Acute disturbance of consciousness prognosis evaluation method and device based on electroencephalogram and medium

Abstract

The invention relates to an electroencephalogram-based acute disturbance of consciousness prognosis evaluation method and device and a medium. The electroencephalogram-based acute disturbance of consciousness prognosis evaluation method comprises the following steps: acquiring electroencephalogram data of a patient; identifying the electroencephalogram data, and extracting characteristic waveforms in the electroencephalogram data; performing classification processing and error correction processing on the characteristic waveforms to form a waveform set, the waveform set comprising at least one characteristic waveform group, and each characteristic waveform group comprising a plurality of related waveform segments belonging to the same characteristic waveform; evaluating the waveform set based on a plurality of pre-stored waveform evaluation rules; and outputting a prognosis evaluation result corresponding to the waveform set under each waveform evaluation rule. By the adoption of the acute consciousness disorder prognosis evaluation method based on the electroencephalogram, the operation process can be simplified, automatic grading is achieved, and reliability, interpretability and accuracy of prognosis evaluation of acute consciousness disorder patients are remarkably improved.

Description

Method, device and medium for prognosis assessment of acute disturbance of consciousness based on electroencephalogram Technical Field

[0001] The present disclosure relates to the technical field of electroencephalogram (EEG) applications, and in particular to an EEG-based prognosis assessment method, device, and medium for acute consciousness disorder. Background Art

[0002] Acute disorder of consciousness is a neurological disease caused by damage to the central nervous system, resulting in impairment of an individual's perceptual ability. It may be caused by a variety of causes, such as acute ischemia-hypoxia, cerebrovascular disease, intracranial inflammation, poisoning, and metabolic diseases. The prognostic assessment of acute disorder of consciousness can assist physicians in timely adjusting treatment measures and promoting the patient's recovery of consciousness. Electroencephalogram (EEG) is a bioelectric signal recorded by electrodes placed in the cerebral cortex or intracranial. Due to its non-invasive, continuous, real-time, dynamic, low-cost, and high correlation with the state of consciousness, it plays a very important role in the prognosis of disorder of consciousness. However, the use of EEG for prognostic assessment in clinical practice requires professional doctors to interpret long-term EEG records, which is a huge workload, and the consistency of the interpretation conclusions is poor. It is very dependent on the doctor's experience and professional quality.

[0003] Summary of the Invention

[0004] To overcome the problems existing in the related art, the present disclosure provides a method, device and medium for prognosis assessment of acute consciousness disorder based on electroencephalogram (EEG).

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided an electroencephalogram-based method for prognosis assessment of acute disturbance of consciousness, comprising: acquiring electroencephalogram data of a patient;

[0006] Identifying the electroencephalogram data and extracting characteristic waveforms from the electroencephalogram data;

[0007] performing classification and error correction processing on the characteristic waveforms to form a waveform set, wherein the waveform set includes at least one characteristic waveform group, each characteristic waveform group including a plurality of related waveform segments belonging to the same characteristic waveform;

[0008] Evaluating the waveform set based on a plurality of pre-stored waveform evaluation rules;

[0009] Outputting the prognosis evaluation result corresponding to the waveform set under each waveform evaluation rule.

[0010] In some exemplary embodiments of the present disclosure, the characteristic waveforms include alpha rhythm, theta rhythm, spindle waves, delta waves, burst suppression, electrical silence, epileptiform discharges, triphasic waves and / or GPD.

[0011] In some exemplary embodiments of the present disclosure, classification and error correction are performed on the characteristic waveforms to form a waveform set, including:

[0012] Classifying waveform segments belonging to the same characteristic waveform into one category as a group of characteristic waveform groups, wherein the multiple waveform segments in each group of characteristic waveform segments are mutually related waveform segments;

[0013] Performing time-frequency transformation on each relevant waveform segment in each set of the characteristic waveform groups to obtain frequency domain information of each relevant waveform segment in each set of the characteristic waveform groups;

[0014] Calculating an average value of the plurality of frequency domain information, and using the obtained average value as reference frequency domain information;

[0015] The difference between the frequency domain information and the reference frequency domain information is calculated, and the relevant waveform segments corresponding to the frequency domain information whose difference is greater than a preset value are removed from the characteristic waveform group to form the waveform set.

[0016] In some exemplary embodiments of the present disclosure, the pre-stored multiple waveform evaluation rules include scale evaluation rules and prediction network model evaluation rules.

