Anesthesia efficacy evaluation method and system based on multi-parameter physiological signals

Abstract

The invention relates to the technical field of anesthesia monitoring, in particular to an anesthesia efficacy evaluation method and system based on multi-parameter physiological signals, and the method comprises the steps: obtaining the brain wave, oxyhemoglobin saturation, respiratory rate, blood pressure and heart rate of a monitored person, and according to the data characteristics of a frequency band curve of a plurality of waveforms corresponding to the brain wave, evaluating the efficacy of the monitored person; determining an anesthesia efficiency index of the monitored person; according to the monitoring curve of the oxyhemoglobin saturation and the respiratory rate, the respiratory resistance condition of the current time period is analyzed, and in combination with the anesthesia efficiency index, the respiratory inhibition index of the monitored person is determined; analyzing the abnormal change condition of the blood pressure and the heart rate according to the monitoring curve of the blood pressure and the heart rate, and determining the anesthesia stress degree of the monitored person; and determining an anesthesia efficacy evaluation value of the current time period according to the respiratory inhibition index and the anesthesia stress degree. According to the method, the defects of static multi-dimensional physiological parameter fusion analysis are overcome to a certain extent, and the accuracy of an anesthesia efficacy evaluation result is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthesia monitoring, and in particular to an anesthetic efficacy evaluation method and system based on multi-parameter physiological signals. Background Art

[0002] The use of anesthetics plays a crucial role in modern medicine, particularly in surgical procedures and pain management. However, due to individual variability and the influence of various external factors, the evaluation and monitoring of anesthetic efficacy remains a major challenge in clinical anesthesiology. Existing anesthesia monitoring systems acquire physiological signals through multi-parameter sensing and generate features through preprocessing steps such as wavelet denoising and motion artifact removal.

[0003] However, the accuracy of existing assessments is limited by: isolated parameter analysis and independent feature extraction processes, which ignore the physiological correlations between parameters; and static fusion defects. Linear combinations such as the existing BIS (Bispectral Index) cannot express pathological coupling and are unable to adapt to dynamic pathological states. Therefore, the current lack of effective data fusion strategies for anesthetic efficacy assessments can lead to low accuracy and reliability of anesthetic efficacy assessment results. Summary of the Invention

[0004] In order to solve the technical problem of low accuracy of the existing anesthetic efficacy evaluation results, the present invention aims to provide an anesthetic efficacy evaluation method and system based on multi-parameter physiological signals. The technical solutions adopted are as follows:

[0005] An embodiment of the present invention provides a method for evaluating anesthetic efficacy based on multi-parameter physiological signals, the method comprising the following steps:

[0006] Acquire physiological parameters of several dimensions corresponding to the current time period when the monitored person is in the target anesthesia stage, including brain waves, blood oxygen saturation, respiratory rate, blood pressure, and heart rate. The target anesthesia stage is the core stage for evaluating drug efficacy;

[0007] Analyzing the sedation depth of the current period based on the data characteristics of the frequency band curves of the plurality of waveforms corresponding to the brain waves, and determining the anesthesia efficiency index of the monitored person in the current period;

[0008] Analyzing the respiratory resistance of the current period according to the monitoring curves of the blood oxygen saturation and the respiratory rate, and determining the respiratory inhibitory index of the anesthetic effect on the monitored person in the current period in combination with the anesthesia efficiency index of the current period;

[0009] Analyzing abnormal changes in blood pressure and heart rate according to the monitoring curves of the blood pressure and the heart rate to determine the degree of anesthesia stress of the monitored person in the current period;

[0010] An anesthetic efficacy evaluation value for the current period is determined according to the respiratory inhibitory index and the anesthetic stress degree.

[0011] Furthermore, analyzing the sedation depth of the current period based on the data features of the frequency band curves of the plurality of waveforms corresponding to the brain waves and determining the anesthesia efficiency index of the monitored person in the current period includes:

[0012] Performing Fourier transform on the brain waves of the current period, and then extracting curves of frequency bands corresponding to several waveforms in the brain wave frequency domain to obtain frequency band curves of each waveform, wherein the waveforms include beta waves and theta waves;

[0013] Determining the sedation depth index of the monitored person during the current period based on the difference between the previous slope and the next slope in the frequency band curve of the beta wave and the correlation between the amplitude data set and the frequency data set of the frequency band curve of the theta wave;

[0014] Obtaining the BIS value of the monitored person during the current period, and determining the anesthetic efficiency index of the monitored person during the current period in combination with the sedation depth index;

[0015] The BIS value is negatively correlated with the anesthesia efficiency index, and the sedation depth is positively correlated with the anesthesia efficiency index.

[0016] Furthermore, determining the sedation depth index of the monitored person in the current time period includes:

[0017] In the frequency band curve of the β wave, the slope between two adjacent data points is calculated to obtain the slope sequence;

[0018] Calculating the difference between the previous slope and the next slope in the slope sequence, and taking the average of all the differences as the degree of trend reduction;

[0019] Obtaining a correlation coefficient between the amplitude data set and the frequency data set;

[0020] Determining a sedation depth index of the monitored person during the current period by combining the correlation coefficient and the trend reduction degree;

[0021] The correlation coefficient is negatively correlated with the sedation depth index, and the trend reduction degree is positively correlated with the sedation depth index.

[0022] Furthermore, the analyzing of the respiratory resistance in the current period based on the monitoring curves of the blood oxygen saturation and the respiratory rate, and determining the respiratory inhibitory index of the anesthetic effect on the monitored person in the current period in combination with the anesthesia efficiency index of the current period, includes:

[0023] Analyzing fluctuations in monitoring data according to the blood oxygen saturation monitoring curve to determine a first respiratory depression factor;

[0024] Analyzing the distribution and numerical abnormality of respiratory frequency data according to the respiratory frequency monitoring curve to determine a second respiratory inhibition factor;

[0025] Determining a respiratory depression index of the monitored person during a current period of time by combining the first respiratory depression factor, the second respiratory depression factor, and the anesthesia efficiency index;

[0026] Among them, the first respiratory inhibition factor, the second respiratory inhibition factor and the anesthesia efficiency index are all positively correlated with the respiratory inhibition index.

