CN115067921B - Brain electrical impedance data-based nerve function damage prediction system for extracorporeal circulation operation - Google Patents
Brain electrical impedance data-based nerve function damage prediction system for extracorporeal circulation operation Download PDFInfo
- Publication number
- CN115067921B CN115067921B CN202210671172.6A CN202210671172A CN115067921B CN 115067921 B CN115067921 B CN 115067921B CN 202210671172 A CN202210671172 A CN 202210671172A CN 115067921 B CN115067921 B CN 115067921B
- Authority
- CN
- China
- Prior art keywords
- data
- brain
- impedance
- electrical impedance
- brain electrical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/053—Measuring electrical impedance or conductance of a portion of the body
- A61B5/0536—Impedance imaging, e.g. by tomography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/053—Measuring electrical impedance or conductance of a portion of the body
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses an extracorporeal circulation operation nerve function damage prediction system based on brain electrical impedance data, which comprises: the data acquisition equipment acquires brain electrical impedance data of a patient in operation; the image reconstruction module is used for reconstructing a brain impedance space distribution diagram according to the brain impedance data acquired by the data acquisition equipment; the data extraction module is used for extracting characteristic parameter indexes from the brain electrical impedance data acquired by the acquisition equipment; and the prediction classification module is used for analyzing the extracted characteristic parameter indexes through the trained classification model and outputting classification results. The brain electrical impedance data-based nerve function damage prediction system for extracorporeal circulation operation can collect brain electrical impedance data of a patient in operation in real time and predict nerve function damage according to the collected data, so that a doctor is guided to adjust a perfusion strategy.
Description
Technical Field
The invention relates to an extracorporeal circulation operation nerve function damage prediction system based on brain electrical impedance data.
Background
Cardiovascular diseases are the primary cause of disease death in China, reaching more than 43% of total mortality, and the morbidity is in a continuous rising stage. Cardiac surgical treatment is the final guarantee of life health for many critical cardiovascular patients. 70% of cardiac surgery needs to be performed under extracorporeal circulation life support conditions with the patient's heart stopped.
The complication of postoperative brain injury is a key problem which currently plagues the curative effect of heart surgery under extracorporeal circulation. Especially in the case of total aortic arch replacement surgery, the probability of occurrence of cerebral hypoxia is as high as 73%, the hypoxia time is accumulated to a certain extent, and the brain injury is often irreversible. How to monitor the peri-operative brain injury in real time and perform brain injury early warning becomes a key for improving the prognosis of patients. The heating monitoring means for nervous system commonly used in the extracorporeal circulation at present comprise electroencephalogram (EEG), evoked Potential Response (EPR), transcranial Doppler (TCD), brain oxygen saturation (NIRS) and other means.
Among them, EEG, NIRS and other means are limited to only the cerebral cortex and subcutaneous local area, and EPR and TCD reflect cerebral perfusion conditions, but lack reliable diagnostic criteria. There is an urgent need in the current extracorporeal circulation for new technology and equipment suitable for bedside use in the operation field, sensitive to the state of brain perfusion in operation, and capable of early warning brain injury in real time.
Disclosure of Invention
The invention provides an extracorporeal circulation operation nerve function damage prediction system based on brain electrical impedance data, which solves the technical problems, and concretely adopts the following technical scheme:
an extracorporeal circulation operation nerve function damage prediction system based on brain electrical impedance data, comprising:
the data acquisition equipment acquires brain electrical impedance data of a patient in operation;
the image reconstruction module is used for reconstructing a brain impedance space distribution diagram according to the brain impedance data acquired by the data acquisition equipment;
the data extraction module is used for extracting characteristic parameter indexes from the brain electrical impedance data acquired by the acquisition equipment;
and the prediction classification module is used for analyzing the extracted characteristic parameter indexes through the trained classification model and outputting classification results.
