Surgical Monitoring Data Analysis System

Abstract

The present invention relates to the field of surgical monitoring, and particularly to a monitoring data analysis system for surgical operations. The system first obtains the inspiratory flow rate and tidal volume at the current moment and each historical moment, analyzes the difference in the inspiratory flow rate between each moment and the previous moments, obtains the inspiratory flow rate difference degree at each moment, clusters all the moments, and obtains the tidal volume difference degree at the current moment according to the difference in tidal volume between the historical moments in the cluster where the current moment is located and the current moment. According to the differences in inspiratory flow rate and tidal volume between the current moment and the historical moments, the difference in the inspiratory flow rate difference degree between the current moment and the historical moments, and the tidal volume difference degree at the current moment, the stability similarity degree at the current moment is obtained. According to the inspiratory flow rate, tidal volume and stability similarity degree at the current moment, the anesthesia state of the patient is evaluated. The present invention can accurately evaluate the anesthesia state of the patient and improve the accuracy of anesthesia monitoring of the patient.

Description

Technical Field

[0001] The present invention relates to the field of surgical monitoring, and particularly to a monitoring data analysis system for surgical operations. Background Art

[0002] A monitoring data analysis system for surgical operations is a system used to monitor and analyze the physiological parameters and disease conditions of patients during surgical operations. Since patients who need to undergo surgical operations usually have relatively serious conditions, anesthesia for patients is an important part of surgical operations. It is necessary to perform surgical operations on patients who are completely under anesthesia to ensure the safety and smooth progress of the operations. Therefore, in surgical operations, the assessment of the anesthesia state of patients is crucial.

[0003] In related technologies, the anesthesia state of patients is usually evaluated by analyzing the changes in physical indicators such as blood pressure, heart rate, respiration, and body temperature of patients. However, during the anesthesia process, the physiological responses of patients are relatively slow, and the changes in physical indicator data are relatively complex, resulting in the inability to accurately evaluate the anesthesia state of patients through existing methods, reducing the accuracy of anesthesia monitoring for patients. Summary of the Invention

[0004] In order to solve the technical problem that the existing methods cannot accurately evaluate the anesthesia state of patients and reduce the accuracy of anesthesia monitoring for patients, the purpose of the present invention is to provide a monitoring data analysis system for surgical operations, and the specific technical solutions adopted are as follows:

[0005] The present invention proposes a monitoring data analysis system for surgical operations, and the system includes:

[0006] A data acquisition module, configured to obtain the inspiratory flow rate and tidal volume of a patient at each moment, take the last moment as the current moment, and take all other moments except the current moment as historical moments;

[0007] A data analysis module, which is used to take any moment as the target moment, and obtain the inspiratory flow rate difference degree of the target moment according to the difference in the inspiratory flow rate between other moments before the target moment and the target moment, and the change in the inspiratory flow rate of other moments before the target moment; cluster all moments according to the difference in the inspiratory flow rate between different moments to obtain multiple clustering clusters; obtain the tidal volume difference degree of the current moment according to the difference in the tidal volume between the historical moments in the clustering cluster where the current moment is located and the current moment; take the nearest preset number of historical moments to the current moment as the reference historical moments of the current moment, and obtain the stability similarity degree of the current moment according to the difference in the inspiratory flow rate and the tidal volume between the current moment and the reference historical moments, the difference in the inspiratory flow rate difference degree between the current moment and the reference historical moments, and the tidal volume difference degree of the current moment;

[0008] An anesthesia analysis module, which is used to obtain the anesthesia possibility of the current moment according to the inspiratory flow rate, the tidal volume and the stability similarity degree of the current moment;

[0009] An anesthesia evaluation module, which is used to evaluate the anesthesia state of the patient based on the anesthesia possibility of the current moment.

[0010] Further, the obtaining of the inspiratory flow rate difference degree of the target moment includes:

[0011] Take all moments before the target moment as the moments to be analyzed of the target moment;

[0012] Obtain the first difference parameter of the target moment according to the difference in the inspiratory flow rate between the target moment and each moment to be analyzed;

[0013] Take the absolute value of the difference in the inspiratory flow rate between each moment and the previous adjacent moment as the flow rate change amount of each moment; obtain the second difference parameter of the target moment according to the difference in the flow rate change amount between the target moment and each moment to be analyzed;

[0014] After comprehensively processing the first difference parameter and the second difference parameter and performing normalization processing, obtain the inspiratory flow rate difference degree of the target moment.