[0027] Furthermore, determining the second respiratory inhibition factor includes:

[0028] Evenly dividing the respiratory frequency monitoring curve into a plurality of local time periods, and calculating the quality heterogeneity index of the respiratory frequency in all local time periods of the current period;

[0029] Obtaining a lower limit value of a normal respiratory frequency range, analyzing the difference between the respiratory frequency value of each data point in the respiratory frequency monitoring curve and the lower limit value, and determining the degree of numerical abnormality of the respiratory frequency in the current period;

[0030] Determining a second respiratory depression factor by combining the qualitative index and the degree of numerical abnormality;

[0031] Among them, the qualitative anomaly index is negatively correlated with the second respiratory inhibition factor, and the numerical abnormality degree is positively correlated with the second respiratory inhibition factor.

[0032] Furthermore, analyzing abnormal changes in blood pressure and heart rate based on the monitoring curves of the blood pressure and heart rate to determine the degree of anesthesia stress of the monitored person in the current period includes:

[0033] Obtaining a first blood pressure data subset and a second blood pressure data subset after division according to the blood pressure data set of the blood pressure monitoring curve;

[0034] determining a degree of abnormal blood pressure increase based on a blood pressure difference between the first blood pressure data subset and the second blood pressure data subset;

[0035] By calculating the slope of every two adjacent data points in the heart rate monitoring curve, the heart rate value corresponding to the maximum slope is selected as the target heart rate value;

[0036] determining the degree of abnormality of the heart rate performance based on the difference between the target heart rate value and the heart rate value of each data point in the heart rate monitoring curve;

[0037] Determining the degree of anesthesia stress of the monitored person in the current period based on the degree of abnormal blood pressure increase and the degree of abnormal heart rate performance;

[0038] Among them, the abnormal increase in blood pressure and the abnormal heart rate performance are both positively correlated with the degree of anesthesia stress.

[0039] Furthermore, the blood pressure data set according to the blood pressure monitoring curve is divided into a first blood pressure data subset and a second blood pressure data subset, including:

[0040] Arranging the blood pressure data set in a preset order to obtain a new blood pressure data set;

[0041] Calculating the difference between every two adjacent blood pressure data in the new blood pressure data set, and using the blood pressure data corresponding to the maximum difference as a segmentation point;

[0042] The new blood pressure data set is divided using the segmentation points to obtain a first blood pressure data subset and a second blood pressure data subset.

[0043] Furthermore, determining the anesthetic efficacy evaluation value of the current period based on the respiratory depressant index and the anesthetic stress level includes:

[0044] performing negative correlation processing on the anesthetic stress degree to obtain a negative correlation value of the anesthetic stress degree;

[0045] The product of the negative correlation value and the respiratory inhibitory index is calculated, the product is normalized to obtain a normalized value, and the normalized value is used as the anesthetic efficacy evaluation value of the current time period.

[0046] Furthermore, after determining the anesthetic efficacy evaluation value of the current period, the method further includes: adjusting the current anesthetic dosage according to the anesthetic efficacy evaluation value of the current period;

[0047] When the anesthetic drug efficacy evaluation value is greater than a first evaluation threshold, determining a product of the anesthetic drug efficacy evaluation value and the current anesthetic drug dose as a reduction amount of the current anesthetic drug dose, and reducing the current anesthetic drug dose by using the reduction amount;

[0048] When the anesthetic efficacy evaluation value is less than a second evaluation threshold, determining a product of a negative correlation value of the anesthetic efficacy evaluation value and a current anesthetic dose as an increase in the current anesthetic dose, and increasing and adjusting the current anesthetic dose by using the increase;

[0049] When the anesthetic drug efficacy evaluation value is greater than or equal to the second evaluation threshold and less than or equal to the first evaluation threshold, maintaining the current anesthetic drug dosage unchanged;

[0050] The first evaluation threshold is greater than the second evaluation threshold.

[0051] Another embodiment of the present invention also provides an anesthetic efficacy evaluation system based on multi-parameter physiological signals, including a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement an anesthetic efficacy evaluation method based on multi-parameter physiological signals.

[0052] The present invention has the following beneficial effects:

[0053] In existing anesthetic efficacy evaluation methods, physiological parameters are mostly analyzed independently and lack effective data fusion strategies. However, the existing multi-dimensional physiological data fusion achieved by machine learning may limit the accuracy and reliability of anesthetic efficacy evaluation results. Therefore, the present invention provides an anesthetic efficacy evaluation method and system based on multi-parameter physiological signals.

[0054] First, physiological parameters corresponding to the core stage of drug efficacy evaluation are obtained. Obtaining physiological parameters in the core stage can provide more reliable data support. Second, the sedation depth of the current period is analyzed through EEG data. The anesthetic efficiency index determined can comprehensively reflect the sedation depth characteristics of multiple aspects and has higher numerical accuracy. Then, the respiratory depression index of the monitored person is determined by combining blood oxygen saturation and respiratory rate with the anesthetic efficiency index. It can reflect the risk of overdose of the current anesthetic dose. The fusion of physiological parameters of different dimensions for analysis and the consideration of the correlation characteristics between physiological parameters of different dimensions significantly improve the numerical accuracy of the respiratory depression index. Then, for the evaluation of anesthetic efficacy, it is necessary to consider not only the situation of anesthetic overdose but also the physical stress caused by insufficient anesthetic. Therefore, it is necessary to combine blood pressure and heart rate to determine the degree of anesthetic stress of the monitored person in the current period. Finally, the respiratory depression index and anesthetic stress degree determined from these two aspects are combined to quantify the anesthetic efficacy evaluation value of the current period. This can effectively overcome the shortcomings of static multi-dimensional physiological parameter fusion analysis and further improve the accuracy of anesthetic efficacy evaluation results. At the same time, it provides reliable data support for anesthesia management, facilitates timely adjustment of anesthesia dosage during surgery, and ensures low-risk requirements during surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 A flowchart of a method for evaluating anesthetic efficacy based on multi-parameter physiological signals provided by one embodiment of the present invention;

[0057] Figure 2 Schematic diagram of EEG signal frequency domain curve;