[0017] In some exemplary embodiments of the present disclosure, the scale evaluation rules include at least one of Synek, Yang, and Hofmeijer; and / or,

[0018] The prediction network model evaluation rules include multiple sub-evaluation network models, which are trained based on electroencephalogram parameters of a patient in a coma state. Different sub-evaluation network models correspond to different durations of the patient's coma state.

[0019] In some exemplary embodiments of the present disclosure, the waveform set is evaluated based on a plurality of pre-stored waveform evaluation rules, including:

[0020] Matching a reference waveform included in the waveform evaluation rule with a plurality of related waveform segments in each of the characteristic waveform groups in the waveform set, and obtaining a first matching degree between each related waveform segment and the corresponding reference waveform;

[0021] Obtaining a second matching degree for each set of characteristic waveform groups according to the first matching degree;

[0022] An evaluation score of the waveform set is obtained according to the second matching degree.

[0023] In some exemplary embodiments of the present disclosure, the prognostic evaluation result corresponding to the waveform set includes a prognostic evaluation, a position of the characteristic waveform in the electroencephalogram data, and the evaluation score, wherein the prognostic evaluation includes a good prognostic condition and a poor prognostic condition.

[0024] According to a second aspect of an embodiment of the present disclosure, there is provided an electroencephalogram-based acute consciousness disorder prognosis assessment device, the electroencephalogram-based acute consciousness disorder prognosis assessment device comprising:

[0025] a receiving module configured to obtain electroencephalogram data of the patient;

[0026] an extraction module, configured to identify the electroencephalogram data and extract characteristic waveforms from the electroencephalogram data;

[0027] a clustering module configured to perform classification and error correction processing on the characteristic waveform to form a waveform set, wherein the waveform set includes at least one set of characteristic waveform groups, each set of the characteristic waveform groups including a plurality of related waveform segments belonging to the same characteristic waveform;

[0028] an evaluation module configured to evaluate the waveform set based on a plurality of pre-stored waveform evaluation rules;

[0029] The output module is configured to output the prognosis evaluation result corresponding to the waveform set under each waveform evaluation rule.

[0030] According to a third aspect of an embodiment of the present disclosure, there is provided an electroencephalogram-based acute consciousness disorder prognosis assessment device, the electroencephalogram-based acute consciousness disorder prognosis assessment device comprising:

[0031] processor;

[0032] a memory for storing processor-executable instructions;

[0033] The processor is configured to execute the electroencephalogram-based acute consciousness disorder prognosis assessment method provided in the first aspect of the present disclosure.

[0034] According to a fourth aspect of an exemplary embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of an electroencephalogram-based acute consciousness disorder prognosis assessment device, the processor is enabled to execute the electroencephalogram-based acute consciousness disorder prognosis assessment method provided by the embodiment provided in the first aspect of the present disclosure.

[0035] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects:

[0036] By extracting characteristic waveforms of acute disorders of consciousness from EEGs, a waveform set is formed. These waveforms are then evaluated based on multiple pre-existing waveform assessment rules, and the corresponding prognostic assessment results for each waveform set are output. This not only simplifies the operational process and enables automated grading, but also significantly improves the reliability, interpretability, and accuracy of prognostic assessments for patients with acute disorders of consciousness.

[0037] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0039] FIG1 is a flow chart showing a method for prognosis assessment of acute consciousness disorder based on electroencephalogram (EEG), according to an exemplary embodiment.

[0040] FIG2 is a block diagram of an EEG-based prognosis assessment device for acute consciousness disorders according to an exemplary embodiment.

[0041] FIG3 is a block diagram of an EEG-based prognosis assessment device for acute consciousness disorders according to an exemplary embodiment. DETAILED DESCRIPTION

[0042] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent the same or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0043] The exemplary embodiment of the present disclosure provides a method for prognostic assessment of acute consciousness disorder based on electroencephalogram (EEG). As shown in FIG1 , the method for prognostic assessment of acute consciousness disorder based on EEG shown in the present disclosure includes:

[0044] S101: Acquire the patient's electroencephalogram data;

[0045] S102: Identify the EEG data and extract characteristic waveforms from the EEG data;

[0046] S103: performing classification and error correction processing on the characteristic waveforms to form a waveform set, where the waveform set includes at least one characteristic waveform group, and each characteristic waveform group includes a plurality of related waveform segments belonging to the same characteristic waveform;

[0047] S104: Evaluate the waveform set based on multiple pre-stored waveform evaluation rules;

[0048] S105: Outputting the prognosis evaluation result corresponding to the waveform set under each waveform evaluation rule.