[0015] Further, the obtaining of the first difference parameter of the target moment includes:

[0016] Take the difference in the inspiratory flow rate between each moment to be analyzed and the target moment as the inspiratory flow rate difference value between each moment to be analyzed and the target moment;

[0017] Perform normalization processing on the average value of the inspiratory flow rate difference values between all moments to be analyzed and the target moment as the first difference parameter of the target moment.

[0018] Further, the obtaining of the second difference parameter at the target moment includes:

[0019] Taking the difference between the flow rate change amount at the target moment and that at each moment to be analyzed as the change amount difference value between the target moment and each moment to be analyzed;

[0020] Normalizing the average value of the change amount difference values between the target moment and all moments to be analyzed as the second difference parameter at the target moment.

[0021] Further, the obtaining of multiple clustering clusters includes:

[0022] Taking the absolute value of the difference in the inspiratory flow rate between any two moments as the distance metric between any two moments;

[0023] Using the K-means clustering algorithm and clustering all moments based on the distance metric between any two moments to obtain multiple clustering clusters.

[0024] Further, the obtaining of the tidal volume difference degree at the current moment includes:

[0025] Taking the absolute value of the difference between the tidal volume at the current moment and the tidal volume at each historical moment in the clustering cluster where the current moment is located as the initial tidal volume difference parameter between the current moment and each historical moment in the clustering cluster where the current moment is located;

[0026] Normalizing the average value of the initial tidal volume difference parameters between the current moment and all historical moments in the clustering cluster where the current moment is located to obtain the tidal volume difference degree at the current moment.

[0027] Further, the obtaining of the steady similarity degree at the current moment includes:

[0028] Taking the current moment or any reference historical moment as the moment to be measured, using the inspiratory flow rate at the moment to be measured as the numerator and the tidal volume at the moment to be measured as the denominator, and taking the ratio as the characteristic index at the moment to be measured;

[0029] Taking the absolute value of the difference in the characteristic index between the current moment and each reference historical moment as the first difference coefficient between the current moment and each reference historical moment;

[0030] Obtaining the second difference coefficient between the current moment and each reference historical moment according to the tidal volume difference degree at the current moment and the difference in the inspiratory flow rate difference degree between the current moment and each reference historical moment;

[0031] Obtain the comprehensive difference coefficient between the current moment and each reference historical moment by multiplying the first difference coefficient and the second difference coefficient;

[0032] Perform negative correlation normalization on the accumulated value of the comprehensive difference coefficients between the current moment and all reference historical moments to obtain the stability similarity at the current moment.

[0033] Further, the obtaining of the second difference coefficient between the current moment and each reference historical moment includes:

[0034] Take the absolute value of the difference between the inspiratory flow rate difference degrees between the current moment and each reference historical moment as the flow rate change difference value between the current moment and each reference historical moment;

[0035] Take the product value of the flow rate change difference value and the tidal volume difference degree at the current moment as the second difference coefficient between the current moment and each reference historical moment.

[0036] Further, the obtaining of the anesthesia possibility at the current moment includes:

[0037] Perform negative correlation mapping after comprehensively combining the inspiratory flow rate and the tidal volume at the current moment to obtain the possibility parameter at the current moment;

[0038] Perform normalization after comprehensively combining the stability similarity and the possibility parameter at the current moment to obtain the anesthesia possibility at the current moment.

[0039] Further, the evaluation of the anesthesia state of the patient includes:

[0040] If the anesthesia possibility at the current moment is greater than the preset anesthesia threshold, the patient has completely entered the anesthesia state; otherwise, the patient has not fully entered the anesthesia state.

[0041] The present invention has the following beneficial effects:

[0042] In view of the fact that the existing methods cannot accurately evaluate the anesthetic state of a patient, which reduces the accuracy of anesthetic monitoring for the patient, the present invention first obtains the inspiratory flow rate and tidal volume of the patient at each moment. Considering that when the patient enters the anesthetic state at a certain moment, the inspiratory flow rate at that moment is smaller than that at the previous moments, and as the anesthetic drug gradually diffuses, the change rate of its inspiratory flow rate gradually increases. Therefore, the difference degree of the respiratory flow rate characteristics at the target moment and those at the previous moments can be reflected by the inspiratory flow rate difference degree. Subsequently, based on the difference between the inspiratory flow rate difference degree at the current moment and those at the previous moments, the stability degree of the inspiratory flow rate at the current moment and the previous moments can be analyzed to improve the accuracy of evaluating the anesthetic state of the patient. Considering that when the patient enters the anesthetic state, for the moments with similar inspiratory flow rates, the tidal volumes at these moments are also relatively close, while when the patient does not enter the anesthetic state, the consistency of the tidal volumes at these moments is poor and there are certain differences. Therefore, all moments can be clustered first to obtain multiple clustering clusters, and then the difference degree of the tidal volumes between the current moment and the historical moments with similar inspiratory flow rates can be reflected by the tidal volume difference degree. Subsequently, it can be accurately evaluated whether the patient enters the anesthetic state based on the tidal volume difference degree. Considering that when the patient enters the anesthetic state, both the inspiratory flow rate and the tidal volume of the patient are low, and their change characteristics are relatively similar and stable. Therefore, the similarity of the low-level stable change characteristics between the inspiratory flow rate and the tidal volume can be reflected by the stability similarity within the time period composed of the current moment and each reference historical moment. Furthermore, the possibility that the patient is in the anesthetic state can be accurately reflected by the obtained anesthetic possibility, improving the accuracy of anesthetic evaluation and monitoring for the patient. Description of the Drawings

