Anesthesia state assessment system and method applicable to patients of different ages

Abstract

The present invention provides an anesthesia state evaluation system and method applicable to patients of different ages. The anesthesia state evaluation system applicable to patients of different ages includes: a signal acquisition module for acquiring electroencephalogram signals of patients of different ages in different states before and after surgery; a signal processing module for processing the electroencephalogram signals and establishing a human consciousness evaluation model based on the processed electroencephalogram signals; and an anesthesia state evaluation module for acquiring the current electroencephalogram signals of the current patient and judging the anesthesia state of the current patient according to the human consciousness evaluation model. The present invention makes the anesthesia state monitoring more objective and scientific, ensures that the evaluation result of the current anesthesia state of the patient can be obtained quickly and efficiently. At the same time, it also reduces the work intensity of anesthesiologists, improves the anesthesia level, reduces the usage amount of anesthetic agents, and lowers the surgical cost.

Description

Technical Field

[0001] The present invention relates to the technical field of neural signal analysis, and particularly relates to an anesthesia state evaluation system and method applicable to patients of different ages. Background Art

[0002] Anesthesia is the use of drugs or other methods to temporarily deprive a patient of sensation throughout the body or locally, so as to achieve the purpose of enabling a surgery to proceed smoothly. A good anesthesia should not only be painless and without subjective consciousness, but more importantly, it should be safe, and can relax the muscles according to the needs of the surgery to facilitate the progress of the surgery. Anesthesia is essential for surgery.

[0003] Traditional anesthesia state evaluation completely relies on the clinical experience of anesthesiologists for judgment, which is greatly affected by subjective consciousness. The work intensity of anesthesiologists is relatively high. At the same time, the dosage and supply speed of anesthetic drugs are also greatly affected by subjective factors, which may cause insufficient anesthesia or overdose of anesthetic drugs, resulting in waste of drugs and increased surgical costs.

[0004] Therefore, it is imperative to develop an anesthesia state evaluation system and method applicable to patients of different ages that is scientific, standardized and can quickly evaluate the current anesthesia state of patients. Summary of the Invention

[0005] The present invention provides an anesthesia state evaluation system and method applicable to patients of different ages. By collecting electroencephalogram (EEG) signals of different patients in different states before and after surgery, a human consciousness evaluation model is established. Using this human consciousness evaluation model, the current anesthesia state of a patient is evaluated based on the current EEG signal of the patient, making the anesthesia state monitoring more objective. At the same time, it also reduces the work intensity of anesthesiologists, improves the anesthesia level, reduces the usage amount of anesthetic agents, and lowers the surgical cost.

[0006] The present invention provides an anesthesia state evaluation system applicable to patients of different ages, including:

[0007] A signal acquisition module, configured to collect EEG signals of different patients in different states before and after surgery;

[0008] A signal processing module, configured to process the EEG signals and establish a human consciousness evaluation model according to the processed EEG signals;

[0009] An anesthesia state evaluation module, configured to collect the current EEG signal of the current patient and judge the anesthesia state of the current patient according to the human consciousness evaluation model.

[0010] Preferably, the different states before and after surgery include the awake state, the anesthesia state, and the recovery state.

[0011] Preferably, the signal acquisition module includes:

[0012] A preparation unit for obtaining the current working state of the electroencephalogram signal acquisition device and initializing the working parameters of the electroencephalogram signal acquisition device according to the current working state;

[0013] A first acquisition unit for controlling the electroencephalogram signal acquisition device to acquire electroencephalogram signals of a target patient;

[0014] A storage unit for storing the electroencephalogram signals of the target patient.

[0015] Preferably, the signal acquisition module further includes:

[0016] A signal verification unit for obtaining a display image of the acquired electroencephalogram signal and judging the validity of the acquired electroencephalogram signal according to the image display rule of the electroencephalogram signal;

[0017] When the display image of the electroencephalogram signal is coherent within the interception time, the electroencephalogram signal is valid, the electroencephalogram signal is stored, and the electroencephalogram signal acquisition of the target patient is completed;

[0018] When the display image of the electroencephalogram signal is not coherent within the interception time, the electroencephalogram signal is invalid, the electroencephalogram signal acquisition device is controlled to continue to acquire the electroencephalogram signal of the target patient, and the inspection is carried out again until an effective electroencephalogram signal is obtained.

[0019] Preferably, the storage unit is further configured to obtain the identity information of the target patient corresponding to the electroencephalogram signal, obtain the age of the target patient according to the identity information, and add a horizontal label to the electroencephalogram signal according to the patient's age;

[0020] Obtain the status information of the target patient corresponding to the electroencephalogram signal, classify the electroencephalogram signal according to the status information, and add a vertical label;

[0021] Based on the horizontal label and the vertical label, store the electroencephalogram signal to the corresponding position according to the preset storage rule.