[0058] Figure 3 This is a schematic diagram of the blood oxygen saturation monitoring curve;

[0059] Figure 4 This is a schematic diagram of the patient's respiratory rate monitoring curve during surgery;

[0060] Figure 5 This is a schematic diagram of the heart rate monitoring curve. DETAILED DESCRIPTION

[0061] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0062] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0063] The application scenarios targeted by the present invention may be:

[0064] The present invention mainly uses anesthesia management during surgery as an application scenario for anesthetic efficacy evaluation. Specifically, in modern operating rooms, anesthesiologists usually need to monitor the patient's vital signs in real time to ensure the effectiveness and safety of anesthetic drugs. The system integrates a variety of sensors, which can monitor physiological parameters of different dimensions in real time, provide comprehensive status information of the patient, evaluate the efficacy of anesthetic drugs, analyze clinical effects, and if the efficacy evaluation is abnormal, the anesthesiologist needs to adjust the drug dosage in time. However, the physiological signals in the existing evaluation methods are mostly analyzed independently, which ignores the physiological correlation between parameters and lacks an effective data fusion strategy, which is not conducive to accurate anesthetic efficacy evaluation.

[0065] In order to more accurately evaluate the anesthetic efficacy, an embodiment of the present invention provides an anesthetic efficacy evaluation method based on multi-parameter physiological signals, such as Figure 1 As shown, the following steps are included:

[0066] S1, obtaining physiological parameters of several dimensions corresponding to the current time period when the monitored person is in the target anesthesia stage.

[0067] Here, the monitored person is a patient who needs anesthesia. The target anesthesia stage is the core stage for evaluating drug efficacy. Physiological parameters include brain waves, blood oxygen saturation, respiratory rate, blood pressure, and heart rate. The current period is the current period in the core stage, such as the current 10 minutes.

[0068] The anesthesia process is typically divided into three phases: induction, maintenance, and recovery. The maintenance phase refers to dynamic adjustments during surgery to stabilize the anesthetic state. Based on existing literature and clinical needs, the anesthesia maintenance phase is a core stage suitable for evaluating drug efficacy based on multi-parameter physiological signals. Of course, practitioners can also collect physiological parameters of different dimensions in real time for anesthetic efficacy assessment, but this is not specifically limited here.

[0069] During the maintenance phase, it is necessary to balance the depth of sedation, analgesia, and physiological stability in real time. The intensity and frequency of surgical stimulation (such as skin incision and organ traction) are constantly changing, and multi-dimensional physiological data must be monitored. For example, multimodal general anesthesia requires simultaneous monitoring of antinociception and unconsciousness levels, and traditional single physiological parameters cannot meet the dynamic needs of surgery. Therefore, it is necessary to collect physiological parameters of several dimensions of the monitored person during the current period of the maintenance phase.

[0070] In this embodiment, appropriate monitoring equipment is selected to ensure that the equipment can monitor the required physiological parameters. For example, ECG electrodes are placed in standard positions on the patient's chest to ensure good contact with the skin. The pulse oximeter probe is placed on the patient's fingertips, earlobes, or toes to ensure that light can penetrate the skin to detect blood oxygen saturation. Respiratory rate can be monitored using a wearable respiratory sensor, or the respiratory monitoring function of the anesthesia machine can be used.

[0071] It should be noted that the monitoring device needs to be checked before it is turned on to ensure that it is working properly and calibrated to improve the numerical accuracy of the collected physiological parameters in different dimensions.

[0072] So far, this embodiment has obtained the physiological parameters of each dimension corresponding to the current time period when the monitored person is in the maintenance period.

[0073] S2, analyzing the sedation depth of the current period based on the data characteristics of the frequency band curves of several waveforms corresponding to the brain waves, and determining the anesthesia efficiency index of the monitored person in the current period.

[0074] Here, the sedation depth of the monitored person has important clinical significance for the evaluation of anesthetic efficacy. Therefore, it is necessary to analyze the sedation depth in the current period to determine the anesthetic efficiency index in order to provide data support for the accurate determination of the subsequent anesthetic efficacy evaluation value.

[0075] As an exemplary embodiment, the above step S2 can be implemented through steps S21 to S23 (not shown):

[0076] S21, performing Fourier transform on the brain waves of the current period, and then extracting the curves of the frequency bands corresponding to several waveforms in the brain wave frequency domain to obtain the frequency band curves of each waveform.

[0077] EEG data is typically displayed as a waveform image, with time typically represented on the horizontal axis and voltage (in millivolts) on the vertical axis. Furthermore, EEG data often includes multiple waveforms, such as alpha, beta, delta, and theta waves.

[0078] In this embodiment, the EEG waves of the current period are converted into the frequency domain through Fourier transform to obtain the EEG frequency domain. Then, different frequency bands are extracted from the EEG frequency domain, such as alpha waves (8-12Hz), beta waves (12-30Hz), delta waves (1-4Hz), and theta waves (4-8Hz). Each waveform can represent a certain physical logic. In this embodiment, only the data characteristics of the frequency band curves of beta waves and theta waves are analyzed.

[0079] Among them, the schematic diagram of the EEG signal frequency domain curve is as follows Figure 2 As shown, in Figure 2 The horizontal axis represents frequency, and the vertical axis represents amplitude. The frequencies of the different waveforms are not randomly set; they are set using an existing method, which is equivalent to the known art. Furthermore, the implementation process of the Fourier transform is prior art and is beyond the scope of this invention, so it will not be elaborated on here.

[0080] S22, determining the sedation depth index of the monitored person in the current time period based on the difference between the previous slope and the next slope in the frequency band curve of the β wave and the correlation between the amplitude data set and the frequency data set of the frequency band curve of the θ wave.

[0081] Under deep anesthesia, the amplitude of beta waves decreases as the depth of sedation increases. Conversely, as the depth of sedation deepens and the anesthetic takes effect, the amplitude of theta waves decreases as the frequency increases. In other words, at higher depths of sedation, the correlation between the amplitude and frequency of theta waves is poor. Therefore, by analyzing the frequency curves of beta and theta waves, we can quantify and determine the depth of sedation of the subject at the current time.