[0043] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a block diagram of a monitoring data analysis system for surgical operations provided by an embodiment of the present invention;

[0045] Figure 2 It is a flowchart of a method for obtaining the stability similarity at the current moment provided by an embodiment of the present invention. Detailed Embodiments

[0046] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manner, structure, features, and effects of a monitoring data analysis system for surgical operations 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.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0048] The following specifically describes the specific solution of a monitoring data analysis system for surgical operations provided by the present invention in combination with the accompanying drawings.

[0049] Please refer to Figure 1 , which shows a block diagram of a monitoring data analysis system for surgical operations provided by an embodiment of the present invention. The system includes: a data acquisition module 101, a data analysis module 102, an anesthesia analysis module 103, and an anesthesia evaluation module 104.

[0050] The data acquisition module 101 is used to obtain the inspiratory flow rate and tidal volume of the patient at each moment, take the last moment as the current moment, and take all other moments except the current moment as historical moments.

[0051] The monitoring data analysis system for surgical operations is an efficient tool specifically designed for hospital operating rooms. Using this system, physical indicators such as the patient's blood pressure, heart rate, respiration, and body temperature can be analyzed to help medical staff monitor the anesthesia status of surgical patients in real time and effectively improve the safety and accuracy of the surgical process.

[0052] Respiratory indicators are a key indicator for evaluating whether a patient has entered the anesthesia state, including, for example, expiratory flow rate, inspiratory flow rate, expiratory pressure, inspiratory pressure, or tidal volume, etc. In the embodiments of the present invention, these two types of data, namely inspiratory flow rate and tidal volume, are selected for subsequent evaluation and analysis of the patient's anesthesia state. First, use monitoring equipment in the hospital, such as a ventilator, to collect the inspiratory flow rate and tidal volume of the patient at each moment. Among them, the time interval for data acquisition is set to 1 second, that is, data is collected every 1 second. The time interval for data acquisition can also be set by the implementer according to the specific implementation scenario and is not limited herein. Then, take the last moment as the current moment, and take all other moments except the current moment as historical moments. Subsequently, in combination with the inspiratory flow rate and tidal volume at the current moment and historical moments, the anesthesia state of the patient is analyzed in real time.

[0053] The data analysis module 102 is used to take any moment as the target moment, obtain the inspiratory flow rate difference degree of the target moment according to the difference in inspiratory flow rate between other moments before the target moment and the target moment, and the change in inspiratory flow rate of other moments before the target moment; cluster all moments according to the difference in inspiratory flow rate between different moments to obtain multiple clustering clusters; obtain the tidal volume difference degree of the current moment according to the difference in tidal volume between the historical moments in the clustering cluster where the current moment is located and the current moment; take the preset number of historical moments closest to the current moment as the reference historical moments of the current moment, and obtain the stability similarity degree of the current moment according to the difference in inspiratory flow rate and tidal volume between the current moment and the reference historical moments, the difference in the inspiratory flow rate difference degree between the current moment and the reference historical moments, and the tidal volume difference degree of the current moment.

[0054] When a patient undergoes a surgical operation, with the injection of anesthetic drugs, the patient's physiological response slows down, and the patient's body enters a calm dormant period. When the patient enters the anesthetic state at a certain moment, the inspiratory flow rate at that moment is smaller than that at previous moments, and as the anesthetic drug gradually diffuses and takes effect, the change rate of its inspiratory flow rate gradually increases. Therefore, in the embodiments of the present invention, any moment is first analyzed, any moment is taken as the target moment, and the difference in inspiratory flow rate between other moments before the target moment and the target moment, and the change in inspiratory flow rate of other moments before the target moment are analyzed. The obtained inspiratory flow rate difference degree reflects the difference degree between the characteristics of the respiratory flow rate at the target moment and those at previous moments. Subsequently, the stability of the inspiratory flow rate within the time period composed of the current moment and historical moments can be further analyzed based on the difference in the inspiratory flow rate difference degrees between the current moment and each historical moment, improving the accuracy of the assessment of the patient's anesthetic state.