[0022] Preferably, the signal processing module includes:

[0023] A signal screening unit for obtaining the electroencephalogram signals corresponding to the same target patient according to the storage rule, and obtaining the first target electroencephalogram signal in the first state according to the vertical label of the corresponding electroencephalogram signal;

[0024] Obtain the first average quality of the first target brain signal, and divide the first target electroencephalogram signal according to a preset electroencephalogram wave segmentation method to obtain a plurality of first segmented electroencephalogram signals;

[0025] Respectively obtaining second average qualities of a plurality of first segmented EEG signals, and obtaining a quality error according to the first average quality and the second average quality;

[0026] When the quality error corresponding to the first segmented EEG signal is greater than a preset value, determining that the first segmented EEG signal is a distorted EEG signal, and removing the distorted EEG signal;

[0027] When the quality error corresponding to the first segmented EEG signal is less than or equal to a preset value, determining that the first segmented EEG signal is a usable EEG signal;

[0028] A signal analysis unit, configured to screen out a standard EEG signal based on a third average quality of all available EEG signals, and obtain a first fluctuation amplitude and a standard time domain of the standard EEG signal;

[0029] Obtaining the injection dose of the target patient's anesthetic, and based on the injection dose, estimating the action range of the anesthetic, determining the action center, and obtaining the dynamic changes of the muscle nerves at the action center;

[0030] Acquire the dynamic changes of muscle nerves corresponding to the standard time domain, determine the activity of the muscle nerves in the standard time domain according to the dynamic changes of the muscle nerves, and gain the first fluctuation amplitude based on the muscle nerve activity to obtain a second fluctuation amplitude;

[0031] a feature acquisition unit, configured to select a target time domain from all first segmented EEG signals according to the second fluctuation amplitude, intercept the EEG signal in the target time domain as a feature EEG signal, and acquire a change feature of the feature EEG signal to obtain a first state change feature;

[0032] Based on the signal screening unit and the signal analyzing unit, a second state change characteristic corresponding to the second state and a third state change characteristic corresponding to the third state of the target patient are respectively obtained.

[0033] Preferably, the signal processing module further includes:

[0034] a data screening unit, used to respectively obtain first state change characteristics of different target patients, classify the first state change characteristics according to the horizontal labels, and obtain a first data set, a second data set, and a third data set;

[0035] Obtaining the overall change characteristics of each data set, dividing multiple sub-data sets according to age characteristics, and obtaining subset change characteristics of the multiple sub-data sets respectively;

[0036] Based on the similarity between the subset change characteristics and the overall change characteristics, obtain the feature influence weight of the corresponding sub-dataset on the corresponding dataset, and screen out the optimal sub-dataset according to the feature influence weight;

[0037] Based on the data screening unit, respectively obtain the optimal sub-datasets corresponding to the second state change characteristic and the third state change characteristic;

[0038] A rule acquisition unit is used to obtain the original electroencephalogram signals of different target patients, determine the state demarcation time domain of the original electroencephalogram signals, and intercept the regional electroencephalogram signals in the state demarcation time domain, and there are at least two demarcation time domains;

[0039] According to the first state change characteristic, the second state change characteristic and the third state change characteristic, divide the regional electroencephalogram signals. If the regional electroencephalogram signals cannot be divided into two stages, determine that the state demarcation time domain is a false time domain;

[0040] If the regional electroencephalogram signals can be divided into two stages, determine that the state demarcation time domain is a true time domain, and the junction of the two stages is the state critical point;

[0041] Obtain the anesthetic injection information corresponding to the critical point and the physical examination information of the corresponding target patient, compare the differences of the critical points between different target patients to obtain the anesthesia influence index, and establish a critical point judgment rule according to the anesthesia influence index;

[0042] A model establishment unit is used to establish a primary human consciousness evaluation model by using the critical point judgment rule, and divide the electroencephalogram signal data corresponding to the optimal data subset into a training set and a test set;

[0043] Use the test set to train the primary human consciousness evaluation model. At the same time, use the test set to test the trained human consciousness evaluation model. When the test result corresponds to the anesthesia state and the actual anesthesia state are consistent, determine that the trained human consciousness evaluation model is the final human consciousness evaluation model.

[0044] Preferably, the anesthesia state evaluation module further includes:

[0045] A first acquisition unit is used to acquire the current electroencephalogram signal of the current patient and filter the current electroencephalogram signal to obtain the current effective electroencephalogram signal;

[0046] An evaluation unit is used to evaluate the current effective electroencephalogram signal by using the human consciousness evaluation model, determine the current state of the current patient, and judge whether the current state is normal according to the surgical progress state;

[0047] An alarm unit, configured to determine that the current state is abnormal and issue an alarm notification when the current state of the current patient does not match the surgical progress state.

[0048] Preferably, the alarm unit is further configured to determine whether the surgery is in progress when the current state of the current patient does not match the surgical progress state;

[0049] If the surgery is in progress, obtain the consciousness index of the current patient, and correct the current consciousness index according to the influence coefficient of the current patient's physical condition on the reduction speed of the anesthetic to obtain a target consciousness index;

[0050] Use the dynamic consciousness index of the current patient during the surgery to determine the target harm index of the anesthetic to the current patient;

[0051] Determine whether the target consciousness index and harm index are higher than the highest consciousness index and harm index during the surgery;

[0052] If they are higher than the highest consciousness index and harm index during the surgery, issue an emergency alarm notification based on the alarm unit;

[0053] Otherwise, issue a general alarm notification based on the alarm unit.