[0082] As an exemplary embodiment, the above step S22 can be implemented through steps 221 to S224 (not shown):

[0083] S221 , in the frequency band curve of the β wave, calculating the slope between two adjacent data points to obtain a slope sequence.

[0084] S222, calculating the difference between the previous slope and the next slope in the slope sequence, and taking the average of all the differences as the degree of trend reduction.

[0085] S223, obtaining the correlation coefficient between the amplitude data set and the frequency data set.

[0086] S224: Determine the sedation depth index of the monitored person in the current time period by combining the correlation coefficient and the trend reduction degree.

[0087] As an example, the above-mentioned sedation depth index can be achieved by the following calculation formula:

[0088] Where, f e represents the sedation depth index of the monitored person in the current period, e represents the current period, H represents the correlation coefficient between the amplitude data set and the frequency data set of the θ wave, n represents the number of slopes in the slope sequence corresponding to the frequency band curve of the β wave, k i represents the i-th slope in the slope sequence, k i+1 represents the i+1th slope in the slope sequence, Indicates the degree of decrease in the trend corresponding to the frequency band curve of the β wave.

[0089] Among them, the correlation coefficient can be the absolute value of the Pearson correlation coefficient. If the correlation coefficient is zero, a non-zero constant, such as 0.01, can be added to the denominator of the fraction to avoid the denominator of the fraction being zero. In addition, the calculation process of the Pearson correlation coefficient is a prior art and is not within the scope of protection of the present invention, and will not be elaborated here.

[0090] S23, obtaining the BIS value of the monitored person in the current period, and determining the anesthesia efficiency index of the monitored person in the current period in combination with the sedation depth index.

[0091] Here, the anesthesia efficiency index refers to the anesthesia level of the monitored person receiving anesthesia treatment in the current period.

[0092] In addition to the frequency band curves of beta and theta waves, which can be used to analyze the depth of sedation, the BIS value of the monitored person during the current period can also be used to characterize the depth of sedation. The lower the BIS value, the deeper the sedation. Therefore, the BIS value is negatively correlated with the anesthesia efficiency index, while the sedation depth determined by the frequency band curves of beta and theta waves is positively correlated with the anesthesia efficiency index. Here, positive correlation means that as the data increases, the corresponding index shows an increasing trend, while negative correlation means that as the data increases, the corresponding index shows a decreasing trend. Therefore, in order to improve the numerical accuracy of the anesthesia efficiency index, the BIS value is also used as one of the key calculation factors for analyzing the depth of sedation and is used to determine the anesthesia efficiency index.

[0093] In this embodiment, the brain activity of the monitored person in the current time period is continuously recorded by the BIS monitoring device, and the BIS value is calculated, and the BIS value of the current time period is recorded as T.

[0094] As an example, the above step S23 can be implemented by the following calculation formula:

[0095] Where, F e It represents the anesthesia efficiency index of the monitored person in the current period, f e It represents the sedation depth index of the monitored person in the current period, and T represents the BIS value of the current period.

[0096] Generally, the BIS value does not reach zero, so this embodiment does not need to consider the special case where the denominator of the fraction is zero. The BIS value is a commonly used index that comprehensively considers information from multiple frequency waveforms and calculates an index value from 0 to 100. Usually, a BIS value between 40 and 60 indicates an appropriate depth of anesthesia, and a lower BIS value indicates deeper sedation.

[0097] Thus, this embodiment obtains the anesthesia efficiency index representing the sedation depth of the monitored person receiving anesthesia treatment in the current period.

[0098] During intraoperative anesthesia management, a higher anesthesia efficiency does not necessarily guarantee that the patient's intraoperative needs are met. Over- or under-anesthesia can impact the actual surgical risk. Furthermore, individual differences in the monitored subjects during anesthesia can lead to errors in the assessment of anesthetic efficacy. Therefore, combining the calculated anesthesia efficiency index with analysis of individual differences in the monitored subject's physiological state leads to the following step S3.

[0099] S3, analyzing the respiratory resistance of the current period according to the monitoring curves of blood oxygen saturation and respiratory rate, and determining the respiratory inhibitory index of the anesthetic effect on the monitored person in the current period in combination with the anesthesia efficiency index of the current period.

[0100] The ideal anesthetic state is for the patient to maintain a sufficient depth of sedation during surgery to avoid pain and discomfort, while also preventing complications caused by over-sedation. Respiratory depression indicators determined through personalized state analysis of the patient can improve the safety of anesthetic medications, reduce adverse reactions, and provide more targeted anesthetic management for patients during surgery.

[0101] As an exemplary embodiment, the above step S3 can be implemented through steps S31 to S33 (not shown):

[0102] S31, analyzing fluctuations in monitoring data based on a monitoring curve of blood oxygen saturation to determine a first respiratory depression factor.

[0103] In this embodiment, the fluctuation variance is calculated based on the blood oxygen saturation monitoring curve. The fluctuation variance can be used to measure the degree of fluctuation of the blood oxygen saturation monitoring curve. The larger the fluctuation variance, the more persistent the fluctuation of blood oxygen saturation during the current period, which in turn indicates that the monitored person has respiratory or circulatory problems. Therefore, the fluctuation variance can be used as the first respiratory depression factor. Of course, implementers can also use other methods to analyze the fluctuation of the monitoring curve, such as calculating the standard deviation.

[0104] Among them, the blood oxygen saturation monitoring curve diagram is as follows Figure 3 As shown, in Figure 3 In the figure, the horizontal axis is time and the vertical axis is blood oxygen saturation; whether calculating the fluctuation variance of the monitoring curve or calculating the fluctuation standard deviation, both are prior arts and are not within the scope of protection of the present invention, and will not be elaborated here.

[0105] S32: Analyze the distribution of respiratory frequency data and abnormal values according to the respiratory frequency monitoring curve to determine a second respiratory inhibition factor.

[0106] The more evenly the respiratory rate data is distributed, the more regular the breathing of the monitored person is. Otherwise, it means that the breathing of the monitored person is not in line with expectations. When the respiratory rate data is significantly lower than the normal range, it indicates that respiratory depression has occurred.

