anesthesia risk indicators at each moment can be obtained.

[0118] Step S5: Perform vital sign monitoring according to the surgical anesthesia risk indicators at each moment.

[0119] When performing real-time monitoring of the vital signs during the general anesthesia surgery for pregnant women, the vital sign monitoring can be carried out according to the surgical anesthesia risk indicators at a certain moment.

[0120] Preferably, in an embodiment of the present invention, performing vital sign monitoring according to the surgical anesthesia risk indicators at each moment includes:

[0121] Based on the foregoing analysis, it can be seen that the greater the surgical anesthesia risk indicator, the higher the surgical anesthesia risk. The doctor should be reminded to perform an examination in a timely manner. Therefore, when the surgical anesthesia risk indicator at a certain moment is greater than or equal to the preset risk threshold, it is prompted that there is a surgical anesthesia risk at this moment for early warning; on the contrary, when the surgical anesthesia risk indicator at a certain moment is less than the preset risk threshold, it is prompted that there is no anesthesia risk at this moment and no early warning is required.

[0122] It should be noted that the preset risk threshold is 0.65, and the specific value can be adjusted according to the implementation scenario and will not be limited here.

[0123] In summary, in the embodiments of the present invention, by first obtaining the time-series signals of the electroencephalogram of a pregnant woman and the time-series data of various physical sign parameters, the physiological state changes of the pregnant woman during the anesthesia process can be comprehensively and meticulously reflected. In different anesthesia stages, the fluctuation states of the physical sign parameters are different, so the weights will vary. Therefore, it is necessary to determine the anesthesia stage corresponding to each moment. Given that when in different anesthesia stages, the brain electrical activities of the pregnant woman usually exhibit different band changes, so at each moment, frequency-domain analysis is performed on the local data segments in the electroencephalogram time-series signals, and based on the data change conditions in the frequency-domain data, the anesthesia stage corresponding to each moment is determined. Then for each moment, in the time-series data of each physical sign parameter, the change fluctuations between its data value and the data value at the historical moment in the same anesthesia stage are analyzed to determine the fluctuation index. This process can quantify the fluctuation conditions of each physical sign parameter, thereby helping to comprehensively compare the fluctuation indexes of all types of physical sign parameters in the subsequent process and dynamically calculate the weight of each physical sign parameter at each moment; this way of dynamically allocating weights is more in line with the physiological change characteristics in the actual anesthesia process. Further, in combination with the change period, data value of the physical sign parameter at the historical moment in the same anesthesia stage as the current moment and the weight of each physical sign parameter, the surgical anesthesia risk index is calculated. Finally, based on the surgical anesthesia risk index at each moment, vital sign monitoring is performed. The embodiments of the present invention can adaptively set the fusion weights of each physical sign parameter at each moment according to the progress stage of the anesthesia process and in combination with the physiological condition of the pregnant woman herself, so as to obtain a more accurate surgical anesthesia risk index for vital sign monitoring and ensure the accuracy of the monitoring results.

[0124] The embodiments of the present invention also provide a vital sign monitoring system during the anesthesia process. Please refer to Figure 7 , which shows a system block diagram, including a data acquisition module 701 for implementing step S1 in the above method embodiment; an anesthesia stage judgment module 702 for implementing step S2 in the above method embodiment; a weight analysis module 703 for implementing step S3 in the above method embodiment; a surgical anesthesia risk index calculation module 704 for implementing step S4 in the above method embodiment; and a vital sign monitoring module 705 for implementing step S5 in the above method embodiment.

[0125] It should be noted that for the system provided in the above embodiment, only the above division of each functional module is used for illustration. In actual application, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, a vital sign monitoring system during the anesthesia process provided in the above embodiment and an embodiment of a vital sign monitoring method during the anesthesia process belong to the same concept. For the specific implementation process, please refer to the method embodiment and will not be elaborated here.