Further, the specific method for acquiring brain electrical impedance data of the patient in operation by the data acquisition equipment comprises the following steps:
the method comprises the steps that 16 electrodes of the data acquisition equipment are uniformly worn on the brain of a patient;
and acquiring brain electrical impedance data of the patient according to a preset mode through a data acquisition device.
Further, the specific method for acquiring brain electrical impedance data through the data acquisition equipment comprises the following steps:
the data acquisition equipment sequentially selects two of 16 electrodes as excitation electrodes according to a preset rule, sequentially measures the voltage difference on each adjacent electrode pair, calculates to obtain corresponding transmission impedance modulus values, obtains 256 transmission impedance modulus values after each electrode traverses one excitation, forms 1 frame of brain impedance data, and records as
Where k denotes a kth frame, removing 64 error data from 256 transmission impedance modulus values,obtaining final 1 frame of brain impedance data, which is marked as x k ∈R 192×1 。
Further, the specific method for reconstructing the brain impedance space distribution diagram by the image reconstruction module according to the brain impedance data acquired by the data acquisition equipment is as follows:
brain electrical impedance data at the moment of full flow perfusion before deep stop is selected as a reference frame and marked as x 0 Brain electrical impedance data acquired during deep stop low flow cerebral perfusion is taken as a current frame and is recorded as x k ；
Establishing an image reconstruction matrix H through an algorithm;
the image is reconstructed according to the following formula,
wherein s is k And the reconstructed value is a reconstructed value of each subdivision unit node in the imaging region obtained through image reconstruction.
Further, the characteristic parameter indexes extracted by the data extraction module comprise the whole brain transmission impedance difference, the left and right transmission impedance difference, the integral of the left and right transmission impedance difference, the left and right distribution impedance difference, the integral of the left and right distribution impedance difference and the total duration of the deep stop process.
Further, the trained classification model is a decision tree.
Further, the specific method for training the decision tree is as follows:
the characteristic and decision threshold are constructed manually according to the electrical impedance monitoring technology and the judgment of the clinician.
Further, the specific method for training the decision tree is as follows:
collecting existing clinical data and postoperative nerve function injury data;
preprocessing clinical data and extracting impedance characteristic parameters;
training the built decision tree through the extracted impedance characteristic parameters and the postoperative nerve function damage data.
Further, the decision tree contains 3 trees.
Further, the data acquisition device has an operating frequency range of 1-190 kHz and an operating current range of 500-1250 uA, and the operating mode selects a counter-excited adjacent receiving mode.
The brain electrical impedance data-based nerve function damage prediction system for the extracorporeal circulation operation has the advantages that the brain electrical impedance data-based nerve function damage prediction system for the extracorporeal circulation operation can collect brain electrical impedance data of a patient in operation in real time, and conduct nerve function damage prediction according to the collected data, so that a doctor is guided to adjust a perfusion strategy.
Drawings
FIG. 1 is a graph of a sigmoid function;
FIG. 2 is a schematic diagram of a first tree in a decision tree;
FIG. 3 is a schematic diagram of a second tree in the decision tree;
FIG. 4 is a schematic diagram of a third tree in the decision tree;
fig. 5 is a graph of the operational characteristics of an intraoperative impedance characteristic parameter decision tree algorithm with or without impairment of neural function.
Detailed Description
The invention is described in detail below with reference to the drawings and the specific embodiments.
An extracorporeal circulation operation nerve function damage prediction system based on brain electrical impedance data of the application comprises: the system comprises data acquisition equipment, an image reconstruction module, a data extraction module and a prediction classification module.
The data acquisition equipment is used for acquiring brain electrical impedance data of the patient in operation. The image reconstruction module is used for reconstructing a brain impedance space distribution diagram according to the brain impedance data acquired by the data acquisition equipment. The data extraction module is used for extracting characteristic parameter indexes from brain electrical impedance data acquired by the acquisition equipment. The prediction classification module is used for analyzing the extracted characteristic parameter indexes through the trained classification model and outputting classification results. The brain electrical impedance data-based nerve function damage prediction system for extracorporeal circulation operation can collect brain electrical impedance data of a patient in operation in real time and predict nerve function damage according to the collected data, so that a doctor is guided to adjust a perfusion strategy.