[0107] As an exemplary embodiment, the above step S32 can be implemented through steps S321 to S323 (not shown):

[0108] S321 , evenly divide the monitoring curve of the respiratory frequency into a plurality of local time periods, and calculate the quality heterogeneity index of the respiratory frequency in all local time periods of the current period.

[0109] For the monitoring curve of respiratory rate, wearable respiratory sensors can be used to convert chest and abdominal movements into resistance or capacitance changes, and output analog voltage signals to reflect the respiratory rate characteristics of the current period. Figure 4 As shown, in Figure 4 In the figure, the horizontal axis is time and the vertical axis is pressure value.

[0110] In this embodiment, the quality heterogeneity index can represent the distribution of respiratory frequency data in all local segments. When the quality heterogeneity index is closer to 1, the data points on the monitoring curve representing the respiratory frequency are evenly distributed, that is, the respiratory state of the monitored person is regular; conversely, when the quality heterogeneity index is closer to 0, the data points on the monitoring curve representing the respiratory frequency are non-uniformly distributed, indicating that the respiratory state of the monitored person is not in line with expectations.

[0111] The number of local time periods can be set to 10. The calculation process of the quality heterogeneity index is a prior art and is not within the scope of protection of the present invention, and will not be elaborated here.

[0112] S322, obtaining the lower limit of the normal respiratory frequency range, analyzing the difference between the respiratory frequency value of each data point in the respiratory frequency monitoring curve and the lower limit, and determining the degree of abnormality of the respiratory frequency value in the current period.

[0113] Here, the lower limit of the normal respiratory rate range can be set by the implementer based on historical experience and is not specifically limited here.

[0114] In this embodiment, the difference between the lower limit value and the respiratory rate value for each data point is calculated, and the average of all differences is used as the degree of numerical abnormality. Of course, the ratio of the lower limit value to the respiratory rate value for each data point can also be calculated, and the average of all ratios is used as the degree of numerical abnormality. The method for calculating the degree of numerical abnormality is not specifically limited here.

[0115] S323, determine the second respiratory depression factor by combining the qualitative index and the degree of numerical abnormality.

[0116] Here, the qualitative anomaly index is negatively correlated with the second respiratory depression factor, and the degree of numerical abnormality is positively correlated with the second respiratory depression factor.

[0117] As an example, the second respiratory inhibition factor can be calculated by the following formula:

[0118] Where g represents the second respiratory inhibition factor, IQV represents the quality index, and α′ represents a non-zero constant, such as 00.01, V ′ Represents the lower limit of the normal respiratory rate range, V represents the respiratory rate value of each data point in the respiratory rate monitoring curve, The average of the ratios of the respiratory frequency value to the lower limit value of each data point in the monitoring curve representing the respiratory frequency is recorded as the numerical abnormality degree of the respiratory frequency in the current period.

[0119] For the degree of numerical anomaly, The greater the degree of numerical abnormality, the more significantly the respiratory rate in the current period is lower than the normal range, indicating that the monitored person in the current period has respiratory depression, which may be caused by an overdose of anesthetics.

[0120] S33, combining the first respiratory depression factor, the second respiratory depression factor and the anesthesia efficiency index to determine the respiratory depression index of the monitored person in the current time period due to the anesthetic drug effect.

[0121] Here, the first respiratory depression factor, the second respiratory depression factor, and the anesthetic efficiency index are all positively correlated with the respiratory depression index. The respiratory depression index refers to the degree to which the anesthetic drug causes breathing difficulties in the monitored subject. The higher the respiratory depression index, the greater the risk of an overdose of the current anesthetic drug dose.

[0122] In this embodiment, the first respiratory inhibition factor representing the degree of fluctuation of blood oxygen saturation, the second respiratory inhibition factor representing the distribution and numerical value of respiratory rate, and the anesthesia efficiency index representing the depth of anesthesia can be multiplied together, and the product obtained is used as the respiratory inhibition index of the anesthetic effect on the monitored person in the current time period.

[0123] Of course, under the premise of clarifying the logical relationship between each calculation factor and the calculation result, other data fusion methods can also be used to combine the first respiratory depression factor, the second respiratory depression factor, and the anesthetic efficiency index to quantify and determine the respiratory depression index of the anesthetic effect on the monitored subject during the current period. For example, the first respiratory depression factor, the second respiratory depression factor, and the anesthetic efficiency index can be standardized and then added together.

[0124] As an example, the calculation formula for the respiratory depression index of the monitored person based on the anesthetic effect in the current period can be:

[0125] G e =F e ×g×U; where G e Indicates the respiratory depression index of the monitored person caused by the anesthetic effect during the current period, F e It represents the anesthesia efficiency index of the current period, g represents the second respiratory depression factor, and U represents the first respiratory depression factor.

[0126] As for the anesthesia efficiency index, when the anesthesia efficiency is high, breathing difficulties are likely to occur, which indicates that the anesthetic's efficacy is highly depressive to the respiratory function of the monitored person. When the respiratory function of the monitored person is highly depressive, it is more necessary to adjust the dosage in a timely manner during the anesthesia management stage.

[0127] So far, this embodiment has obtained the respiratory depression index of the anesthetic effect on the monitored person in the current time period.

[0128] During the anesthetic management stage, the higher the respiratory depressant effect of the anesthetic on the monitored person, the more likely it is that an overdose may occur during the actual anesthetic dosage treatment process. However, the anesthetic efficacy of the anesthesia management process cannot be accurately evaluated based solely on changes in respiratory rate. Therefore, this embodiment introduces the following step S4.

[0129] S4, analyzing abnormal changes in blood pressure and heart rate based on the monitoring curves of blood pressure and heart rate to determine the degree of anesthesia stress of the monitored person in the current period.

[0130] During actual surgery, after the anesthetic takes effect, the patient loses the ability to perceive pain, and their physiological signals tend to stabilize. Therefore, if the patient's physiological signals fluctuate or increase abnormally as the surgery progresses, this may indicate pain or stress, and additional anesthesia or adjustment of the anesthesia depth may be necessary.

[0131] As an exemplary embodiment, the above step S4 can be implemented through steps S41 to S45 (not shown):

[0132] S41 , obtaining a first blood pressure data subset and a second blood pressure data subset after division according to the blood pressure data set of the blood pressure monitoring curve.