[0055] Preferably, in an embodiment of the present invention, the method for obtaining the inspiratory flow rate difference degree of the target moment specifically includes:

[0056] First, take all moments before the target moment as the moments to be analyzed for the target moment, and obtain the first difference parameter of the target moment according to the difference in inspiratory flow rate between the target moment and each moment to be analyzed. The larger the first difference parameter, the smaller the inspiratory flow rate at the target moment compared to the inspiratory flow rates at previous moments, and thus the greater the possibility that the patient enters the anesthetic state, providing a data basis for calculating the inspiratory flow rate difference degree of the target moment.

[0057] Preferably, in an embodiment of the present invention, the method for obtaining the first difference parameter of the target moment specifically includes:

[0058] The difference between the inspiratory flow rate at each moment to be analyzed and the target moment is used as the inspiratory flow rate difference value between each moment to be analyzed and the target moment. The larger the inspiratory flow rate difference value, the smaller the inspiratory flow rate at the target moment compared to the inspiratory flow rate at each moment to be analyzed. Furthermore, the average value of the inspiratory flow rate difference values between all moments to be analyzed and the target moment can be normalized and used as the first difference parameter of the target moment.

[0059] In one embodiment of the present invention, an existing function can be used to implement the normalization process, and the normalization in subsequent steps can all adopt function to implement the normalization process. In other embodiments of the present invention, other normalization methods can be selected according to the specific numerical range, which will not be elaborated herein.

[0060] As an example, in one embodiment of the present invention, the expression of the first difference parameter of the target moment can be specifically, for example:

[0061]

[0062] Wherein, represents the first difference parameter of the target moment; represents the inspiratory flow rate at the th moment to be analyzed of the target moment; represents the inspiratory flow rate at the target moment; represents the th inspiratory flow rate difference value between the moment to be analyzed and the target moment; represents the number of moments to be analyzed of the target moment; represents the activation function for normalization processing.

[0063] It should be noted that for the existing boundary problem, when the target moment is the first moment, there is no other moment before the first moment. At this time, the first difference parameter of the first moment can be directly set to the numerical value 0 to solve the existing boundary problem.

[0064] Then, the absolute value of the difference between the inspiratory flow rate at each moment and the inspiratory flow rate at the previous adjacent moment is used as the flow rate change amount at each moment, and the degree or speed of the inspiratory flow rate change at each moment is reflected through the flow rate change amount. It should be noted that there is no previous adjacent moment for the first moment. At this time, the flow rate change amount of the first moment can be set to the numerical value 0. Furthermore, according to the difference in the flow rate change amount between the target moment and each moment to be analyzed, the second difference parameter of the target moment is obtained. The larger the second difference parameter, the greater the change speed of the inspiratory flow rate at the target moment compared to the change speed of the inspiratory flow rate at the previous moments, and further indicates that the possibility of the patient entering the anesthesia state is greater, providing a data basis for calculating the inspiratory flow rate difference degree at the target moment.

[0065] Preferably, in an embodiment of the present invention, the method for obtaining the second difference parameter at the target time specifically includes:

[0066] The difference between the flow rate change amount at the target time and each time to be analyzed is used as the change amount difference value between the target time and each time to be analyzed. The larger the change amount difference value, the greater the instantaneous change amount of the inspiratory flow rate at the target time compared to the instantaneous change amount of the inspiratory flow rate at each time to be analyzed. Furthermore, the average value of the change amount difference values between the target time and all times to be analyzed can be normalized and used as the second difference parameter at the target time.

[0067] As an example, in an embodiment of the present invention, the expression of the second difference parameter at the target time can be specifically, for example:

[0068]

[0069] Wherein, represents the second difference parameter at the target time; represents the flow rate change amount at the target time; represents the th flow rate change amount of the time to be analyzed at the target time; represents the change amount difference value between the target time and the th time to be analyzed; represents the number of times to be analyzed at the target time; represents the activation function for normalization processing.

[0070] Finally, the first difference parameter and the second difference parameter are combined and then normalized to obtain the inspiratory flow rate difference degree at the target time.

[0071] In the embodiment of the present invention, the combination of the two can be achieved by calculating the sum value or product value of the first difference parameter and the second difference parameter, which is not limited herein.