[0054] The present invention provides an anesthesia state evaluation method applicable to patients of different ages, including:

[0055] Step 1: Collect electroencephalogram signals of patients of different ages in different states before and after surgery;

[0056] Step 2: Process the electroencephalogram signals and establish a human consciousness evaluation model according to the processed electroencephalogram signals;

[0057] Step 3: Used to collect the current electroencephalogram signal of the current patient, and judge the anesthesia state of the current patient according to the human consciousness evaluation model.

[0058] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification, claims, and drawings.

[0059] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0060] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0061] Figure 1 Schematic diagram of an anesthesia state evaluation system applicable to patients of different ages in an embodiment of the present invention;

[0062] Figure 2 Schematic diagram of a signal acquisition module of an anesthesia state evaluation system applicable to patients of different ages in an embodiment of the present invention;

[0063] Figure 3 Schematic diagram of a signal processing module of an anesthesia state evaluation system applicable to patients of different ages in an embodiment of the present invention;

[0064] Figure 4 Schematic diagram of an anesthesia state evaluation module of an anesthesia state evaluation system applicable to patients of different ages in an embodiment of the present invention;

[0065] Figure 5 Schematic diagram of an anesthesia state evaluation method applicable to patients of different ages in an embodiment of the present invention. Detailed implementation manners

[0066] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for explaining and illustrating the present invention, and are not used to limit the present invention.

[0067] Embodiment 1:

[0068] The present invention provides an anesthesia state evaluation system applicable to patients of different ages, as Figure 1 shown, including:

[0069] A signal acquisition module, configured to acquire electroencephalogram signals of different patients in different states before and after surgery;

[0070] A signal processing module, configured to process the electroencephalogram signals and establish a human consciousness evaluation model based on the processed electroencephalogram signals;

[0071] An anesthesia state evaluation module, configured to acquire the current electroencephalogram signals of the current patient and determine the anesthesia state of the current patient according to the human consciousness evaluation model.

[0072] In this embodiment, different patients refer to child patients (3 - 13 years old), adult patients: (14 - 60 years old), and elderly patients (61 - 80 years old).

[0073] Advantages of this embodiment: The present invention collects EEG signals of different patients in different states before and after surgery to establish a human consciousness evaluation model, and uses this human consciousness evaluation model to evaluate the current anesthesia state of a patient based on the patient's current EEG signals, making the anesthesia state monitoring more objective. At the same time, it also reduces the work intensity of anesthesiologists, improves the anesthesia level, reduces the usage of anesthetic agents, and lowers the surgical cost.

[0074] Embodiment 2:

[0075] Based on Embodiment 1, the different states before and after surgery include the awake state, the anesthesia state, and the recovery state.

[0076] Advantages of this embodiment: The present invention collects data of different patients in different states, making the establishment of the human consciousness evaluation model more objective and comprehensive. At the same time, it also increases the reliability of this anesthesia state evaluation system.

[0077] Embodiment 3:

[0078] Based on Embodiment 1, the signal acquisition module, as Figure 2 shown, includes:

[0079] A preparation unit, configured to obtain the current working state of the EEG signal acquisition device, and perform initialization processing on the working parameters of the EEG signal acquisition device according to the current working state;

[0080] A first acquisition unit, configured to control the EEG signal acquisition device to acquire EEG signals of a target patient;

[0081] A storage unit, configured to store the EEG signals of the target patient.

[0082] In this embodiment, the current working state refers to whether the EEG signal acquisition device (for example, an EEG signal sensor) is currently acquiring EEG signals of other patients.

[0083] In this embodiment, the initialization processing refers to when the EEG acquisition device is acquiring EEG signals of other patients and receives a new EEG signal acquisition, the EEG signal acquisition of the EEG signal acquisition device is restored to the signal zero position.

[0084] In this embodiment, the target patient refers to the patient used to acquire EEG signals to establish a human consciousness evaluation model, and the data (EEG signals, anesthesia injection information, etc.) corresponding to the target patient are all historical data.

[0085] Advantages of this embodiment: Before collecting the EEG signals of the target patient, the present invention initializes the EEG signal acquisition device, avoiding the confusion of EEG signals among different target patients caused by inappropriate time collection, and ensuring the accuracy and uniqueness of EEG signal collection.

[0086] Embodiment 4:

[0087] Based on Embodiment 3, the signal acquisition module further includes:

[0088] A signal verification unit, configured to obtain the display image of the collected EEG signal, and judge the validity of the collected EEG signal according to the image display rule of the EEG signal;

[0089] When the display image of the EEG signal is coherent within the intercepted time, the EEG signal is valid, the EEG signal is stored, and the EEG signal acquisition of the target patient is completed;

[0090] When the display image of the EEG signal is not coherent within the intercepted time, the EEG signal is invalid, and the EEG signal acquisition device is controlled to continue collecting the EEG signal of the target patient and perform verification again until a valid EEG signal is obtained.

[0091] In this embodiment, validity refers to the continuity of the EEG signals of the same patient collected during EEG signal acquisition.

[0092] In this embodiment, a valid EEG signal means that the EEG signal collected within the intercepted time is continuous; wherein, the intercepted time refers to a period of time intercepted from all the collected EEG signals for self-check, and this period of time includes three states of the target patient, namely the awake state, the anesthesia state, and the recovery state.