[0133] As an exemplary embodiment, the above step S41 can be implemented through steps S411 to S413 (not shown):

[0134] S411 , arranging the blood pressure data set according to a preset order to obtain a new blood pressure data set.

[0135] S412: Calculate the difference between every two adjacent blood pressure data in the new blood pressure data set, and use the blood pressure data corresponding to the maximum difference as a segmentation point.

[0136] S413 , dividing the new blood pressure data set using the segmentation point to obtain a first blood pressure data subset and a second blood pressure data subset.

[0137] In this embodiment, in order to organize the blood pressure distribution of the blood pressure data set, the blood pressure data set is sorted. The preset order can be from small to large or from large to small. When sorted in the order of small to large, the first blood pressure data subset consists of the blood pressure data with smaller blood pressure changes corresponding to the left portion of the new blood pressure data set, and the second blood pressure data subset consists of the blood pressure data with larger blood pressure changes corresponding to the right portion of the new blood pressure data set.

[0138] Yet another exemplary embodiment includes:

[0139] The number of blood pressure data sets is counted, and half of the smaller blood pressure data in the blood pressure data set are obtained to form a first blood pressure data subset, and the remaining blood pressure data in the blood pressure data set are used to form a second blood pressure data subset.

[0140] It should be noted that the first blood pressure data subset and the second blood pressure data subset are obtained in order to analyze the overall change trend of the blood pressure data.

[0141] S42: Determine the degree of abnormal blood pressure increase based on the blood pressure difference between the first blood pressure data subset and the second blood pressure data subset.

[0142] In this embodiment, the blood pressure mean of the first blood pressure data subset is calculated, and the blood pressure mean of the second blood pressure data subset is calculated. The degree of abnormal blood pressure increase can be obtained by subtracting the smaller blood pressure mean from the larger blood pressure mean.

[0143] A significant abnormal rise in blood pressure indicates an abnormal increase in blood pressure during the current period, which may indicate that the subject is experiencing pain or stress during surgery. The greater the degree of anesthesia stress, the greater the degree of abnormal rise in blood pressure. Therefore, the degree of abnormal rise in blood pressure is one of the key factors in calculating the degree of anesthesia stress.

[0144] S43, calculating the slope of every two adjacent data points in the heart rate monitoring curve, and selecting the heart rate value corresponding to the maximum slope as the target heart rate value.

[0145] In this embodiment, in the heart rate monitoring curve, two adjacent data points can form a slope value, and the slope value can be positive or negative. A positive slope indicates that the heart rate is on an upward trend, while a negative slope indicates that the heart rate is on a downward trend. Figure 5 As shown, in Figure 5 In the figure, the horizontal axis is time and the vertical axis is heart rate.

[0146] It is worth noting that the maximum slope selected in this embodiment is a positive value.

[0147] S44, determining the degree of abnormality of the heart rate performance based on the difference between the target heart rate value and the heart rate value of each data point in the heart rate monitoring curve.

[0148] As an example, the average value of the difference between the target heart rate value and the heart rate value of each data point in the heart rate monitoring curve is calculated, and the average value of the difference is used as the degree of abnormality of the heart rate performance.

[0149] Of course, the difference between the heart rate values of each data point of the target heart rate value can also be quantified by ratio, which is not specifically limited here.

[0150] The greater the degree of heart rate abnormality, the more significant changes in the patient's heart rate during surgery. This also indicates that the patient may experience pain or stress during surgery, which increases the degree of anesthetic stress. Therefore, the degree of heart rate abnormality is also a key factor in calculating the degree of anesthetic stress.

[0151] S45, combining the degree of abnormal blood pressure increase and the degree of abnormal heart rate performance, determining the degree of anesthesia stress of the monitored person in the current period.

[0152] Among them, the degree of abnormal blood pressure increase and the degree of abnormal heart rate performance are positively correlated with the degree of anesthetic stress.

[0153] As an example, the product of the abnormal blood pressure rise degree and the abnormal heart rate performance degree is used as the anesthetic stress degree of the monitored person in the current period.

[0154] Of course, different aspects of anesthetic stress manifestation factors can also be combined together by adding and summing, that is, the degree of abnormal increase in blood pressure and the degree of abnormal heart rate manifestation, which is not specifically limited here.

[0155] The greater the degree of anesthetic stress, the more stressful the monitored person is, which means that the anesthetic dosage may be insufficient, further increasing the risk during the operation.

[0156] So far, this embodiment has determined the anesthetic stress level of the monitored person in the current period.

[0157] S5, determining the anesthetic efficacy evaluation value of the current period according to the respiratory depression index and the anesthetic stress level.

[0158] Here, the anesthetic efficacy evaluation value refers to the effectiveness of the current anesthetic dose. The anesthetic efficacy evaluation value is not monotonic. When the anesthetic efficacy evaluation value is within a reasonable range, it can be considered that the clinical effect of the anesthetic is good. When the anesthetic efficacy evaluation value is abnormally large, it indicates that there is a risk of overdose of the current anesthetic dose. When the anesthetic efficacy evaluation value is abnormally small, it indicates that there is a risk of underdose of the current anesthetic dose.

[0159] As an exemplary embodiment, the above step S5 can be implemented through steps S51 to S52 (not shown):

[0160] S51, performing negative correlation processing on the anesthesia stress degree to obtain a negative correlation value of the anesthesia stress degree.

[0161] S52, calculating the product of the negative correlation value and the respiratory depressant index, normalizing the product to obtain a normalized value, and using the normalized value as the anesthetic efficacy evaluation value for the current period.

[0162] As an example, the calculation formula for the anesthetic efficacy evaluation value of the current period can be:

[0163] Where p e Indicates the anesthetic efficacy evaluation value of the current period, th represents the normalization function, such as maximum and minimum value normalization, G e Indicates the respiratory depression index of the monitored person caused by the anesthetic effect during the current period, X e Indicates the degree of anesthesia stress of the monitored person in the current period. Indicates a negative correlation value with the degree of anesthetic stress.