[0072] As an example, in an embodiment of the present invention, the expression of the inspiratory flow rate difference degree at the target time can be specifically, for example:

[0073]

[0074] Wherein, represents the inspiratory flow rate difference degree at the target time; represents the first difference parameter at the target time; represents the second difference parameter at the target time; represents the activation function for normalization processing.

[0075] The difference degree of inspiratory flow rate at each moment can be obtained by the same method as described above.

[0076] When the patient enters the anesthetic state, for each moment with similar inspiratory flow rates, the tidal volumes at these moments are also relatively close. When the patient has not entered the anesthetic state, the consistency of the tidal volumes at these moments is poor and there are certain differences. Therefore, first, based on the difference in inspiratory flow rates between different moments, all moments can be clustered to obtain multiple clusters. Subsequently, the difference in tidal volume between each historical moment and the current moment in the cluster where the current moment is located can be analyzed to accurately evaluate the anesthetic state of the patient at the current moment.

[0077] Preferably, in an embodiment of the present invention, the method for obtaining multiple clusters specifically includes:

[0078] The absolute value of the difference in inspiratory flow rate between any two moments is used as the distance metric between any two moments. Then, the K-means clustering algorithm is used, and based on the distance metric between any two moments, all moments are clustered to obtain multiple clusters. Among them, the number of clusters can be determined using the existing elbow method. In other embodiments of the present invention, other clustering algorithms based on distance metrics can also be used for clustering operations, which are not limited herein.

[0079] As can be seen from the above analysis, when the patient has not entered the anesthetic state, there are certain differences in the tidal volumes at each moment with similar inspiratory flow rates. Therefore, the difference in tidal volume between the historical moments and the current moment in the cluster where the current moment is located can be analyzed. The obtained difference degree of tidal volume reflects the degree of difference in tidal volume between the current moment and each historical moment with similar inspiratory flow rates. The greater the difference degree of tidal volume, the greater the difference in tidal volume between the current moment with similar inspiratory flow rates and each historical moment, and the less likely the patient is in the anesthetic state. On the contrary, it indicates that the tidal volume at the current moment with similar inspiratory flow rates is closer to the tidal volumes at each historical moment, and the more likely the patient is in the anesthetic state. Subsequently, based on the difference degree of tidal volume, it can be accurately evaluated whether the patient enters the anesthetic state at the current moment.

[0080] Preferably, in an embodiment of the present invention, the method for obtaining the difference degree of tidal volume at the current moment specifically includes:

[0081] The absolute value of the difference between the tidal volume at the current moment and the tidal volume at each historical moment in the cluster where the current moment is located is used as the initial tidal volume difference parameter between the current moment and each historical moment in the cluster where the current moment is located. The larger the initial tidal volume difference parameter, the greater the tidal volume difference between the current moment and each historical moment with similar inspiratory flow rates. Furthermore, the average value of the initial tidal volume difference parameters between the current moment and all historical moments in the cluster where the current moment is located can be normalized to obtain the tidal volume difference degree at the current moment.

[0082] As an example, in an embodiment of the present invention, the expression of the tidal volume difference degree at the current moment can be specifically, for example:

[0083]

[0084] Wherein, represents the tidal volume difference degree at the current moment; represents the tidal volume at the current moment; represents the th historical moment in the cluster where the current moment is located; represents the number of historical moments in the cluster where the current moment is located; represents the activation function for normalization processing.

[0085] When the patient enters the anesthesia state, the patient's brain consciousness is in a fuzzy state, and the sensitivity of the patient's body decreases. Therefore, both the inspiratory flow rate and tidal volume of the patient are relatively low, and the change characteristics of the inspiratory flow rate and tidal volume are relatively similar and stable. Therefore, in the embodiment of the present invention, first, the preset number of historical moments closest to the current moment are used as the reference historical moments of the current moment, and the differences in inspiratory flow rate and tidal volume between the current moment and the reference historical moments, the differences in inspiratory flow rate difference degrees between the current moment and the reference historical moments, and the tidal volume difference degree at the current moment are analyzed. The obtained stable similarity reflects the similarity of the low-level stable change characteristics between the inspiratory flow rate and tidal volume within the time period composed of the current moment and each reference historical moment. The greater the stable similarity, the more likely the patient is in the anesthesia state at the current moment. Subsequently, based on the stable similarity at the current moment, the possibility of the patient being in the anesthesia state can be accurately calculated and analyzed. Among them, the preset number is set to 5, and the specific value of the preset number can also be set by the implementer according to the specific implementation scenario and is not limited herein.

[0086] Preferably, in an embodiment of the present invention, the method for obtaining the stable similarity at the current moment specifically includes:

[0087] Please refer to Figure 2, which shows a flowchart of a method for obtaining the smooth similarity at the current moment provided by an embodiment of the present invention.