In the application, the working frequency range of the data acquisition device is 1-190 kHz, the working current range is 500-1250 uA, and the excitation measurement mode adopts a counter excitation adjacent receiving mode suitable for human brain measurement. The specific method for acquiring brain electrical impedance data of the patient in operation by the data acquisition equipment comprises the following steps:
the 16 electrodes of the data acquisition device were uniformly worn on the brain of the patient.
And acquiring brain electrical impedance data of the patient according to a preset mode through a data acquisition device.
As a preferred embodiment, the specific method for acquiring brain electrical impedance data through the data acquisition device is as follows:
the data acquisition device sequentially selects two of 16 electrodes as excitation electrodes according to a preset rule (such as adjacent, opposite and the like), sequentially measures the voltage difference (also called boundary voltage difference) on each adjacent electrode pair, calculates and obtains the corresponding transmission impedance module value through the following formula, wherein V represents opposite excitation, 256 voltage differences in an adjacent receiving mode, I represents excitation current,
after each electrode is stimulated once, 256 transmission impedance modulus values can be obtained to form 1 frame of brain impedance data, which is recorded as
Where k represents the kth frame. In the above 256 transmission impedance module values, in the total measurement process of 4×16=64 transmission impedance values, there are measurement electrodes serving as excitation electrodes at the same time, which are susceptible to the influence of the skin contact impedance of the electrodes, so that these data need to be removed. Thus, 64 error data are removed from 256 transmission impedance modulus values to obtain final 1 frame of brain impedance data, which is denoted as x k ∈R 192×1 。
As a preferred implementation mode, the specific method for reconstructing the brain impedance space distribution diagram by the image reconstruction module according to the brain impedance data acquired by the data acquisition equipment is as follows:
brain electrical impedance data at full flow perfusion time before deep stop (deep cryogenic stop body circulation) is selected as a reference frame and marked as x 0 Brain electrical impedance data acquired during deep stop low flow cerebral perfusion is taken as a current frame and is recorded as x k 。
An image reconstruction matrix H is established through an algorithm.
The image is reconstructed according to the following formula,
wherein s is k The reconstruction value of each subdivision unit node in the imaging area obtained through image reconstruction represents the relative variation of the resistivity at each node relative to the reference moment at the kth frame moment, and is dimensionless.
As a preferred embodiment, the characteristic parameter indicators extracted by the data extraction module include a total brain transmission impedance difference, a left-right transmission impedance difference, an integral of the left-right transmission impedance difference, a left-right distribution impedance difference, an integral of the left-right distribution impedance difference, and a total duration of the deep stop process. The comparison of the relative values is more meaningful, so the data analysis of the entire monitoring process uses the relative values for calculation.
TABLE 1 parameter index comparison Table
| Parameter index | Description of the invention |
| 1.ati_norm | Total brain transmission impedance difference (percent) relative to reference time |
| 2.ati_diff | Difference in transmission impedance between left and right with respect to reference time |
| 3.ati_dsum | Integration of the left and right transmission impedance differences relative to a reference time |
| 4.eit_diff | Left-right distributed (reconstructed) impedance differences relative to reference time |
| 5.eit_dsum | Integration of left and right distributed (reconstructed) impedance differences relative to a reference instant |
| 6.dhca_mtime | Total duration of deep stop process |
The specific meanings and calculation modes of the 6 parameter indexes are as follows:
1、ati_norm＝(Ak-A0)/A0*100
where Ak represents the whole brain transmission impedance at the k frame time, and A0 represents the whole brain transmission impedance at the reference time. Normally there should not be a large change in the whole brain impedance, which might suggest an increased risk.