[0049] Among them, in step S101, the EEG signal of a patient who has been diagnosed with acute consciousness disorder or has a tendency to acute consciousness disorder is collected. The collection method can be, for example, to collect the patient's EEG data by attaching electrodes to the patient's head, and a special EEG collection device can be used for collection. When attaching electrodes, the number of electrodes can be selected according to the patient's condition and the physician's experience. For example, if the patient's symptoms are more severe, the number of electrodes can be increased; for example, if the patient's brain is traumatized, a smaller number of electrodes can be attached to the traumatized location, and the remaining locations do not need to be attached. In one example, the position of the electrodes can be placed according to the international standard lead 10-20 electrode system (i.e., the international standard 10-20 for EEG electrode positions). The number of electrodes can be appropriately reduced according to clinical needs, such as setting 18 electrodes, so as to obtain the patient's EEG data as basic data for prognostic assessment. Among them, the international standard lead 10-20 electrode system is a reference standard for an EEG data collection process commonly used in this field.

[0050] In step S102, the acquired EEG data is input into a device, such as a characteristic waveform detector, to extract characteristic waveforms from the EEG data. For example, characteristic waveforms associated with acute impaired consciousness are extracted from the EEG data by traversing the EEG data. If the device used to collect the EEG data also has a characteristic waveform detection function, the characteristic waveforms in the EEG data can be directly output by the device collecting the EEG data.

[0051] The characteristic waveforms include alpha rhythm, theta rhythm, spindles, delta waves, burst suppression, electrical quiet, epileptiform discharges, triphasic waves, and / or GPD. When extracting characteristic waveforms from EEG data, relevant characteristic waveforms can be selectively extracted based on the patient's condition and the physician's experience. For example, alpha rhythm, triphasic waves, and burst suppression can be extracted for patients with encephalopathy. For another example, alpha rhythm, theta rhythm, spindles, and GPD can be extracted for patients in a sleeping state.

[0052] Among them, the alpha rhythm is a rhythmic waveform in the EEG with a frequency of 8-12 Hz, mostly sinusoidal. It is more likely to occur when the subject is eyes closed and mentally relaxed, and is the most important indicator for analyzing EEG background activity. The theta rhythm is a rhythmic waveform in the EEG with a frequency of 12-20 Hz, which occurs in normal adults during sleep. Sleep spindles, also known as the sigma rhythm, are a marker of the entry into stage 2 sleep and can continue into stage 3. They are one of many important measurable features of brain activity during sleep. Delta waves are EEG waveforms with a frequency below 4 Hz. Delta waves rarely occur in normal adults during wakefulness, but only during sleep. Burst suppression is a serious EEG abnormality characterized by bursts of medium-to-high amplitude activity alternating with low-voltage or electrical suppression states, indicating widespread damage or inhibition in the cerebral cortex and subcortex. Electrical silence is a waveform characterized by EEG activity consistently below 20 μV, unaffected by state changes and rarely responding to external stimuli. Clinically, epileptic discharges include paroxysmal abnormalities such as spikes, sharp waves, spike-slow complexes, sharp-slow complexes, and polyspike-slow complexes. Triphasic waves are medium-to-high amplitude slow waves with a frequency of approximately 1-2 Hz. The brain waves deflect three times above and below the baseline, forming a wave with three components alternating above and below the baseline. The first phase is a low-amplitude negative wave, the second phase is a prominent positive wave, and the third phase is a negative slow wave that lasts longer than the second phase. These are common in various metabolic encephalopathy, Creutzfeldt-Jakob disease, hypoxic encephalopathy, and toxic encephalopathy. GPD (Generalized Periodic Discharge), also known as generalized periodic complexes, is a severe EEG abnormality characterized by the repetitive and stereotyped appearance of generalized spikes, sharp waves, and other complexes that stand out from the background at similar intervals.