[0088] Step S201: Take the current moment or any reference historical moment as the moment to be measured. Use the inspiratory flow rate at the moment to be measured as the numerator, the tidal volume at the moment to be measured as the denominator, and the ratio as the characteristic index of the moment to be measured. Take the absolute value of the difference between the characteristic indices between the current moment and each reference historical moment as the first difference coefficient between the current moment and each reference historical moment.

[0089] First, analyze the current moment or any reference historical moment. Take the current moment or any reference historical moment as the moment to be measured. Use the inspiratory flow rate at the moment to be measured as the numerator, the tidal volume at the moment to be measured as the denominator, and the ratio as the characteristic index of the moment to be measured. The characteristic index can reflect the proportional characteristics between the inspiratory flow rate and the tidal volume at the moment to be measured. By the same method as above, the characteristic indices of the current moment and each reference historical moment can be obtained. The smaller the difference between the characteristic indices between the current moment and each reference historical moment, the more similar the change trends of the inspiratory flow rate and the tidal volume within the time period composed of the current moment and each reference historical moment. Therefore, take the absolute value of the difference between the characteristic indices between the current moment and each reference historical moment as the first difference coefficient between the current moment and each reference historical moment. The smaller the first difference coefficient, the smaller the difference between the characteristic indices between the current moment and the reference historical moment, providing a data basis for subsequent calculation and analysis of the smooth similarity at the current moment.

[0090] As an example, in an embodiment of the present invention, the expression of the first difference coefficient between the current moment and each reference historical moment can be specifically, for example:

[0091]

[0092] Where represents the first difference coefficient between the current moment and the th reference historical moment; represents the inspiratory flow rate at the current moment; represents the tidal volume at the current moment; represents the characteristic index at the current moment; represents the th reference historical moment's inspiratory flow rate; represents the th reference historical moment's tidal volume; represents the th reference historical moment's characteristic index.

[0093] Step S202: Obtain the second difference coefficient between the current moment and each reference historical moment according to the tidal volume difference degree at the current moment and the difference in the inspiratory flow rate difference degree between the current moment and each reference historical moment, and synthesize the first difference coefficient and the second difference coefficient to obtain the comprehensive difference coefficient between the current moment and each reference historical moment.

[0094] Preferably, in an embodiment of the present invention, the method for obtaining the second difference coefficient between the current moment and each reference historical moment specifically includes:

[0095] Take the absolute value of the difference in the inspiratory flow rate difference degree between the current moment and each reference historical moment as the flow rate change difference value between the current moment and each reference historical moment; take the product value of the flow rate change difference value and the tidal volume difference degree at the current moment as the second difference coefficient between the current moment and each reference historical moment.

[0096] As an example, in an embodiment of the present invention, the expression of the second difference coefficient between the current moment and each reference historical moment can be specifically, for example:

[0097]

[0098] Wherein, represents the second difference coefficient between the current moment and the th reference historical moment; represents the tidal volume difference degree at the current moment; represents the inspiratory flow rate difference degree at the current moment; represents the inspiratory flow rate difference degree of the th reference historical moment; represents the flow rate change difference value between the current moment and the th reference historical moment.

[0099] Wherein, when is relatively large, it indicates that it may be in the initial stage of anesthesia at this time. Although the patient's inspiratory flow rate has changed, the change in the inspiratory flow rate has not reached a stable state. The smaller is, the more stable the change in the patient's inspiratory flow rate is, indicating that the possibility of the patient being fully anesthetized is relatively high at this time, and the tidal volume difference degree

[0100] at the current moment is used to weight it.

[0101] Step S203: Perform negative-correlation normalization on the cumulative value of the comprehensive difference coefficients between the current moment and all reference historical moments to obtain the stability similarity at the current moment.

[0102] As can be seen from the above analysis, the smaller the comprehensive difference coefficient between the current moment and each reference historical moment, the lower and more stable the inspiratory flow rate and tidal volume are during the time period composed of the current moment and each reference historical moment, and the more similar the change trends are. Furthermore, it indicates that the greater the possibility that the patient is in an anesthetic state at the current moment. Therefore, the cumulative value of the comprehensive difference coefficients between the current moment and all reference historical moments can be subjected to negative-correlation normalization to obtain the stability similarity at the current moment.

[0103] In one embodiment of the present invention, a negative-exponential function with the natural constant as the base can be used to implement the negative-correlation normalization.