[0126] Please refer to Figure 8 , which shows a schematic structural diagram of a vital sign monitoring system during anesthesia provided by an embodiment of the present invention, including a processor 800, a memory 801, a bus 802, and a communication interface 803. The processor 800, the communication interface 803, and the memory 801 are connected through the bus 802. Among them, the memory 801 may include a high-speed random access memory. The bus 802 may be an ISA bus, a PCI bus, an EISA bus, etc. The processor 800 may be an integrated circuit chip with signal processing capabilities. At least one instruction, at least one program, a code set, or an instruction set is stored in the memory 801. When at least one instruction, at least one program, a code set, or an instruction set is loaded and executed by the processor, the steps in a vital sign monitoring method during anesthesia are implemented.

[0127] It should be noted that the above order of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0128] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key points of each embodiment are the differences from other embodiments.

Claims

1. A method for monitoring vital signs during anesthesia, characterized in that, The method includes: Obtaining the time series signal of the electroencephalogram of the pregnant woman and the time series data of various physical sign parameters; At each moment, perform frequency domain analysis on the local data corresponding to each moment in the electroencephalogram time series signal, and based on the data change situation in the frequency domain data, determine the anesthesia stage corresponding to each moment; In the time series data of each physical sign parameter, analyze the change and fluctuation situation of the data value at each moment and the data value at the historical moment in the same anesthesia stage, and determine the fluctuation index of each physical sign parameter at each moment; at each moment, comprehensively compare the fluctuation indexes of all types of physical sign parameters, and thus calculate the weight of each physical sign parameter; In the time series data of multiple physical sign parameters, for any moment, combine the change period of the physical sign parameters at the historical moment in the same anesthesia stage as this moment, the data value corresponding to this moment in the time series data of each physical sign parameter, and the weight of each physical sign parameter, to obtain the surgical anesthesia risk index at this moment; Perform vital sign monitoring according to the surgical anesthesia risk index at each moment.

2. The method for monitoring vital signs during anesthesia according to claim 1, characterized in that, The method for determining the anesthesia stage includes: In terms of time series, for any moment, starting from this moment, select a preset number of consecutive moments in the historical moments to obtain the time series data segment corresponding to this moment in the electroencephalogram time series signal; Perform fast Fourier transform on the time series data segment corresponding to this moment to obtain frequency domain data; Based on a preset frequency, divide the frequency domain data corresponding to this moment to obtain different frequency bands, and the frequency bands include Alpha band, Beta band, Theta band, and Delta band; In each frequency band, analyze the change and fluctuation situation of the frequency amplitude, so as to obtain the intensity characteristic value of each frequency band; In the frequency domain data corresponding to this moment, when the frequency band corresponding to the maximum intensity characteristic value is the Alpha band or the Beta band, it is determined that this moment is in the anesthesia awakening stage; when the frequency band corresponding to the maximum intensity characteristic value is the Theta band, it is determined that this moment is in the anesthesia induction stage; when the frequency band corresponding to the maximum intensity characteristic value is the Delta band, it is determined that this moment is in the anesthesia maintenance stage.

3. The method for monitoring vital signs during anesthesia according to claim 2, wherein The method for obtaining the intensity characteristic value includes: In the frequency domain data of this moment, in each frequency band, take the cumulative value of the amplitudes at all frequencies as the first intensity factor of each frequency band; In each frequency band, take the mean value of the amplitudes at all frequencies as the intensity mean value, and take the proportion of the intensity mean value of each frequency band in the intensity mean values of all frequency bands as the second intensity factor of each frequency band; Take the normalized value of the product of the first intensity factor and the second intensity factor of each frequency band as the intensity characteristic value of each frequency band.