[0164] Anesthetic efficacy evaluation value p e If the value is abnormally large, the anesthetic effect has a strong depressive effect on the respiratory function of the monitored person, indicating that the anesthetic dose may be excessive for the monitored person in the current period, and there is no strong anesthetic stress during the monitoring process, so there will be no respiratory arrest or circulatory system instability caused by insufficient anesthetic dose; the anesthetic effect evaluation value p e If the abnormality is small, the anesthetic effect has a weak depressive effect on the respiratory function of the monitored person, indicating that the monitored person may not suffer from an overdose of anesthetics in the current period. However, if strong anesthetic stress symptoms appear during the monitoring process, the monitored person may suffer from insufficient anesthetics, resulting in respiratory arrest, circulatory system instability, etc.

[0165] At this point, based on the characteristics of physiological parameters in different dimensions, data fusion analysis of physiological parameters in different dimensions is performed to obtain a more accurate anesthetic efficacy evaluation value for the current period.

[0166] Abnormally large or small anesthetic efficacy evaluation values are relatively poor for the evaluation results of anesthetic efficacy during surgery. For poor anesthesia management stages, timely adjustments are required, including: adjusting the current anesthetic dosage according to the anesthetic efficacy evaluation value of the current period.

[0167] Furthermore, it specifically includes:

[0168] When the anesthetic efficacy evaluation value is greater than the first evaluation threshold, it indicates that the current anesthetic dose may be at risk of overdose. The product of the anesthetic efficacy evaluation value and the current anesthetic dose can be determined as the reduction amount of the current anesthetic dose, and the current anesthetic dose can be reduced and adjusted using the reduction amount.

[0169] Among them, the greater the degree to which the anesthetic efficacy evaluation value is greater than the first evaluation threshold, the greater the risk of overdose, and the greater the degree of reduction in the current anesthetic dose should be, so the product of the anesthetic efficacy evaluation value and the current anesthetic dose can be taken as the reduction in the current anesthetic dose.

[0170] When the anesthetic efficacy evaluation value is less than the second evaluation threshold, it indicates that the current anesthetic dose may be at risk of being insufficient. The product of the negative correlation value of the anesthetic efficacy evaluation value and the current anesthetic dose is determined as the increase in the current anesthetic dose, and the increase is used to increase and adjust the current anesthetic dose.

[0171] The smaller the degree to which the anesthetic efficacy evaluation value is less than the second evaluation threshold, the greater the risk of insufficiency, and the greater the increase in the current anesthetic dose should be. Therefore, the anesthetic efficacy evaluation value needs to be negatively correlated and then multiplied by the current anesthetic dose to obtain the increase in the current anesthetic dose. Here, the anesthetic efficacy evaluation value ranges from 0 to 1, so the negative correlation value of the anesthetic efficacy evaluation value can be equal to the difference between 1 and the anesthetic efficacy evaluation value.

[0172] When the anesthetic efficacy evaluation value is greater than or equal to the second evaluation threshold and less than or equal to the first evaluation threshold, it indicates that the anesthetic dosage is within the normal range. Keeping the current anesthetic dosage unchanged can ensure that there is no risk of excessive anesthetic dosage during anesthesia management, and will not cause stress reactions in patients during surgery, thereby ensuring the smooth progress of the operation.

[0173] It is worth noting that the anesthetic efficacy evaluation value can be used to assess whether there is a risk of excessive or insufficient anesthetic dosage. The implementer can also adaptively adjust the current anesthetic dosage based on prior knowledge. There is no specific limitation on the adjustment method of the anesthetic dosage.

[0174] The first evaluation threshold is greater than the second evaluation threshold. The first evaluation threshold can be set to 0.7, while the second evaluation threshold can be set to 0.4. The first evaluation threshold and the second evaluation threshold can be set by the implementer based on the monitored person's tolerance to anesthetics. The setting of the evaluation threshold varies depending on the tolerance to anesthetics, and is not specifically limited here.

[0175] At this point, by monitoring the changing behavior of the patient's physiological signals and adopting reasonable adjustment strategies, the safety of the monitored person receiving anesthesia and the effectiveness of anesthesia can be ensured.

[0176] Another embodiment of the present invention provides an anesthetic efficacy evaluation system based on multi-parameter physiological signals, including a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement an anesthetic efficacy evaluation method based on multi-parameter physiological signals as described above.

[0177] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for evaluating anesthetic efficacy based on multi-parameter physiological signals, characterized in that: The following steps are involved: Acquire physiological parameters of several dimensions corresponding to the current time period when the monitored person is in the target anesthesia stage, including brain waves, blood oxygen saturation, respiratory rate, blood pressure, and heart rate. The target anesthesia stage is the core stage for evaluating drug efficacy; Analyzing the sedation depth of the current period based on the data characteristics of the frequency band curves of the plurality of waveforms corresponding to the brain waves, and determining the anesthesia efficiency index of the monitored person in the current period; Analyzing the respiratory resistance of the current period according to the monitoring curves of the blood oxygen saturation and the respiratory rate, and determining the respiratory inhibitory index of the anesthetic effect on the monitored person in the current period in combination with the anesthesia efficiency index of the current period; Analyzing abnormal changes in blood pressure and heart rate according to the monitoring curves of the blood pressure and the heart rate to determine the degree of anesthesia stress of the monitored person in the current period; An anesthetic efficacy evaluation value for the current period is determined according to the respiratory inhibitory index and the anesthetic stress degree.

2. The method for evaluating anesthetic efficacy based on multi-parameter physiological signals according to claim 1, characterized in that: Analyzing the sedation depth of the current period based on the data features of the frequency band curves of the plurality of waveforms corresponding to the brain waves and determining the anesthesia efficiency index of the monitored person in the current period includes: Performing Fourier transform on the brain waves of the current period, and then extracting curves of frequency bands corresponding to several waveforms in the brain wave frequency domain to obtain frequency band curves of each waveform, wherein the waveforms include beta waves and theta waves; Determining the sedation depth index of the monitored person during the current period based on the difference between the previous slope and the next slope in the frequency band curve of the beta wave and the correlation between the amplitude data set and the frequency data set of the frequency band curve of the theta wave; Obtaining the BIS value of the monitored person during the current period, and determining the anesthetic efficiency index of the monitored person during the current period in combination with the sedation depth index; The BIS value is negatively correlated with the anesthesia efficiency index, and the sedation depth is positively correlated with the anesthesia efficiency index.