[0053] In step S103, the characteristic waveforms extracted in step S102 are classified according to waveform categories, and multiple related waveform segments belonging to the same characteristic waveform are grouped into the same characteristic waveform group. For example, if three waveforms, namely α rhythm, triphasic wave, and burst suppression, are extracted, then each waveform segment belonging to α rhythm, triphasic wave, and burst suppression in the EEG data is grouped together to form three characteristic waveform groups, namely α rhythm, triphasic wave, and burst suppression. At the same time, error correction is performed on the waveforms of each characteristic waveform group to eliminate irrelevant waveforms incorrectly extracted by the waveform detector. For example, if the waveform detector actually extracted a θ rhythm waveform segment but mistakenly identified it as an α rhythm during output, it would be classified into the characteristic waveform group of α rhythm. After error correction, the θ rhythm waveform segment can be eliminated, so that all the corresponding waveform segments in the characteristic waveform group are correct. All characteristic waveform groups constitute a waveform set, where the number of characteristic waveform groups is not limited, and everything is based on the number of characteristic waveform categories extracted.

[0054] In step S103, the characteristic waveforms are classified and error-corrected to form a waveform set, including:

[0055] S1031: grouping waveform segments belonging to the same characteristic waveform into one category as a set of characteristic waveform groups, wherein the waveform segments in each set of characteristic waveform segments are mutually related waveform segments;

[0056] S1032: performing time-frequency transformation on each relevant waveform segment in each characteristic waveform group to obtain frequency domain information of each relevant waveform segment in each characteristic waveform group;

[0057] S1033: Calculate an average value of the multiple frequency domain information, and use the obtained average value as reference frequency domain information;

[0058] S1034: Calculate the difference between the frequency domain information and the reference frequency domain information, and remove the relevant waveform segments corresponding to the frequency domain information whose difference is greater than a preset value from the characteristic waveform group to form a waveform set.

[0059] Taking the α rhythm as an example, step S1031 assigns all extracted α rhythms from the special waveforms to an α rhythm characteristic waveform group, ensuring that all waveform segments in the α rhythm characteristic waveform group are α rhythms. In step S1032, a time-frequency transformation is performed on each α rhythm waveform segment in the α rhythm characteristic waveform group to obtain conventional frequency domain information, such as frequency and amplitude. Step S1033 combines the frequency domain information of all α rhythm waveform segments in the group and uses a clustering algorithm to obtain an average value. This average value is used as the reference frequency domain information for the α rhythm characteristic waveform group for error correction in step S1034. Step S1034 calculates the difference between the frequency domain information of each α rhythm waveform segment and the reference frequency domain information, sorts them by difference, and eliminates α rhythm waveform segments corresponding to frequency domain information with a difference greater than a preset value. α rhythm waveform segments that meet the preset difference requirement are retained and determined as the final α rhythm waveform group. The preset difference value can be set individually according to the nature of each characteristic waveform. Similarly, each characteristic waveform segment extracted from theta rhythm, spindles, and GPD is subjected to the same classification and error correction process, forming multiple characteristic waveform groups. All characteristic waveform groups constitute a waveform set. This classification and error correction process eliminates the erroneous extraction of irrelevant waveforms due to waveform detector errors, reducing the impact on prognostic assessment results and ensuring more accurate results.

[0060] In step S104, the pre-stored waveform rules are all mature grading methods at this stage, including manual grading methods and semi-automatic grading methods. These mature grading methods are added to the prognosis evaluation method as evaluation rules. Among them, they can be selectively used from the evaluation rules according to clinical needs. The waveform set is evaluated multiple times by multiple pre-stored evaluation rules, so that the evaluation results of the waveform set are interpretable and reliable.

[0061] Among them, the pre-stored multiple waveform evaluation rules include scale evaluation rules and prediction network model evaluation rules.

[0062] Scale assessment rules are currently manual grading methods. These schemes have low sensitivity and specificity, requiring physicians to possess extensive EEG image reading experience and specialized knowledge. Predictive network model assessment rules are currently semi-automatic grading methods, employing a single feature dimension and poor interpretability, requiring validation with clinical data. Incorporating existing manual and semi-automatic grading methods as pre-existing assessment rules into the prognostic assessment method simplifies the process and enhances the theoretical support, interpretability, and reliability of the automated grading output.

[0063] The scale evaluation rules include at least one of Synek, Yang, and Hofmeijer. The prediction network model evaluation rules include multiple sub-evaluation network models, each trained based on electroencephalogram (EEG) parameters of a comatose patient. Different sub-evaluation network models correspond to different durations of coma.