[0093] Advantages of this embodiment: Before storing the EEG signals of the target patient, the present invention verifies the validity of the collected EEG signals, ensuring the integrity of the collected EEG signals and providing a more effective basis for evaluating the anesthesia state of the target patient.

[0094] Embodiment 5:

[0095] Based on Embodiment 3, the storage unit is further configured to obtain the identity information of the target patient corresponding to the EEG signal, obtain the age of the target patient according to the identity information, and add a horizontal label to the EEG signal according to the patient's age;

[0096] Obtain the state information of the target patient corresponding to the EEG signal, classify the EEG signal according to the state information, and add a vertical label;

[0097] Based on the horizontal label and the vertical label, the EEG signal is stored in a corresponding position according to a preset storage rule.

[0098] In this embodiment, the identity information includes the target patient's age, height, blood type, medical history, and other information.

[0099] In this embodiment, the horizontal label refers to the label related to the age of the target patient, and the purpose is to distinguish the age groups of the target patients; the vertical label refers to the label related to the state of the target patient during the EEG acquisition (awake, anesthetized, recovered), and the purpose is to determine the patient state of the target patient at each stage of the EEG signal.

[0100] In this embodiment, the status information refers to whether the target patient has been injected with anesthesia and whether the operation has started or ended.

[0101] Beneficial effects of this embodiment: When storing the EEG signals of the target patient, the present invention adds horizontal labels and vertical labels to the corresponding EEG signals respectively, thereby ensuring the neatness of the data storage and, at the same time, ensuring the efficient and rapid extraction of the corresponding data when the data is called.

[0102] Embodiment 6:

[0103] Based on Example 1, the signal processing module is as follows: Figure 3 As shown, including:

[0104] A signal screening unit, configured to obtain, according to the storage rule, corresponding EEG signals of the same target patient, and obtain, according to the longitudinal labels of the corresponding EEG signals, a first target EEG signal in a first state;

[0105] Acquire a first average quality of the first target brain signal, and segment the first target EEG signal according to a preset EEG segmentation method to obtain a plurality of first segmented EEG signals;

[0106] Respectively obtaining second average qualities of a plurality of first segmented EEG signals, and obtaining a quality error according to the first average quality and the second average quality;

[0107] When the quality error corresponding to the first segmented EEG signal is greater than a preset value, determining that the first segmented EEG signal is a distorted EEG signal, and removing the distorted EEG signal;

[0108] When the quality error corresponding to the first segmented EEG signal is less than or equal to a preset value, determining that the first segmented EEG signal is a usable EEG signal;

[0109] A signal analysis unit, configured to screen out a standard EEG signal based on a third average quality of all available EEG signals, and obtain a first fluctuation amplitude and a standard time domain of the standard EEG signal;

[0110] Obtain the anesthetic injection dose of the target patient, and based on the injection dose, infer the action range of the anesthetic and determine the center of action, and obtain the dynamic changes of the muscle nerves at the center of action;

[0111] Obtain the dynamic changes of the muscle nerves corresponding to the standard time domain, and based on the dynamic changes of the muscle nerves, determine the muscle nerve activity level of the standard time domain, and perform gain on the first fluctuation amplitude based on the muscle nerve activity level to obtain the second fluctuation amplitude;

[0112] A feature acquisition unit, configured to screen out a target time domain from all the first segmented EEG signals according to the second fluctuation amplitude, intercept the EEG signals of the target time domain as feature EEG signals, and obtain the change features of the feature EEG signals to obtain the first state change features;

[0113] Based on the signal screening unit and the signal analysis unit, respectively obtain the second state change features corresponding to the second state of the target patient and the third state change features corresponding to the third state.

[0114] In this embodiment, the storage rule refers to the pre-set rule of storing data to a specified location according to your data tags.

[0115] In this embodiment, the first state refers to the patient being in a waking state; the second state refers to the patient being in an anesthetized state; the third state refers to the patient being in an anesthetic recovery state.

[0116] In this embodiment, the first target EEG signal refers to the EEG signal of the target patient in the first state (waking state).

[0117] In this embodiment, the first average quality refers to the average quality situation determined according to the fluctuation stability, continuity, and integrity of the first target EEG wave.

[0118] In this embodiment, the first segmented EEG signal refers to the EEG signal obtained by segmenting the first target EEG signal according to a pre-set EEG wave segmentation method. Among them, the pre-set EEG wave signal segmentation method can have a data overlap rate of 70% between the current segmented EEG signal and the previous segmented EEG signal.

[0119] In this embodiment, the second average quality refers to the quality situation determined according to the fluctuation stability, continuity, and integrity of the segmented EEG signal itself.

[0120] In this embodiment, the quality error refers to the difference between the second average quality and the first average quality.

[0121] In this embodiment, the distorted EEG signal refers to the first segmented EEG signal that needs to be excluded because the difference between the second average quality corresponding to the first segmented EEG signal and the first average quality is too large; the available EEG signal refers to the first segmented EEG signal that is retained because the difference between the second average quality corresponding to the first segmented EEG signal and the first average quality is small.

[0122] In this embodiment, the third average quality refers to the average value of the second average qualities corresponding to all available EEG signals.

[0123] In this embodiment, the standard EEG signal refers to the first segmented EEG signal in which the second average quality corresponding to the available EEG signal is closest to the third average quality.