3. The method for evaluating anesthetic efficacy based on multi-parameter physiological signals according to claim 2, characterized in that: Determining the sedation depth index of the monitored person during the current period includes: In the frequency band curve of the β wave, the slope between two adjacent data points is calculated to obtain the slope sequence; Calculating the difference between the previous slope and the next slope in the slope sequence, and taking the average of all the differences as the degree of trend reduction; Obtaining a correlation coefficient between the amplitude data set and the frequency data set; Determining a sedation depth index of the monitored person during the current period by combining the correlation coefficient and the trend reduction degree; The correlation coefficient is negatively correlated with the sedation depth index, and the trend reduction degree is positively correlated with the sedation depth index.

4. The method for evaluating anesthetic efficacy based on multi-parameter physiological signals according to claim 1, characterized in that: The analyzing the respiratory resistance of the current period according to the monitoring curves of the blood oxygen saturation and the respiratory rate, and determining the respiratory inhibitory index of the anesthetic effect on the monitored person in the current period in combination with the anesthesia efficiency index of the current period, includes: Analyzing fluctuations in monitoring data according to the blood oxygen saturation monitoring curve to determine a first respiratory inhibition factor; Analyzing the distribution and numerical abnormality of respiratory frequency data according to the respiratory frequency monitoring curve to determine a second respiratory inhibition factor; Determining a respiratory depression index of the monitored person during a current period of time by combining the first respiratory depression factor, the second respiratory depression factor, and the anesthesia efficiency index; Among them, the first respiratory inhibition factor, the second respiratory inhibition factor and the anesthesia efficiency index are all positively correlated with the respiratory inhibition index.

5. The method for evaluating anesthetic efficacy based on multi-parameter physiological signals according to claim 4, characterized in that: Determining the second respiratory inhibition factor comprises: Evenly dividing the respiratory frequency monitoring curve into a plurality of local time periods, and calculating the quality heterogeneity index of the respiratory frequency in all local time periods of the current period; Obtaining a lower limit value of a normal respiratory frequency range, analyzing the difference between the respiratory frequency value of each data point in the respiratory frequency monitoring curve and the lower limit value, and determining the degree of numerical abnormality of the respiratory frequency in the current period; Determining a second respiratory depression factor by combining the qualitative index and the degree of numerical abnormality; Among them, the qualitative anomaly index is negatively correlated with the second respiratory inhibition factor, and the numerical abnormality degree is positively correlated with the second respiratory inhibition factor.

6. The method for evaluating anesthetic efficacy based on multi-parameter physiological signals according to claim 1, characterized in that: Analyzing abnormal changes in blood pressure and heart rate based on the monitoring curves of the blood pressure and heart rate to determine the degree of anesthesia stress of the monitored person in the current period includes: Obtaining a first blood pressure data subset and a second blood pressure data subset after division according to the blood pressure data set of the blood pressure monitoring curve; determining a degree of abnormal blood pressure increase based on a blood pressure difference between the first blood pressure data subset and the second blood pressure data subset; By calculating the slope of every two adjacent data points in the heart rate monitoring curve, the heart rate value corresponding to the maximum slope is selected as the target heart rate value; determining the degree of abnormality of the heart rate performance based on the difference between the target heart rate value and the heart rate value of each data point in the heart rate monitoring curve; Determining the degree of anesthesia stress of the monitored person in the current period based on the degree of abnormal blood pressure increase and the degree of abnormal heart rate performance; Among them, the abnormal increase in blood pressure and the abnormal heart rate performance are both positively correlated with the degree of anesthesia stress.

7. The method for evaluating anesthetic efficacy based on multi-parameter physiological signals according to claim 6, characterized in that: The blood pressure data set according to the blood pressure monitoring curve is divided into a first blood pressure data subset and a second blood pressure data subset, including: Arranging the blood pressure data set in a preset order to obtain a new blood pressure data set; Calculating the difference between every two adjacent blood pressure data in the new blood pressure data set, and using the blood pressure data corresponding to the maximum difference as a segmentation point; The new blood pressure data set is divided using the segmentation points to obtain a first blood pressure data subset and a second blood pressure data subset.

8. The method for evaluating anesthetic efficacy based on multi-parameter physiological signals according to claim 1, characterized in that: Determining the anesthetic efficacy evaluation value of the current time period based on the respiratory depressant index and the anesthetic stress level includes: performing negative correlation processing on the anesthetic stress degree to obtain a negative correlation value of the anesthetic stress degree; The product of the negative correlation value and the respiratory inhibitory index is calculated, the product is normalized to obtain a normalized value, and the normalized value is used as the anesthetic efficacy evaluation value of the current time period.

9. The method for evaluating anesthetic efficacy based on multi-parameter physiological signals according to claim 1, characterized in that: After determining the anesthetic drug efficacy evaluation value of the current period, the method further includes: adjusting the current anesthetic drug dosage according to the anesthetic drug efficacy evaluation value of the current period; When the anesthetic drug efficacy evaluation value is greater than a first evaluation threshold, determining a product of the anesthetic drug efficacy evaluation value and the current anesthetic drug dose as a reduction amount of the current anesthetic drug dose, and reducing the current anesthetic drug dose by using the reduction amount; When the anesthetic efficacy evaluation value is less than a second evaluation threshold, determining a product of a negative correlation value of the anesthetic efficacy evaluation value and a current anesthetic dose as an increase in the current anesthetic dose, and increasing and adjusting the current anesthetic dose by using the increase; When the anesthetic drug efficacy evaluation value is greater than or equal to the second evaluation threshold and less than or equal to the first evaluation threshold, maintaining the current anesthetic drug dosage unchanged; The first evaluation threshold is greater than the second evaluation threshold.

10. An anesthetic efficacy evaluation system based on multi-parameter physiological signals, characterized in that: The invention comprises a processor and a memory, wherein the processor is used to process instructions stored in the memory to implement an anesthetic efficacy evaluation method based on multi-parameter physiological signals as described in any one of claims 1 to 9.

Images