2、
Wherein, the liquid crystal display device comprises a liquid crystal display device,
left brain transmission impedance representing k frame moments, < >>
Right brain transmission impedance representing k frame moments, < >>
Left brain transmission impedance representing reference moment, +.>
The right brain transmission impedance at the reference moment is indicated. Normally there should not be a large change in the left and right brain impedance differences, which might suggest an increased risk.
3、
Normally there should not be a continuous large change in the left and right brain impedance differences, a large change in duration may suggest an increased risk.
4、eit_diff＝eit_L-eit_R
The eit _l and eit _r are the left half brain impedance mean value and the right half brain impedance mean value of the whole brain impedance distribution calculated by the resistance reconstruction algorithm, and the reconstruction impedance contains more brain space distribution impedance compared with the transmission impedance, which is the advantage of the impedance imaging algorithm. Normally there should not be a large change in the left and right brain impedance differences, which might suggest an increased risk.
5、
Normally there should not be a continuously large change in the left and right brain impedance differences, which could suggest an increased risk.
6、dhca_mtime＝T e -T 0
Wherein Te represents the end of the deep stop, T0 represents the start of the deep stop, and the unit is minutes. The shorter the cryogenic time should be, the lower the risk of cerebral hypoxia, and the longer the cryogenic stop time may suggest an increased risk.
In the present application, the classification model is selected as a decision tree, and is a logistic regression model.
The logistic regression model assumes that the strain Y is a binary variable, and takes the values as follows:
in addition, there are m independent variables X affecting Y 1 ,X 2 ,…,X m The logistic regression model can be expressed as:
wherein beta is 0 Is a constant term, beta 1 ,L,β m Is a regression coefficient. Let z=β 0 +β 1 X 1 +β 2 X 2 +L+β m X m Can obtain sigmoid function
The corresponding function curves are shown in fig. 1.
As can be seen from the figures: when Z tends to ++ infinity in the time-course of which the first and second contact surfaces, the P value approaches 1; as Z tends to- ≡the P value approaches 0. The P value is between 0 and 1, and the S shape is symmetrical with the (0, 0.5) as the center along with the increase or decrease of Z. These features of the LR model can be well matched to biological data. The logistic regression model formula is logarithmically transformed to obtain a linear form:
the left side thereof represents the occurrence probability ratio of positive to negative. In this embodiment, Y corresponds to the postoperative nerve function injury, and the independent variable X 1 ,X 2 ,…,X m Are m independent predictors of impedance characteristic parameters related to postoperative brain injury.
The decision tree is a basic classification and regression method, and has the meaning that the postoperative nerve function injury is basically classified (the most basic distinction of brain injury or no brain injury) through the impedance characteristic parameters in the operation. The positive detection accuracy is improved to the greatest extent by comprehensively judging the combination of the 6 parameters.
As a preferred embodiment, the specific method for training the decision tree is as follows:
the characteristic and decision threshold are constructed manually according to the electrical impedance monitoring technology and the judgment of the clinician. As shown in fig. 2-4, the decision tree of the present application contains 3 trees.
The intra-operative impedance characteristic parameter decision tree algorithm and the working characteristic curve with or without the neural function injury in the application are shown in fig. 5, the area under the average curve is 0.868, and the classification effect is ideal.
As an alternative implementation manner, the specific method for training the decision tree may be: existing clinical data and post-operative neurological impairment data are collected. The clinical data are preprocessed and impedance characteristic parameters are extracted. Training the built decision tree through the extracted impedance characteristic parameters and the postoperative nerve function damage data.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be appreciated by persons skilled in the art that the above embodiments are not intended to limit the invention in any way, and that all technical solutions obtained by means of equivalent substitutions or equivalent transformations fall within the scope of the invention.