4. The vital sign monitoring method during anesthesia according to claim 1, wherein, The method for obtaining the fluctuation index includes: For any moment, in the historical moments before this moment in terms of time series, take the historical moments in the same anesthesia stage as this moment as the reference moments, and form the reference data segment of this moment with the numerical values corresponding to this moment and all reference moments in the time series data of each physical sign parameter; At this moment, in the reference data segment of each physical sign parameter, adaptive segmentation is performed based on the data distribution to obtain multiple segments, and the segmentation situation of the reference data segment is analyzed to determine the first fluctuation factor of each physical sign parameter at this moment; At this moment, in the reference data segment of each physical sign parameter, comprehensively analyze the fluctuation situation of the data values within all segments to determine the second fluctuation factor of each physical sign parameter at this moment; Take the normalized value of the product of the first fluctuation factor and the second fluctuation factor of each physical sign parameter at this moment as the fluctuation index of each physical sign parameter at this moment.

5. The vital sign monitoring method during anesthesia according to claim 4, wherein The method for obtaining the first fluctuation factor includes: For any moment, in the reference data segment of each physical sign parameter at this moment, use the adaptive piecewise constant approximation method to segment the reference data segment to obtain multiple segments and the APCA approximation value of each segment; Take the absolute value of the difference between the APCA approximation value of each segment and the mean value of the APCA approximation values of all segments as the deviation factor, and take the ratio of the deviation factor to the length of each segment as the first fluctuation coefficient of each segment; Take the sum of the fluctuation coefficients of all segments as the first fluctuation factor of each physical sign parameter at this moment.

6. The method for monitoring vital signs during anesthesia according to claim 5, wherein The method for obtaining the second fluctuation factor includes: In each segment, calculate the absolute value of the difference between each data value and the mean value of all data values as the difference factor, and take the mean value of the difference factors of all data values as the second fluctuation coefficient of each segment; Take the mean value of the fluctuation coefficients of all segments as the second fluctuation factor of each physical sign parameter at this moment.

7. A method for monitoring vital signs during anesthesia according to claim 1, characterized in that The method for obtaining the weight includes: At each moment, take the proportion of the fluctuation index of each physical sign parameter in the fluctuation indexes of all types of physical sign parameters as the weight of each physical sign parameter at each moment.

8. A method for monitoring vital signs during anesthesia according to claim 1, characterized in that The method for obtaining the surgical anesthesia risk index includes: The physical sign parameters include pregnant woman's blood pressure, pregnant woman's heart rate, and fetal heart rate; For any moment, in the reference data segments of the pregnant woman's heart rate and fetal heart rate at this moment, use the AMPD algorithm to obtain the minimum AMPD value in the reference data segment, and obtain the period value of the reference data segments of the pregnant woman's heart rate and fetal heart rate corresponding to this moment based on the time delay corresponding to the minimum AMPD value; The formula model of the surgical anesthesia risk index at this moment includes: ; Among them, represents the surgical anesthesia risk index at this moment; represents the weight of the pregnant woman's heart rate at this moment; represents the period value of the reference data segment of the pregnant woman's heart rate at this moment; represents the value of the pregnant woman's heart rate at this moment; represents the weight of the fetal heart rate at this moment; represents the period value of the reference data segment of the fetal heart rate at this moment; represents the value of the fetal heart rate at this moment; represents the weight of the pregnant woman's blood pressure at this moment; represents the value of the pregnant woman's blood pressure at this moment; represents the natural constant; represents the normalization function.

9. A method for monitoring vital signs during anesthesia according to claim 1, characterized in that The life sign monitoring according to the surgical anesthesia risk index at each moment includes: When the surgical anesthesia risk index at a certain moment is greater than or equal to the preset risk threshold, it is prompted that there is a surgical anesthesia risk at this moment for early warning; When the surgical anesthesia risk index at a certain moment is less than the preset risk threshold, it is prompted that there is no surgical anesthesia risk at this moment and no early warning is required.

10. A vital sign monitoring system during anesthesia, characterized in that, It includes a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory. When at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor, the steps of a method for monitoring life signs during anesthesia as described in any one of claims 1-9 are implemented.

Images