[0104] As an example, in one embodiment of the present invention, the expression of the stability similarity at the current moment can be specifically, for example:

[0105]

[0106] Among them, represents the stability similarity at the current moment; represents the first difference coefficient between the current moment and the th reference historical moment; represents the second difference coefficient between the current moment and the th reference historical moment; represents the comprehensive difference coefficient between the current moment and the th reference historical moment; represents the number of all reference historical moments; represents the exponential function with the natural constant as the base.

[0107] Thus, the stability similarity at the current moment is obtained.

[0108] The anesthesia analysis module 103 is configured to obtain the anesthesia possibility at the current moment according to the inspiratory flow rate, tidal volume, and stability similarity at the current moment.

[0109] The greater the smooth similarity at the current moment, the greater the likelihood that the patient is in an anesthetic state at the current moment. When the patient is in an anesthetic state, the sensitivity of the patient's body decreases, consciousness becomes blurred, and both the inspiratory flow rate and tidal volume are relatively low. Therefore, the inspiratory flow rate, tidal volume, and smooth similarity at the current moment can be analyzed, and the likelihood of the patient being in an anesthetic state can be accurately reflected through the obtained anesthetic probability, improving the accuracy of subsequent assessment of the patient's anesthetic state.

[0110] Preferably, in an embodiment of the present invention, the method for obtaining the anesthetic probability at the current moment specifically includes:

[0111] The inspiratory flow rate and tidal volume at the current moment are combined and subjected to negative correlation mapping to obtain the probability parameter at the current moment. The larger the probability parameter, the more likely the patient is in an anesthetic state at the current moment. Furthermore, the smooth similarity and probability parameter at the current moment are combined and normalized to obtain the anesthetic probability at the current moment.

[0112] In an embodiment of the present invention, the combination of the inspiratory flow rate and tidal volume at the current moment can be achieved by calculating the sum value or product value of the two, and no limitation is made here.

[0113] In an embodiment of the present invention, the combination of the smooth similarity and probability parameter can be achieved by calculating the sum value or product value of the two, and no limitation is made here.

[0114] As an example, in an embodiment of the present invention, the expression of the anesthetic probability at the current moment can be specifically, for example:

[0115]

[0116] Wherein, represents the anesthetic probability at the current moment; represents the smooth similarity at the current moment; represents the inspiratory flow rate at the current moment; represents the tidal volume at the current moment; represents the probability parameter at the current moment; represents the activation function for normalization processing.

[0117] Thus, the anesthetic probability at the current moment is obtained. Subsequently, based on the anesthetic probability, the anesthetic state of the patient at the current moment can be accurately evaluated, improving the accuracy of the surgical monitoring system.

[0118] The anesthesia evaluation module 104 is used to evaluate the anesthetic state of the patient based on the anesthetic probability at the current moment.

[0119] The greater the anesthetic possibility at the current moment, the more likely the patient is in an anesthetic state at the current moment. Therefore, based on the anesthetic possibility at the current moment, the anesthetic state of the patient can be evaluated.

[0120] Preferably, in an embodiment of the present invention, the method for evaluating the anesthetic state of a patient specifically includes:

[0121] If the anesthetic possibility at the current moment is greater than the preset anesthetic threshold, the patient has completely entered the anesthetic state. At this time, the monitoring system can remind medical staff that the patient has entered the anesthetic state through a warning light or other means. Otherwise, the patient has not completely entered the anesthetic state. At this time, it is necessary to continue to monitor or detect the anesthetic state of the patient. Among them, the preset anesthetic threshold is set to 0.8, and the specific value of the preset anesthetic threshold can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0122] It should be noted that: the above sequence of embodiments of the present invention is only for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying 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.

[0123] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A monitoring data analysis system for surgical operations, characterized in that: The system comprises: A data acquisition module, used for acquiring the inspiratory flow rate and tidal volume of the patient at each moment, taking the last moment as the current moment, and taking all other moments except the current moment as historical moments; A data analysis module, for taking any moment as a target moment, and obtaining the inspiratory flow rate difference degree of the target moment according to the difference between the inspiratory flow rate of other moments before the target moment and the target moment, and the change of the inspiratory flow rate of other moments before the target moment; clustering all moments according to the difference between the inspiratory flow rate of different moments to obtain multiple clustering clusters; obtaining the tidal volume difference degree of the current moment according to the difference between the historical moments in the clustering cluster where the current moment is located and the current moment; taking the preset number of historical moments closest to the current moment as the reference historical moments of the current moment, and obtaining the stationary similarity of the current moment according to the difference between the inspiratory flow rate and the tidal volume between the current moment and the reference historical moment, the difference between the inspiratory flow rate difference degree between the current moment and the reference historical moment, and the tidal volume difference degree of the current moment; an anesthesia analysis module, used to obtain the anesthesia possibility at the current moment according to the inspiratory flow rate, the tidal volume and the stationary similarity at the current moment; an anesthesia assessment module, used to assess the patient's anesthesia state based on the anesthesia possibility at the current moment; The step of obtaining the stable similarity at the current moment includes: The current moment or any reference historical moment is used as the moment to be measured, the inspiratory flow rate at the moment to be measured is used as the numerator, the tidal volume at the moment to be measured is used as the denominator, and the ratio is used as the characteristic index of the moment to be measured; The absolute value of the difference between the characteristic index at the current moment and each reference historical moment is used as the first difference coefficient between the current moment and each reference historical moment; Obtaining a second difference coefficient between the current moment and each reference historical moment according to the tidal volume difference at the current moment and the difference in the inspiratory flow rate difference between the current moment and each reference historical moment; The product of the first difference coefficient and the second difference coefficient is used to obtain a comprehensive difference coefficient between the current moment and each reference historical moment; Perform negative correlation normalization processing on the accumulated value of the comprehensive difference coefficient between the current moment and all reference historical moments to obtain the stable similarity of the current moment; The obtaining of the second difference coefficient between the current moment and each reference historical moment comprises: The absolute value of the difference between the inspiratory flow rate difference between the current moment and each reference historical moment is used as the flow rate change difference between the current moment and each reference historical moment; The product value of the flow rate change difference value and the tidal volume difference at the current moment is used as the second difference coefficient between the current moment and each reference historical moment.

2. A monitoring data analysis system for surgical operations according to claim 1, characterized in that: The obtaining of the inspiratory flow rate difference at the target time comprises: All moments before the target moment are taken as the moments to be analyzed of the target moment; According to the difference of the inspiratory flow rate between the target moment and each moment to be analyzed, obtaining a first difference parameter at the target moment; The absolute value of the difference between the inspiratory flow rate at each moment and the adjacent previous moment is used as the flow rate change at each moment; and the second difference parameter at the target moment is obtained according to the difference between the flow rate change between the target moment and each moment to be analyzed; The first difference parameter and the second difference parameter are integrated and normalized to obtain the inspiratory flow rate difference at the target moment.

3. A monitoring data analysis system for surgical operations according to claim 2, characterized in that: The first difference parameter of the target time is obtained including: The difference between the inspiratory flow rate at each time to be analyzed and the target time is used as the difference value of the inspiratory flow rate between each time to be analyzed and the target time; The average value of the inspiratory flow rate difference between all the time points to be analyzed and the target time point is normalized and used as the first difference parameter at the target time point.

4. A monitoring data analysis system for surgical operations according to claim 2, characterized in that: The second difference parameter of obtaining the target time comprises: The difference between the flow velocity change at the target moment and each time to be analyzed is used as the difference value of the change between the target moment and each time to be analyzed; The average value of the difference in the variation between the target moment and all the moments to be analyzed is normalized to be used as the second difference parameter of the target moment.

5. A monitoring data analysis system for surgical operations according to claim 1, characterized in that: The obtaining of multiple clusters comprises: The absolute value of the difference between the inspiratory flow rates at any two moments is used as the distance measure between the two moments; Using the K-means clustering algorithm, and based on the distance metric between any two moments, all moments are clustered to obtain a plurality of clusters.

6. A monitoring data analysis system for surgical operations according to claim 1, characterized in that: The obtaining of the tidal volume difference at the current moment includes: The absolute value of the difference between the tidal volume at the current moment and the tidal volume at each historical moment in the cluster where the current moment is located is used as the initial tidal volume difference parameter between the current moment and each historical moment in the cluster where the current moment is located; The average value of the initial tidal volume difference parameter between the current moment and all historical moments in the cluster where the current moment is located is normalized to obtain the tidal volume difference degree at the current moment.

7. A monitoring data analysis system for surgical operations according to claim 1, characterized in that: The method of obtaining the anesthesia possibility at the current moment includes: The inspiratory flow rate and the tidal volume at the current moment are integrated and negatively correlated to obtain the possibility parameter at the current moment; The stationary similarity and the possibility parameter at the current moment are integrated and normalized to obtain the anesthesia possibility at the current moment.

8. A monitoring data analysis system for surgical operations according to claim 1, characterized in that: The assessment of the patient's anesthetic status includes: If the anesthesia possibility at the current moment is greater than the preset anesthesia threshold, the patient has completely entered the anesthesia state; otherwise, the patient has not yet completely entered the anesthesia state.

Images