Claims (7)
1. An extracorporeal circulation operation nerve function injury prediction system based on brain electrical impedance data, comprising:
the data acquisition equipment acquires brain electrical impedance data of a patient in operation;
the image reconstruction module is used for reconstructing a brain impedance space distribution diagram according to the brain impedance data acquired by the data acquisition equipment;
the data extraction module is used for extracting characteristic parameter indexes from the brain electrical impedance data acquired by the data acquisition equipment;
the prediction classification module is used for analyzing the extracted characteristic parameter indexes through a trained classification model and outputting classification results;
the specific method for acquiring brain electrical impedance data of the patient in operation by the data acquisition equipment comprises the following steps:
uniformly wearing 16 electrodes of the data acquisition equipment on the brain of a patient;
collecting the brain electrical impedance data of the patient according to a preset mode through a data collecting device;
the specific method for acquiring the brain electrical impedance data through the data acquisition equipment comprises the following steps:
the data acquisition equipment sequentially selects two of 16 electrodes as excitation electrodes according to a preset rule, sequentially measures the voltage difference on each adjacent electrode pair, calculates to obtain corresponding transmission impedance modulus values, obtains 256 transmission impedance modulus values after each electrode traverses one excitation, forms 1 frame of brain impedance data, and records as
Where k represents the kth frame, 64 error data are removed from 256 transmission impedance modulus values to obtain final 1 frame of brain electrical impedance data, denoted as x k ∈R 192×1 ；
The specific method for reconstructing the brain impedance space distribution diagram by the image reconstruction module according to the brain impedance data acquired by the data acquisition equipment comprises the following steps:
brain electrical impedance data at the moment of full flow perfusion before deep stop is selected as a reference frame and marked as x 0 Brain electrical impedance data acquired during deep stop low flow cerebral perfusion is taken as a current frame and is recorded as x k ；
Image reconstruction matrix H is established through algorithm k ；
The image is reconstructed according to the following formula,
wherein s is k And the reconstructed value is a reconstructed value of each subdivision unit node in the imaging region obtained through image reconstruction.
2. The brain electrical impedance data based extracorporeal circulation operation nerve function damage prediction system according to claim 1,
the characteristic parameter indexes extracted by the data extraction module comprise the whole brain transmission impedance difference, the left and right transmission impedance difference, the integral of the left and right transmission impedance difference, the left and right distribution impedance difference, the integral of the left and right distribution impedance difference and the total duration of the deep stop process.
3. The brain electrical impedance data based extracorporeal circulation operation nerve function damage prediction system according to claim 1,
the trained classification model is a decision tree.
4. The system for predicting nerve function injury by extracorporeal circulation operation based on brain electrical impedance data according to claim 3,
the specific method for training the decision tree comprises the following steps:
according to the electrical impedance monitoring technology and the judgment of a clinician, the characteristic parameters and the decision threshold are constructed manually.
5. The system for predicting nerve function injury by extracorporeal circulation operation based on brain electrical impedance data according to claim 3,
the specific method for training the decision tree comprises the following steps:
collecting existing clinical data and postoperative nerve function injury data;
preprocessing clinical data and extracting impedance characteristic parameters;
training the built decision tree through the extracted impedance characteristic parameters and the postoperative nerve function damage data.
6. The system for predicting nerve function injury by extracorporeal circulation operation based on brain electrical impedance data according to claim 3,
the decision tree contains 3 trees.