[0064] Among manual grading methods, the Synek scale, proposed by Synek in 1988, is an EEG-based prognostic scale for adult comatose patients. It was the first grading system to use EEG signals as primary information, with a four-level classification system. This grading method has strong theoretical and practical support. The Young scale, proposed by Young in 1997 based on the Synek scale, is a more widely used grading standard for severe brain damage. The Hofmeijer scale is designed for patients after cardiopulmonary resuscitation and is generally divided into three levels. In the semi-automatic grading method, the prediction network model uses a convolutional neural network with a VGG architecture. By collecting EEG parameters from patients with different durations of coma, such as 12 hours and 24 hours, it trains sub-evaluation network models for different durations. The patient's EEG waveforms are used as input data and fed into the prediction network model for evaluation. The corresponding sub-evaluation network model is used as the evaluation rule for different durations of coma. For example, if a patient has been in a coma for 12 hours, the sub-evaluation network model for the 12-hour coma is used. In addition, the waveform sets of different durations of the patient's coma can be used as EEG data for subsequent neural network training.

[0065] Step S104 evaluates the waveform set based on multiple pre-stored waveform evaluation rules, including:

[0066] S1041: Matching the reference waveform included in the waveform evaluation rule with a plurality of related waveform segments in each characteristic waveform group in the waveform set to obtain a first matching degree between each related waveform segment and its corresponding reference waveform;

[0067] S1042: Obtaining a second matching degree for each characteristic waveform group based on the first matching degree;

[0068] S1043: Obtain an evaluation score of the waveform set according to the second matching degree.

[0069] In step S1041, the multiple waveform evaluation rules pre-stored each include a reference waveform for each characteristic waveform and its related information. Using the reference waveform as the reference standard for evaluation, each relevant waveform segment in each characteristic waveform group is matched with a reference waveform of the same category, and the matching degree of each relevant waveform segment is recorded as a first matching degree. In step S1042, after each relevant waveform segment in each characteristic waveform group has been matched, all first matching degrees are combined to obtain a second matching degree for each characteristic waveform group. In step S1043, the second matching degrees of each characteristic waveform group are combined to obtain an evaluation score for the waveform set under different evaluation rules.

[0070] In step S105 , the prognostic evaluation results of the waveform set evaluated by each grading method are output, and the combined output results contain prediction evidence, thereby improving the reliability of the prognostic evaluation.

[0071] The prognostic evaluation result corresponding to the waveform set includes a prognostic evaluation, a position of the characteristic waveform in the electroencephalogram data, and an evaluation score, wherein the prognostic evaluation includes a good prognostic condition and a poor prognostic condition.

[0072] The system takes a waveform set as input and evaluates it using multiple pre-existing waveform evaluation rules. The system then outputs the combined prognostic results for each evaluation rule. The results include an evaluation score and provide the location and original image of the relevant characteristic waveforms in the EEG data. This provides an index for doctors to view the results, allowing them to identify the EEG information and the cause of the illness when analyzing the patient's condition. Prognostic evaluation is based on two criteria: good and poor, providing doctors with a concise assessment and facilitating appropriate treatment options. For example, if the prognosis is good, a more aggressive treatment plan can be adopted to help the patient recover faster. If the prognosis is poor, less expensive medications and conservative treatment can be used to reduce the patient's financial burden.

[0073] The exemplary embodiments of the present disclosure provide an EEG-based prognostic assessment device for acute impaired consciousness. FIG2 shows a block diagram of the EEG-based prognostic assessment device for acute impaired consciousness. The block diagram includes a receiving module 21, an extraction module 22, a clustering module 23, an assessment module 24, and an output module 25.

[0074] a receiving module 21 configured to obtain electroencephalogram data of a patient;

[0075] an extraction module 22 configured to identify the EEG data and extract characteristic waveforms from the EEG data;

[0076] The clustering module 23 is configured to perform classification processing and error correction processing on the characteristic waveform to form a waveform set, where the waveform set includes at least one set of characteristic waveform groups, each of which includes multiple related waveform segments belonging to the same characteristic waveform;

[0077] An evaluation module 24 is configured to evaluate the waveform set based on a plurality of pre-stored waveform evaluation rules;

[0078] The output module 25 is configured to output the prognosis evaluation result corresponding to the waveform set under each waveform evaluation rule.

[0079] In an exemplary embodiment of the present disclosure, the characteristic waveforms are classified and error corrected to form a waveform set. The clustering module 23 is configured to:

[0080] The waveform segments belonging to the same characteristic waveform are classified into one category as a group of characteristic waveform groups, wherein the multiple waveform segments in each group of characteristic waveform segments are mutually related waveform segments;

[0081] Performing time-frequency transformation on each relevant waveform segment in each set of characteristic waveform groups to obtain frequency domain information of each relevant waveform segment in each set of characteristic waveform groups;

[0082] Calculate the average value of multiple frequency domain information and use the obtained average value as the reference frequency domain information;

[0083] The difference between the frequency domain information and the reference frequency domain information is calculated, and the relevant waveform segments corresponding to the frequency domain information whose difference is greater than a preset value are removed from the characteristic waveform group to form a waveform set.

[0084] In an exemplary embodiment of the present disclosure, the evaluation module 24 is configured to:

[0085] Matching the reference waveform included in the waveform evaluation rule with a plurality of related waveform segments in each characteristic waveform group in the waveform set to obtain a first matching degree between each related waveform segment and its corresponding reference waveform;

[0086] Obtaining a second matching degree for each characteristic waveform group according to the first matching degree;

[0087] An evaluation score of the waveform set is obtained based on the second matching degree.

[0088] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0089] FIG3 is a block diagram of an EEG-based acute consciousness disorder prognosis assessment device 1000 according to an exemplary embodiment. For example, the device 1000 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0090] 3 , apparatus 1000 may include one or more of the following components: a processing component 1002 , a memory 1004 , a power component 1006 , a multimedia component 1008 , an audio component 1010 , an input / output (I / O) interface 1012 , a sensor component 1014 , and a communication component 1016 .

[0091] The processing component 1002 generally controls the overall operation of the device 1000, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 1002 may include one or more processors 1020 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 1002 may include one or more modules to facilitate interaction between the processing component 1002 and other components. For example, the processing component 1002 may include a multimedia module to facilitate interaction between the multimedia component 1008 and the processing component 1002.

[0092] The memory 1004 is configured to store various types of data to support the operations of the device 1000. Examples of such data include instructions for any application or method operating on the device 1000, contact data, phone book data, messages, pictures, videos, etc. The memory 1004 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0093] The power component 1006 provides power to the various components of the device 1000. The power component 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 1000.

[0094] The multimedia component 1008 includes a screen that provides an output interface between the device 1000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1008 includes a front camera and / or a rear camera. When the device 1000 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0095] The audio component 1010 is configured to output and / or input audio signals. For example, the audio component 1010 includes a microphone (MIC) that is configured to receive external audio signals when the device 1000 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 1004 or transmitted via the communication component 1016. In some embodiments, the audio component 1010 also includes a speaker for outputting audio signals.

[0096] I / O interface 1012 provides an interface between processing component 1002 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0097] The sensor assembly 1014 includes one or more sensors for providing various aspects of the status assessment of the device 1000. For example, the sensor assembly 1014 can detect the open / closed state of the device 1000, the relative positioning of components, such as the display and keypad of the device 1000. The sensor assembly 1014 can also detect changes in the position of the device 1000 or a component of the device 1000, the presence or absence of user contact with the device 1000, the orientation or acceleration / deceleration of the device 1000, and changes in the temperature of the device 1000. The sensor assembly 1014 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 1014 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 can also include an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0098] The communication component 1016 is configured to facilitate wired or wireless communication between the device 1000 and other devices. The device 1000 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1016 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0099] In an exemplary embodiment, the apparatus 1000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described methods.

[0100] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1004 including instructions, which can be executed by the processor 1020 of the apparatus 1000 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0101] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a processing device of an electronic device, enables the processing device of the electronic device to perform the electroencephalogram-based acute consciousness disorder prognosis assessment method provided by an exemplary embodiment of the present disclosure.

[0102] Other embodiments of the present invention will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

[0103] It should be understood that the present invention is not limited to the exact construction described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims. Industrial Applicability

[0104] The disclosed embodiments extract relevant characteristic waveforms of acute disorders of consciousness from electroencephalograms to form a waveform set, convert existing scales and predictive network models into evaluation rules, analyze the waveforms in the waveform set, and output prognostic evaluation results with predictive evidence. This can greatly simplify the operation process, realize automated grading, and significantly improve the reliability, interpretability, and accuracy of prognostic evaluation of patients with acute disorders of consciousness.

Claims

1. A method for evaluating the prognosis of acute disturbance of consciousness based on electroencephalogram, characterized in that: include: Obtaining the patient's EEG data; Identifying the electroencephalogram data and extracting characteristic waveforms from the electroencephalogram data; performing classification and error correction processing on the characteristic waveforms to form a waveform set, wherein the waveform set includes at least one characteristic waveform group, each characteristic waveform group including a plurality of related waveform segments belonging to the same characteristic waveform; Evaluating the waveform set based on a plurality of pre-stored waveform evaluation rules; Outputting the prognosis evaluation result corresponding to the waveform set under each waveform evaluation rule.

2. The method for evaluating the prognosis of acute disturbance of consciousness based on electroencephalogram (EEG) according to claim 1, wherein: The characteristic waveforms include alpha rhythm, theta rhythm, spindle waves, delta waves, burst suppression, electrical silence, epileptiform discharges, triphasic waves and / or GPD.

3. The method for prognosis assessment of acute disturbance of consciousness based on electroencephalogram according to claim 1, characterized in that: Classifying and correcting the characteristic waveforms to form a waveform set includes: Classifying waveform segments belonging to the same characteristic waveform into one category as a group of characteristic waveform groups, wherein the multiple waveform segments in each group of characteristic waveform segments are mutually related waveform segments; Performing time-frequency transformation on each relevant waveform segment in each set of the characteristic waveform groups to obtain frequency domain information of each relevant waveform segment in each set of the characteristic waveform groups; Calculating an average value of the plurality of frequency domain information, and using the obtained average value as reference frequency domain information; The difference between the frequency domain information and the reference frequency domain information is calculated, and the relevant waveform segments corresponding to the frequency domain information whose difference is greater than a preset value are removed from the characteristic waveform group to form the waveform set.

4. The method for prognosis assessment of acute disturbance of consciousness based on electroencephalogram according to claim 1, characterized in that: The pre-stored multiple waveform evaluation rules include scale evaluation rules and prediction network model evaluation rules.

5. The method for prognosis assessment of acute disturbance of consciousness based on electroencephalogram according to claim 4, characterized in that: The scale evaluation rules include at least one of Synek, Yang, and Hofmeijer; and / or, The prediction network model evaluation rules include multiple sub-evaluation network models, which are trained based on electroencephalogram parameters of a patient in a coma state. Different sub-evaluation network models correspond to different durations of the patient's coma state.

6. The method for prognosis assessment of acute disturbance of consciousness based on electroencephalogram according to claim 1, characterized in that: Evaluate the waveform set based on multiple pre-stored waveform evaluation rules, including: Matching a reference waveform included in the waveform evaluation rule with a plurality of related waveform segments in each of the characteristic waveform groups in the waveform set, and obtaining a first matching degree between each related waveform segment and the corresponding reference waveform; Obtaining a second matching degree for each set of characteristic waveform groups according to the first matching degree; An evaluation score of the waveform set is obtained according to the second matching degree.

7. The method for prognosis assessment of acute disturbance of consciousness based on electroencephalogram according to claim 6, characterized in that: The prognostic evaluation result corresponding to the waveform set includes a prognostic evaluation, a position of the characteristic waveform in the electroencephalogram data, and the evaluation score, wherein the prognostic evaluation includes a good prognostic condition and a poor prognostic condition.

8. An electroencephalogram-based prognosis assessment device for acute consciousness disorders, characterized in that: The electroencephalogram-based acute consciousness disorder prognosis assessment device comprises: a receiving module configured to obtain electroencephalogram data of the patient; an extraction module, configured to identify the electroencephalogram data and extract characteristic waveforms from the electroencephalogram data; a clustering module configured to perform classification and error correction processing on the characteristic waveform to form a waveform set, wherein the waveform set includes at least one set of characteristic waveform groups, each set of the characteristic waveform groups including a plurality of related waveform segments belonging to the same characteristic waveform; an evaluation module configured to evaluate the waveform set based on a plurality of pre-stored waveform evaluation rules; The output module is configured to output the prognosis evaluation result corresponding to the waveform set under each waveform evaluation rule.

9. An electroencephalogram-based prognosis assessment device for acute consciousness disorders, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the electroencephalogram-based acute consciousness disorder prognosis assessment method as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by the processor of the electroencephalogram-based acute consciousness disorder prognosis assessment device, the processor is enabled to execute the electroencephalogram-based acute consciousness disorder prognosis assessment method as described in any one of claims 1 to 7.

Images