[0124] In this embodiment, the standard time domain refers to the time period corresponding to the standard EEG signal.

[0125] In this embodiment, the action center refers to the range outlined by drawing a circle with a certain radius centered on the center point of the anesthetic action range.

[0126] In this embodiment, the muscle nerve activity level is a parameter used to measure the muscle nerve movement condition of the anesthetic action center within the standard time domain, and this parameter is based on the muscle nerve state when the patient is awake.

[0127] In this embodiment, the first fluctuation amplitude refers to the fluctuation amplitude of the EEG signal of the target patient in the current state determined based on the fluctuations of all available EEG signals on the basis of the standard EEG signal; the second fluctuation amplitude refers to the fluctuation amplitude of the EEG signal of the target patient in the current state obtained by expanding the first fluctuation amplitude according to the influence of the type and dosage of the injection agent on the muscle nerve activity level, which in turn affects the EEG signal.

[0128] In this embodiment, the target time domain refers to the time corresponding to the EEG signals that meet the requirements selected from all the first segmented EEG signals according to the second fluctuation amplitude.

[0129] In this embodiment, the characteristic EEG signal refers to the EEG signal corresponding to the target time domain.

[0130] In this embodiment, the first state change characteristic refers to the EEG signal change characteristic of the target patient in the first state; the second state change characteristic refers to the EEG signal change characteristic of the target patient in the second state; the third state change characteristic refers to the EEG signal change characteristic of the target patient in the third state.

[0131] Advantages of this embodiment: The present invention processes the electroencephalogram signals of the target patients collected, obtains the electroencephalogram signal change characteristics of the same target patient in different states, which is beneficial to the judgment of the state critical point; at the same time, it is also beneficial to the monitoring of the surgical awareness state of the target patient, and quickly judges the anesthesia state of the target patient according to the state change characteristics.

[0132] Embodiment 7:

[0133] Based on Embodiment 1, the signal processing module, as Figure 3 shown, further includes:

[0134] A data screening unit, configured to respectively obtain the first state change characteristics of different target patients, classify the first state change characteristics according to horizontal labels, and respectively obtain a first data set, a second data set, and a third data set;

[0135] Obtain the overall change characteristics of each data set, divide them into multiple sub-data sets according to age characteristics, and respectively obtain the subset change characteristics of the multiple sub-data sets;

[0136] Based on the similarity between the subset change characteristics and the overall change characteristics, obtain the characteristic influence weight of the corresponding sub-data set on the corresponding data set, and screen out the optimal sub-data set according to the characteristic influence weight;

[0137] Based on the data screening unit, respectively obtain the optimal sub-data sets corresponding to the second state change characteristics and the third state change characteristics;

[0138] A rule acquisition unit, configured to obtain the original electroencephalogram signals of different target patients, determine the state boundary time domain of the original electroencephalogram signals, intercept the regional electroencephalogram signals in the state boundary time domain, and there are at least two of the boundary time domains;

[0139] According to the first state change characteristic, the second state change characteristic, and the third state change characteristic, divide the regional electroencephalogram signals. If the regional electroencephalogram signals cannot be divided into two stages, determine that the state boundary time domain is a false time domain;

[0140] If the regional electroencephalogram signals can be divided into two stages, determine that the state boundary time domain is a true time domain, and the junction of the two stages is the state critical point;

[0141] Obtain the anesthetic injection information corresponding to the critical point and the physical examination information of the corresponding target patient, compare the differences in the critical points between different target patients, obtain the anesthesia influence index, and establish a critical point judgment rule according to the anesthesia influence index;

[0142] A model establishment unit is configured to establish a primary human consciousness evaluation model by using the critical point determination rule, and divide the EEG signal data corresponding to the optimal data subset into a training set and a test set.

[0143] Use the test set to train the primary human consciousness evaluation model. Meanwhile, use the test set to test the trained human consciousness evaluation model. When the tested result corresponding anesthesia state is consistent with the actual anesthesia state, determine the trained human consciousness evaluation model as the final human consciousness evaluation model.

[0144] In this embodiment, the first data set refers to the first state change feature data set when the target patient is a child; the second data set refers to the first state change feature data set when the target patient is an adult; the third data set refers to the first state change feature data set when the target patient is an elderly person.

[0145] In this embodiment, the overall change situation of all EEG signals in the overall change feature data set, the data set includes the first data set, the second data set, and the third data set; the subset change feature refers to dividing the data set into multiple sub - data sets according to age, and the change situation of the EEG signals in the sub - data set.

[0146] In this embodiment, the similarity is used to measure the similarity degree between the change feature of the data set and the change feature of the sub - data set.

[0147] In this embodiment, the feature influence weight refers to the influence degree of the sub - data set on the overall feature of the corresponding data set. The higher the similarity, the higher the feature influence weight.

[0148] In this embodiment, the best sub - data set refers to the sub - data set whose similarity with the corresponding data set reaches a certain value (such as 90%).

[0149] In this embodiment, the original EEG signal is the effective EEG signal without any processing.

[0150] In this embodiment, the state boundary time domain refers to the time corresponding to the region where the original EEG signal fluctuates greatly.

[0151] In this embodiment, the regional EEG signal refers to the EEG signal corresponding to the state boundary time domain.

[0152] In this embodiment, the false time domain refers to the state boundary time domain where the regional EEG signal cannot be divided into two stages according to the state change feature, where the state change feature includes the first state change feature, the second state change feature, and the third state change feature; the true time domain refers to the state boundary time domain where the regional EEG signal can be divided into two stages according to the state change feature, and the junction of the two stages is the critical point.

[0153] In this embodiment, the anesthesia injection information includes the type and dosage of anesthetic agents injected into the target patient.

[0154] In this embodiment, the physical constitution information refers to the absorption of anesthetic drugs by the target patient and the harm of anesthetic drugs to the target patient.

[0155] In this embodiment, the anesthesia effect index is used to measure the degree of influence of the dosage and type of injected anesthetic agents and the physical constitution of the target patient on the effect of anesthetic drugs.

[0156] In this embodiment, the critical point judgment rule refers to the judgment rules for different state critical points.

[0157] Beneficial effects of this embodiment: The present invention uses the EEG signals of different target patients to determine the judgment rules for critical points, providing a basis for the establishment of a human consciousness evaluation model; at the same time, establishing a human consciousness evaluation model can more standardly and normatively evaluate the current anesthesia state of patients.

[0158] Embodiment 8:

[0159] Based on Embodiment 1, the anesthesia state evaluation module, as Figure 4 shown, further includes:

[0160] A first acquisition unit, configured to acquire the current EEG signal of the current patient and filter the current EEG signal to obtain a current effective EEG signal;

[0161] An evaluation unit, configured to use the human consciousness evaluation model to evaluate the current effective EEG signal, determine the current state of the current patient, and judge whether the current state is normal according to the surgical progress state;

[0162] An alarm unit, configured to determine that the current state is abnormal and issue an alarm notification when the current state of the current patient does not match the surgical progress state.

[0163] In this embodiment, the current effective EEG signal refers to the EEG signal collected from the current patient after filtering out the noise signals in the EEG signal.

[0164] In this embodiment, the current state refers to any one of the awake state, anesthesia state, and recovery state of the current patient.

[0165] In this embodiment, the surgical progress includes before surgery, during surgery, and after surgery.

[0166] In this embodiment, the current status being normal means that the current status matches the progress of the surgery. For example, when the current patient is in the middle of a surgery, the current status should be the anesthetic state; the current status being abnormal means that the current status does not match the progress of the surgery. For example, when the current patient is in the middle of a surgery, the current status is in the recovery state.

[0167] In this embodiment, the current patient refers to the patient who needs to have their anesthetic state evaluated.

[0168] The beneficial effects of this embodiment: By using the human consciousness evaluation model to evaluate the anesthetic state of the current patient, it is beneficial to more objectively monitor the patient's anesthetic state. At the same time, it avoids mistakes in artificial judgment of the anesthetic state, making the monitoring of the anesthetic state more standardized and regularized.

[0169] Embodiment 9:

[0170] Based on Embodiment 8, the alarm unit is further configured to, when the current status of the current patient does not match the surgical progress status, determine whether the surgery is in progress;

[0171] If the surgery is in progress, obtain the current consciousness index of the current patient, and correct the current consciousness index according to the influence coefficient of the current patient's physique on the reduction speed of the anesthetic agent to obtain the target consciousness index;

[0172] The calculation of the target consciousness index of the current patient is as follows:

[0173] Obtain the historical surgical anesthetic agent usage dose of the current patient and the optimal anesthetic agent usage dose for the current surgery, and use the following formula to calculate the evaluation error of the consciousness index of the current patient:

[0174]

[0175] where ε represents the evaluation error of the consciousness index of the current patient; M 最佳 represents the optimal anesthetic agent usage dose for the entire process of the current patient's surgery; K represents the current local area to which the optimal anesthetic agent usage dose acts on the current patient; τ represents the current correlation value of the body part where the current local area acts on the current patient to the consciousness index; q represents the influence value of the current patient's historical disease on the body function, taking values in (0, 1); p represents the influence value of the current patient's current disease on the body function, taking values in (0, 1); represents the influence value of all the diseases of the current patient on the body function; M i represents the anesthetic agent usage dose for the entire process of the current patient's i-th historical surgery; n represents the number of historical surgeries of the current patient; K i represents the historical local area to which the corresponding anesthetic agent usage dose acts on the corresponding patient during the entire process of the i-th historical surgery; τi It represents the historical correlation value of the body part corresponding to the historical local area acting on the corresponding patient during the entire process of the i-th historical surgery with respect to the consciousness index, and the value range is (0, 1);

[0176] Calculate the target consciousness index of the current patient according to the consciousness index evaluation error of the current patient and the following formula:

[0177]

[0178] Where γ represents the target consciousness index of the current patient; It represents the influence coefficient of the constitution of the current patient on the reduction speed of the anesthetic, taking the value in [0.1, 1); γ0 represents the value of the degree of consciousness wakefulness reflected by the current electroencephalogram signal of the current patient, taking the value in [0, 1], 1 represents complete consciousness wakefulness, and 0 represents unconscious sleep;

[0179] Determine the target harm index of the anesthetic for the current patient by using the dynamic consciousness index of the current patient during the operation;

[0180] Judge whether the target consciousness index and the target harm index are higher than the highest consciousness index and harm index during the operation;

[0181] If it is higher than the highest consciousness index and harm index during the operation, send an emergency alarm notification based on the alarm unit;

[0182] Otherwise, send a general alarm notification based on the alarm unit.

[0183] In this embodiment, the current consciousness index and harm index refer to the values for judging the degree of patient wakefulness obtained based on the patient's electroencephalogram signal according to a mathematical model; the target consciousness index and target harm index are the consciousness index and harm index of the current patient obtained by correcting the current consciousness index and harm index according to the influence coefficient of the constitution of the current patient on the reduction speed of the anesthetic; the highest consciousness index and harm index during the operation refer to the maximum values that the consciousness index and harm index of the patient can reach during the operation, which are determined according to the patient's own constitution.

[0184] Assume that the consciousness index evaluation error of the current patient is 0.1, the influence coefficient of the constitution of the current patient on the reduction speed of the anesthetic is 0.3, the influence value of the historical disease on the body function is 0.3, the influence value of the historical disease of the current patient on the body function is 0.2, and the current consciousness index is 0.6. It is calculated that the target consciousness index of the current patient is 0.51.

[0185] In this embodiment, an emergency alarm refers to the alarm issued by the alarm unit when the patient's consciousness index is too high during the operation, that is, when the anesthetic fails; a general alarm refers to the alarm issued by the alarm unit when the current state of the patient does not match the progress of the operation but the patient is not in the middle of the operation.

[0186] Advantages of this embodiment; The present invention issues an alarm notification when the current state of the patient does not match the progress of the operation, which is beneficial to timely detecting problems with surgical anesthesia and also beneficial to observing the recovery of the patient's surgical consciousness; when the current state of the patient does not match the progress of the operation but the patient is not in the middle of the operation, an emergency alarm is issued, which is beneficial to timely supplement of anesthetic drugs during the operation. At the same time, intraoperative awareness is also prevented, and doctor-patient disputes are reduced.

[0187] Embodiment 10:

[0188] The present invention provides an anesthesia state evaluation method applicable to patients of different ages, such as Figure 5 shown, including:

[0189] Step 1: Collect electroencephalogram (EEG) signals of patients of different ages in different states before and after the operation;

[0190] Step 2: Process the EEG signals and establish a human consciousness evaluation model based on the processed EEG signals;

[0191] Step 3: Used to collect the current EEG signal of the current patient and judge the anesthesia state of the current patient according to the human consciousness evaluation model.

[0192] Advantages of this embodiment: The present invention collects EEG signals of different patients in different states before and after the operation to establish a human consciousness evaluation model, and uses this human consciousness evaluation model to evaluate the current anesthesia state of the patient according to the current EEG signal of the patient, making the anesthesia state monitoring more objective. At the same time, it also reduces the work intensity of anesthesiologists, improves the anesthesia level, reduces the usage of anesthetic drugs, and reduces the surgical cost.

[0193] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. An anesthesia state assessment system applicable to patients of different ages, characterized in that, include: Signal acquisition module, used to collect EEG signals of patients of different ages in different states before and after surgery; A signal processing module, used to process the EEG signal and establish a human consciousness assessment model based on the processed EEG signal; An anesthesia state assessment module, used to collect the current EEG signal of the current patient and determine the anesthesia state of the current patient according to the human consciousness assessment model; Wherein, the signal processing module includes: A signal screening unit, configured to obtain, according to the storage rule, corresponding EEG signals of the same target patient, and obtain, according to the longitudinal labels of the corresponding EEG signals, a first target EEG signal in a first state; Acquire a first average quality of the first target brain signal, and segment the first target EEG signal according to a preset EEG segmentation method to obtain a plurality of first segmented EEG signals; Respectively obtaining second average qualities of a plurality of first segmented EEG signals, and obtaining a quality error according to the first average quality and the second average quality; When the quality error corresponding to the first segmented EEG signal is greater than a preset value, determining that the first segmented EEG signal is a distorted EEG signal, and removing the distorted EEG signal; When the quality error corresponding to the first segmented EEG signal is less than or equal to a preset value, determining that the first segmented EEG signal is a usable EEG signal; A signal analysis unit, configured to screen out a standard EEG signal based on a third average quality of all available EEG signals, and obtain a first fluctuation amplitude and a standard time domain of the standard EEG signal; Obtaining the injection dose of the target patient's anesthetic, and based on the injection dose, estimating the action range of the anesthetic, determining the action center, and obtaining the dynamic changes of the muscle nerves at the action center; Acquire the dynamic changes of muscle nerves corresponding to the standard time domain, determine the activity of the muscle nerves in the standard time domain according to the dynamic changes of the muscle nerves, and gain the first fluctuation amplitude based on the muscle nerve activity to obtain a second fluctuation amplitude; a feature acquisition unit, configured to select a target time domain from all first segmented EEG signals according to the second fluctuation amplitude, intercept the EEG signal in the target time domain as a feature EEG signal, and acquire a change feature of the feature EEG signal to obtain a first state change feature; Based on the signal screening unit and the signal analyzing unit, a second state change characteristic corresponding to the second state and a third state change characteristic corresponding to the third state of the target patient are respectively obtained.

2. The anesthesia state evaluation system applicable to patients of different ages according to claim 1, characterized in that, The different states before and after the operation include awake state, anesthesia state, and recovery state.

3. The anesthetic state assessment system applicable to patients of different ages according to claim 1, wherein The signal acquisition module comprises: A preparation unit, used to obtain the current working state of the EEG signal acquisition device, and initialize the working parameters of the EEG signal acquisition device according to the current working state; A first acquisition unit, used to control the EEG signal acquisition device to acquire EEG signals from a target patient; A storage unit is used to store the EEG signal of the target patient.

4. The anesthetic state assessment system applicable to patients of different ages according to claim 3, characterized in that, The signal acquisition module further includes: A signal verification unit, which is used to verify the validity of the collected electroencephalogram (EEG) signals of the target patient before storing the EEG signals of the target patient, including: Obtaining a display image of the collected EEG signals, and judging the validity of the collected EEG signals according to the image display rules of the EEG signals; When the display images of the EEG signals within the intercepted time are coherent, the EEG signals are valid, the EEG signals are stored, and the acquisition of the EEG signals of the target patient is completed; When the display images of the EEG signals within the intercepted time are not coherent, the EEG signals are invalid, the EEG signal acquisition device is controlled to continue to collect the EEG signals of the target patient, and the verification is performed again until valid EEG signals are obtained.

5. The anesthesia state evaluation system applicable to patients of different ages according to claim 3, wherein: The storage unit is further configured to obtain the identity information of the target patient corresponding to the EEG signals, obtain the age of the target patient according to the identity information, and add a horizontal label to the EEG signals according to the patient age; Obtaining the state information of the target patient corresponding to the EEG signals, classifying the EEG signals according to the state information, and adding a vertical label; Based on the horizontal label and the vertical label, the EEG signals are stored in corresponding positions according to preset storage rules.

6. The anesthesia state evaluation system applicable to patients of different ages according to claim 1, characterized in that The signal processing module further includes: A data screening unit, which is used to respectively obtain the first state change characteristics of different target patients, classify the first state change characteristics according to the horizontal label, and respectively obtain a first data set, a second data set, and a third data set; Obtaining the overall change characteristics of each data set, dividing the overall change characteristics into multiple sub-data sets according to the age characteristics, and respectively obtaining the subset change characteristics of the multiple sub-data sets; Based on the similarity between the subset change characteristics and the overall change characteristics, obtaining the characteristic influence weight of the corresponding sub-data set corresponding to the data set, and screening out the optimal sub-data set according to the characteristic influence weight; Based on the data screening unit, respectively obtaining the optimal sub-data sets corresponding to the second state change characteristics and the third state change characteristics; A rule acquisition unit, which is used to obtain the original EEG signals of different target patients, determine the state boundary time domain of the original EEG signals, intercept the regional EEG signals of the state boundary time domain, and there are at least two of the boundary time domains; Dividing the regional EEG signals according to the first state change characteristics, the second state change characteristics, and the third state change characteristics. If the regional EEG signals cannot be divided into two stages, it is determined that the state boundary time domain is a false time domain; If the regional EEG signals can be divided into two stages, it is determined that the state boundary time domain is a true time domain, and the junction of the two stages is the state critical point; Obtaining the anesthetic injection information corresponding to the critical point and the physical examination information of the corresponding target patient, comparing the differences of the critical points between different target patients, obtaining an anesthesia influence index, and establishing a critical point judgment rule according to the anesthesia influence index; A model establishment unit is configured to establish a primary human consciousness evaluation model by using the critical point judgment rule, and divide the EEG signal data corresponding to the optimal sub-dataset into a training set and a test set; Use the test set to train the primary human consciousness evaluation model. At the same time, use the test set to test the trained human consciousness evaluation model. When the test result corresponds to the anesthesia state that is consistent with the actual anesthesia state, determine the trained human consciousness evaluation model as the final human consciousness evaluation model.

7. An anesthetic state assessment system applicable to patients of different ages according to claim 1, characterized in that, The anesthesia state evaluation module further includes: A first acquisition unit is configured to acquire the current EEG signal of the current patient, and filter the current EEG signal to obtain a current effective EEG signal; An evaluation unit is configured to evaluate the current effective EEG signal by using the human consciousness evaluation model, determine the current state of the current patient, and judge whether the current state is normal according to the surgical progress state; An alarm unit is configured to determine that the current state is abnormal and issue an alarm notification when the current state of the current patient does not match the surgical progress state.

8. The anesthesia state evaluation system for patients of different ages according to claim 7, wherein: The alarm unit is further configured to judge whether the surgery is in progress when the current state of the current patient does not match the surgical progress state; If it is during the surgery, obtain the consciousness index of the current patient, and correct the current consciousness index according to the influence coefficient of the patient's constitution on the reduction speed of the anesthetic to obtain a target consciousness index; Use the dynamic consciousness index of the current patient during the surgery to determine the target harm index of the anesthetic for the current patient; Judge whether the target consciousness index and the target harm index are higher than the highest consciousness index and harm index during the surgery; If it is higher than the highest consciousness index and harm index during the surgery, issue an emergency alarm notification based on the alarm unit; Otherwise, issue a general alarm notification based on the alarm unit.

Images