7. The brain electrical impedance data based extracorporeal circulation operation nerve function damage prediction system according to claim 1,
the working frequency range of the data acquisition equipment is 1-190 kHz, the working current range is 500-1250 uA, and the working mode selects the opposite excitation adjacent receiving mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210671172.6A CN115067921B (en) | 2022-06-14 | 2022-06-14 | Brain electrical impedance data-based nerve function damage prediction system for extracorporeal circulation operation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210671172.6A CN115067921B (en) | 2022-06-14 | 2022-06-14 | Brain electrical impedance data-based nerve function damage prediction system for extracorporeal circulation operation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115067921A CN115067921A (en) | 2022-09-20 |
| CN115067921B true CN115067921B (en) | 2023-06-13 |
Family
ID=83252016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210671172.6A Active CN115067921B (en) | 2022-06-14 | 2022-06-14 | Brain electrical impedance data-based nerve function damage prediction system for extracorporeal circulation operation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115067921B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0309049D0 (en) * | 2003-04-22 | 2003-05-28 | Univ Manchester | Nervous system monitoring method |
| CN212755675U (en) * | 2020-01-07 | 2021-03-23 | 南京邮电大学 | Physiological condition monitoring equipment based on electroencephalogram signals and bioimpedance data |
| CN112200221B (en) * | 2020-09-22 | 2021-06-15 | 深圳市丰盛生物科技有限公司 | Epilepsy prediction system and method based on electrical impedance imaging and electroencephalogram signals |
| CN114469046A (en) * | 2020-10-23 | 2022-05-13 | 北京华睿博视医学影像技术有限公司 | Electrical impedance imaging method, electrical impedance imaging system, storage medium, and electronic apparatus |
-
2022
- 2022-06-14 CN CN202210671172.6A patent/CN115067921B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115067921A (en) | 2022-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210000362A1 (en) | Monitoring the effects of sleep deprivation using neuronal avalanches | |
| EP2286723A1 (en) | Method and apparatus for determining sleep apnea | |
| WO2011044228A1 (en) | System and method for pain monitoring at the point-of-care | |
| DE102008002933A1 (en) | Data recording for patient status analysis | |
| KR102075503B1 (en) | System of Predicting Dementia and Operating Method The Same | |
| JP2019536562A (en) | Seizure symptomology involving muscle signals collected from electroencephalography electrodes | |
| US8219187B2 (en) | Method and apparatus for providing improved assessment of a physiological condition of a patient | |
| CN114748080A (en) | Method and system for detecting and quantifying sensory-motor function | |
| CN115299887B (en) | Detection and quantification method and system for dynamic metabolic function | |
| Bacher et al. | Validation of an EEG seizure detection paradigm optimized for clinical use in a chronically implanted subcutaneous device | |
| CN114267444A (en) | Method for detecting obstructive apnea and night frontal epilepsy by using sleep structure | |
| CN115067921B (en) | Brain electrical impedance data-based nerve function damage prediction system for extracorporeal circulation operation | |
| Kempfner et al. | Automatic REM sleep detection associated with idiopathic rem sleep Behavior Disorder | |
| Sloboda et al. | A simple sleep stage identification technique for incorporation in inexpensive electronic sleep screening devices | |
| CN115251852A (en) | Detection quantification method and system for body temperature regulation function | |
| CN116369853A (en) | Olfactory function standardized evaluation device and method based on brain-computer interaction technology | |
| Forouzanfar et al. | Automatic detection of hot flash occurrence and timing from skin conductance activity | |
| Bashi et al. | Diagnosis of obstructive apnea disease AHI in chemical warfare veterans based on HRV signals analysis using the ANFIS neural network | |
| CN109567823A (en) | A kind of anesthesia depth monitoring system and method based on near-infrared spectrum technique | |
| CN214906876U (en) | Integrated multifunctional monitoring equipment | |
| CN115486819B (en) | Method, system and device for multi-cascade detection and quantification of sensory-perceptual neural pathway | |
| Farooq et al. | Classification of Sleep using Polysomnography | |
| Navaneethakrishna et al. | Analysis of Heart Rate Variability in Normal and Diabetic ECG signals using Fragmentation Approach | |
| Cohen et al. | Exaggerated High-Beta Oscillations are Associated with Cortical Thinning at the Motor Cortex in Parkinson’s Disease | |
| Forouzandeh et al. | Depression diagnosis based on KNN algorithm and EEG signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |