WO2012165602A1 - 認知機能障害判別装置、認知機能障害判別システム、およびプログラム - Google Patents
認知機能障害判別装置、認知機能障害判別システム、およびプログラム Download PDFInfo
- Publication number
- WO2012165602A1 WO2012165602A1 PCT/JP2012/064237 JP2012064237W WO2012165602A1 WO 2012165602 A1 WO2012165602 A1 WO 2012165602A1 JP 2012064237 W JP2012064237 W JP 2012064237W WO 2012165602 A1 WO2012165602 A1 WO 2012165602A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- feature amount
- determination
- cognitive dysfunction
- cognitive
- 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.)
- Ceased
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
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4088—Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus, e.g. for MRI, optical tomography or impedance tomography apparatus; Arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus, e.g. for MRI, optical tomography or impedance tomography apparatus; Arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
- A61B5/0042—Features or image-related aspects of imaging apparatus, e.g. for MRI, optical tomography or impedance tomography apparatus; Arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
- A61B5/026—Measuring blood flow
- A61B5/0261—Measuring blood flow using optical means, e.g. infrared light
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
- A61B5/4064—Evaluating the brain
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2576/00—Medical imaging apparatus involving image processing or analysis
- A61B2576/02—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part
- A61B2576/026—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part for the brain
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
- A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Definitions
- the present invention relates to a cognitive dysfunction discriminating device, a cognitive dysfunction discriminating system, and a program, and in particular, a cognitive dysfunction discriminating device, a cognitive dysfunction discriminating system, and It is about the program.
- the present invention has been made to solve the above problems, and an object of the present invention is to provide a cognitive dysfunction discriminating apparatus, a cognitive dysfunction discriminating system, and a program suitable for early screening of brain function.
- the cognitive impairment determination device provides a biological signal in a predetermined brain region of a subject measured when giving a task for activating the brain.
- a data acquisition unit that acquires data
- a feature amount extraction unit that extracts a feature amount of biological signal data acquired by the data acquisition unit
- a feature amount extracted by the feature amount extraction unit And a discriminator that discriminates the degree of the subject's cognitive dysfunction based on the data used for the determination of cognitive dysfunction.
- the cognitive dysfunction discriminating device is the cognitive dysfunction discriminating device according to the first aspect of the present invention, wherein the biological signal data is a blood flow in the predetermined brain region. It is the cerebral blood flow data which measured.
- the cognitive dysfunction discriminating device is the cognitive dysfunction discriminating device according to the first aspect of the present invention, wherein the biological signal data is the frontal as the predetermined brain region. It is the cerebral blood flow data which measured the hemoglobin flow rate by NIRS apparatus in each of an anterior field, a left temporal lobe, a right temporal lobe, a left parietal lobe, and a right parietal lobe.
- the cognitive dysfunction discriminating device is the cognitive dysfunction discriminating device according to the first aspect of the present invention, wherein the biological signal data is the frontal as the predetermined brain region.
- the biological signal data is the frontal as the predetermined brain region.
- the predetermined region in the left parietal lobe as the predetermined brain region
- the predetermined region in the left temporal lobe and the right parietal lobe as the predetermined brain region
- the cognitive dysfunction discriminating device is the cognitive dysfunction discriminating device according to any one of the first to fourth aspects of the present invention, wherein the degree of the cognitive dysfunction is known.
- a known data acquisition unit that acquires the biological signal data measured when giving the subject to a plurality of subjects, and a known data feature that extracts the feature amount of the biological signal data acquired by the known data acquisition unit
- a quantity extraction unit and a determination data generation unit that generates data used for the determination of the cognitive impairment based on the feature quantity extracted by the known data feature quantity extraction unit.
- the cognitive dysfunction discriminating apparatus is the cognitive dysfunction discriminating apparatus according to the fifth aspect of the present invention, wherein the determination data generating unit is extracted by the known data feature amount extracting unit.
- a selection unit that selects a feature amount to be used for determination of the cognitive dysfunction among the feature amounts that have been determined, the feature amount selected by the selection unit, and the degree of the cognitive dysfunction of the subject from which the feature amount has been extracted
- a learning unit that constructs a model for the determination unit to determine the degree of the cognitive impairment corresponding to the feature amount.
- a cognitive dysfunction discriminating apparatus uses a plurality of low-pass filters in the cognitive dysfunction discriminating apparatus according to any one of the first to sixth aspects of the present invention.
- a plurality of low-pass filters wherein the plurality of low-pass filters include a first filter, an electroencephalogram and a blood pressure used to remove noise including noise due to ambient light.
- the maximum amplitude value, the minimum amplitude value, the amplitude variance value, the amplitude average value, the fundamental frequency, and the slope of the approximate straight line in the biological signal data subjected to noise removal and noise removal using the first filter A variance value of amplitude of difference data between the biological signal data and the biological signal data noise-removed using the third filter, and the biological signal data noise-removed using the second filter and the first filter 3 is extracted as a feature value of the biological signal data, and the determination unit extracts the feature value extracted by the data feature value extraction unit.
- the degree of cognitive dysfunction of the subject is determined.
- the cognitive impairment determination system is a predetermined measurement measured when giving a task for activating the brain to a plurality of subjects whose cognitive impairment is known.
- a determination data generation device including a determination data generation unit that generates data used for determination of the cognitive dysfunction based on the extracted feature amount, and the cognitive dysfunction measured when the task is given
- a feature amount extraction unit that extracts a feature amount of signal data, and a degree of the cognitive dysfunction is unknown based on the feature amount extracted by the feature amount extraction unit and the data generated by the determination data generation device
- a cognitive impairment determining device including a determining unit that determines the degree of cognitive impairment of the subject.
- the program according to the ninth aspect of the present invention is a program for acquiring biological signal data in a predetermined brain region of a subject measured when a computer is given a task for activating the brain.
- a discriminating unit that discriminates the degree of the cognitive dysfunction of the subject based on the data used for the test.
- a biological signal of a plurality of regions of the brain of a subject who is executing a cognitive task is acquired, and a feature amount of the biological signal is extracted, and this feature amount is obtained in advance.
- fNIRS functional near-infrared spectroscopy
- fNIRS is a known technique for measuring hemoglobin flow in the brain using near-infrared light, is non-invasive and has little restraint on the subject (hereinafter also referred to as a subject), and selects the measurement environment. A relatively simple measurement is possible.
- cerebral blood flow data during execution of a cognitive task is measured using such functional near infrared spectroscopy, and based on the measured cerebral blood flow data, normal (NC), mild recognition
- MCI functional impairment
- AD Alzheimer type dementia
- the cognitive impairment determination device 10 includes fNIRS measurement devices 20 and 20 a that measure cerebral blood flow data during execution of a cognitive task using functional near-infrared spectroscopy.
- a learning device 31 a data storage device 32, a discrimination device 33, and a display device 40 for displaying the processing results of the discrimination device 33, which are constituted by a computer that executes the cognitive impairment determination processing according to the present invention. Yes.
- the learning device 31, the data storage device 32, and the discriminating device 33 each have a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), and HDD (Hard Disk Drive) not shown. Prepare.
- the HDD stores a program used when the CPU executes the cognitive impairment determination process according to the present invention.
- the learning device 31 includes a feature selection unit 31a, a learning unit 31b, a clinical database 31d, and a model storage unit 31e as processing functions realized by executing a program.
- the data storage device 32 includes an original waveform signal acquisition unit 32a, a primitive analysis unit 32b, a feature amount extraction unit 32c, and a clinical database 32d as processing functions realized by executing a program.
- the discriminating apparatus 33 includes an original waveform signal acquisition unit 33a, a primitive analysis unit 33b, a feature amount extraction unit 33c, a Bayesian classifier 33d, and a model storage unit 33e as processing functions realized by executing a program.
- each of the data storage device 32 and the discrimination device 33 is configured to include original waveform signal acquisition units 32a and 33a, primitive analysis units 32b and 33b, and feature amount extraction units 32c and 33c.
- original waveform signal acquisition units 32a and 33a By configuring each of the data storage device 32 and the determination device 33 in the same computer, any of the original waveform signal acquisition units 32a and 33a, any of the primitive analysis units 32b and 33b, and a feature amount extraction unit 32c. , 33c may be shared.
- the fNIRS measuring devices 20 and 20a measure the cerebral blood flow data of the subject as a biological signal.
- the increase in cerebral blood flow is, for example, “Villringer, A. and Firnafl, U .: Coupling of brain activity and cerebral blood flow: basis of functional nuroimaging, Cerebrovasc. Brain Metab. Rev., Vol. 7, pp. 240-276 (1995) "reflects the activation of neural activity in the brain region, and changes in cerebral blood flow are measured by measuring changes in oxygenated hemoglobin (oxy-Hb) in the blood. Can be captured. Therefore, a change in the amount of oxy-Hb measured by the fNIRS measurement devices 20 and 20a can be regarded as an index of brain activity.
- multi-channel fNIRS measurement devices 20 and 20a are used for measuring brain activity of elderly people who are executing cognitive tasks.
- a near infrared light brain functional imaging device FOIRE-3000 manufactured by Shimadzu Corporation (R) was used.
- the cerebral blood flow data of the subject is measured at a plurality of locations as shown in FIGS.
- a white circle portion is a light emitter (illuminator)
- a black circle portion is a detector.
- the fNIRS measuring devices 20 and 20a measure the cerebral blood flow in the 22 channel portions of 1 to 22 in the right region Fr, the central region Fc, and the left region Fl in the prefrontal cortex. Further, as shown in FIG. 3, the fNIRS measuring devices 20 and 20a measure the cerebral blood flow in 10 channel portions of 1 to 10 in the front region Rf and the rear region Rr in the right temporal lobe. Further, as shown in FIG. 4, the fNIRS measurement devices 20 and 20a measure cerebral blood flow in the 10 channel portions of 1 to 10 in the front region Lf and the rear region Lr in the left temporal lobe. As described above, the fNIRS measurement devices 20 and 20a measure the cerebral blood flow in a total of 42 channel portions.
- the probe set in the prefrontal cortex is placed horizontally so that the center of the bottom overlaps Fpz, and the left and right temporal lobes and parietal lobes
- the probe set was arranged based on the positions of P3 and T3 (P4 and T4).
- the discriminating device 33 takes in the cerebral blood flow data of a plurality of parts measured from the subject by the fNIRS measuring device 20 by the original waveform signal acquisition unit 33a. Based on the acquired cerebral blood flow data of a plurality of parts, the discriminating device 33 acquires cerebral blood flow data of a plurality of regions obtained by dividing the plurality of parts of the brain into a plurality by the primitive analysis unit 33b.
- the discrimination device 33 extracts the feature amount of the obtained cerebral blood flow data by the feature extraction unit 33c.
- determination apparatus 33 uses the model (model memory
- the discrimination result is output from the discrimination device 33 to the display device 40 and displayed on the display device 40.
- the learning device 31 stores the cerebral blood flow data stored in advance in the data storage device 32 in a plurality of parts of the brain during the cognitive task of the subject who knows whether or not the cognitive function is impaired.
- storage parts 31e and 33e) used for determination of the above-mentioned cognitive dysfunction in the discrimination device 33 is constructed
- the data storage device 32 uses the original waveform signal acquisition unit 32a to obtain fNIRS from the brain blood flow data of a plurality of parts of the brain that are executing the cognitive task of the subject whose cognitive function is known or not. Acquired from the measurement device 20a and collects and accumulates clinical diagnosis results of the subject inputted from an input device (not shown).
- the data storage device 32 uses the primitive analysis unit 32b to acquire cerebral blood flow data of a plurality of regions obtained by dividing a plurality of brain regions into a plurality of regions based on the accumulated cerebral blood flow data of the plurality of regions. Next, the data storage device 32 extracts the feature amount of the obtained cerebral blood flow data by the feature extraction unit 32c.
- the data storage device 32 performs these processes on a plurality of subjects whose cognitive function is known or not, and if so, obtains cerebral blood flow data feature quantities of the plurality of subjects. , Each of them is associated and stored in the clinical database 32d.
- the learning device 31 accumulates the same information as the information accumulated in the clinical database 32d by the clinical database 31d. Further, the learning device 31 uses the feature selection unit 31a to select a feature amount used for determination from the feature amounts obtained in the clinical database 31d in this way. And the learning apparatus 31 builds the model for discriminating cognitive dysfunction by the learning part 31b based on this selected feature-value and the extracted feature-value.
- Table 1 shows a breakdown of clinical diagnosis groups and age composition of subjects.
- the numbers in parentheses in Table 1 indicate the numbers of NC (healthy) group, MCI (mild cognitive impairment) group, and AD (Alzheimer type dementia) group, respectively.
- the MCI group is intended for patients whose “CDR (Clinical Dementia Rating)” in the “clinical dementia evaluation method” is equivalent to 0.5
- the AD group is intended for patients equivalent to CDR1. .
- CDR Clinical Dementia Rating
- behavior observation scales observation formulas
- 6 items of the care situation are evaluated in 5 levels.
- subjects with CDR2 or higher who have moderate or severe dementia were excluded from the target group.
- the attitude of the subjects was comprehensively evaluated from the observations by the operators who attended the task execution and the response contents of the tasks, and subjects who had obvious problems in the performance of the cognitive task itself were also excluded from the target group.
- the block design problem shown in FIG. 5 is designed, and simultaneous voice / fNIRS measurement is performed. It was.
- the subject's birthplace and boyhood conversation and the Hasegawa-style test were conducted, and in the latter 12 minutes, the recollection method (1. listening, 2. listening). Talking, 3. Watching, and working memory tasks (1. category recall, 2. reading span test, 3. face recall) were performed.
- the time of one task was set to 60 seconds so that the task could be concentrated, and a one-point gaze break (rest) of 60 seconds was taken before and after each cognitive task.
- the measurer sits on the subject (subject) in front of the task presentation device (display) and performs fNIRS measurement on the head of the subject (subject). Probe (or electrode for measuring EEG / Electroencephalogram). Then, the measurer presents a cognitive task from the display and a side speaker to the person to be measured (subject).
- the measurement subject executes the task in accordance with instructions from the display and the speaker, and the measurer measures the brain activity state during execution of the task from the fNIRS measuring device (or electroencephalogram measuring device or the like).
- the fNIRS measuring device or electroencephalogram measuring device or the like.
- the fNIRS measuring devices 20 and 20a are used, and this fNIRS measuring device includes oxy-Hb (oxygenated hemoglobin amount), deoxy-Hb (deoxygenated hemoglobin amount), and total-Hb (total amount). Hemoglobin amount) is measured.
- oxy-Hb oxygenated hemoglobin amount
- deoxy-Hb deoxygenated hemoglobin amount
- total-Hb total amount
- Hemoglobin amount is measured.
- an example using an oxy-Hb measurement signal is shown.
- NC three groups (NC, NC) of all channels (except 33CH and 41CH) using the fNIRS data (oxy-Hb) during execution of the task of the working memory task 1 “category recall” are used.
- FIG. 7 to FIG. 9 show examples in which channels that have been confirmed to have a significant difference in the test are mapped with 16 gradations based on the t-value.
- the healthy group is significantly activated as compared with the disease group (Fr, Fc, and Fl regions shown in FIG. 2 in the left diagrams of FIGS. 7 and 8).
- the cerebral blood flow in the left and right temporal lobes was also confirmed to be significantly activated in the healthy group compared to the disease group (Rf shown in FIGS. 3 and 4 in the middle right diagrams of FIGS. 7 and 8). , Rr, Lf, and Lr regions).
- the MCI group which is mildly cognitively impaired, slightly activates these cerebral blood flow compared to the AD group.
- FIG. 7 shows channels in which a significant difference was confirmed between the healthy (NC) group and the mild cognitive impairment (MCI) group.
- FIG. 8 shows a channel in which a significant difference was confirmed between a healthy (NC) group and an Alzheimer type dementia (AD) group.
- FIG. 9 shows a channel in which a significant difference was confirmed between the mild cognitive impairment (MCI) group and the Alzheimer's dementia (AD) group.
- screening for dementia is a process in which the health of cognitive function is first judged, and if there is a suspicion, whether it is mild cognitive impairment or dementia depending on the degree.
- the Bayesian classifier 33d includes a Bayesian classifier (1) 33d ′ and a Bayesian classifier (1) 33d ′′.
- the primitive analysis units 32b and 33b perform primitive analysis for each channel (CH1 to CH42) on the original waveform of the fNIRS measurement signal input by the original waveform signal acquisition units 32a and 33a.
- noise is removed by applying a low-pass filter and a difference filter, and the averaging of channels in the region of interest is performed.
- the primitive analysis units 32b and 33b first smooth the fNIRS signal of each channel through three low-pass filters F1 to F3 (both Butterworth characteristics, order 5), as shown in FIG. Turn into.
- the cutoff frequency of the low-pass filter F1 is 1.92 Hz
- the cutoff frequency of the low-pass filter F2 is 0.96 Hz
- the cutoff frequency of the low-pass filter F3 is 0.48 Hz.
- the primitive analysis units 32b and 33b add two difference data to these three smoothed signals to generate five fNIRS time-series signals per channel.
- the five fNIRS time series signals 1201 to 1205 shown in FIG. 12 are as follows.
- the fNIRS time series signal 1201 is a signal from which noise mainly due to ambient light has been removed by the low-pass filter F1 (cutoff frequency 1.92 Hz).
- the fNIRS time series signal 1202 is a signal obtained by extracting a fluctuation component (background noise) due to a pulse wave or blood pressure by a low-pass filter F2 (cutoff frequency 0.96 Hz).
- the fNIRS time series signal 1203 is a signal from which noise due to movements such as forehead opening / closing, eye movement, and neck flexion is mainly removed by a low-pass filter F3 (cutoff frequency 0.48 Hz).
- the fNIRS time series signal 1204 is a signal series obtained by subtracting the fNIRS time series signal 1203 from the fNIRS time series signal 1201 and is a signal focusing on fluctuation.
- the fNIRS time series signal 1205 is a signal series obtained by subtracting the fNIRS time series signal 1203 from the fNIRS time series signal 1202 and is a signal focusing on fluctuation.
- the primitive analysis units 32b and 33b divide the measurement brain region into the following seven regions, and add and average the fNIRS time series signals in each region. Specifically, the primitive analysis units 32b and 33b use the seven regions of the head (prefrontal cortex: three regions, left and right temporal lobes) as the addition average values Fr, Fc, Fl, Rf, Rr, Lf, and Lr in FIG. : For the channels in each of the two areas, the above five series signals are averaged (Averaging).
- the addition average value Fr is obtained by averaging the above five series signals for the seven channels on the right side of the prefrontal cortex (channels 1, 5, 6, 10, 14, 15, 19).
- the addition average value Fc is obtained by adding and averaging the above five series signals for the central 8 channels (channels 2, 3, 7, 11, 12, 16, 20, 21) of the prefrontal cortex.
- the addition average value Fl is obtained by averaging the above five series signals for the seven channels on the left side of the prefrontal cortex (channels 4, 8, 9, 13, 17, 18, 22).
- the addition average value Rf is an average of the above five series signals for the five front channels (channels 23, 24, 26, 27, 30) of the right parietal lobe.
- the addition average value Rr is an average of the above five series signals for the five channels (channels 25, 28, 29, 31, 32) in the right temporal lobe.
- the addition average value Lf is the average of the above five series signals for the five front channels (channels 33, 34, 36, 37, and 40) of the left parietal lobe.
- the addition average value Lr is an average of the above five series signals for the five channels behind the left temporal lobe (channels 35, 38, 39, 41, 42).
- the primitive analysis units 32b and 33b input the value obtained by adding and averaging the five series signals obtained for each region to the feature amount extraction units 32c and 33c.
- the feature quantity extraction units 32c and 33c perform feature extraction for calculating the following 11 feature quantities from the five sequences for each region obtained by the primitive analysis units 32b and 33b. Specifically, the feature quantity extraction units 32c and 33c calculate the feature quantities shown in Table 2 from the prepared fNIRS data as the feature quantities representing the features of cerebral blood flow fluctuations. Eleven fNIRS feature values are calculated.
- filter 1 F1
- filter 3 F3
- filter 1-3 F1-3
- filter 2-3 F2-3
- Filter 1 (F1) is a low-pass filter having a cutoff frequency of 1.92 Hz.
- the signal that has passed through the filter 1 (F1) is mainly free from noise due to ambient light, and has the widest frequency component in the five signal sequences.
- the filter 1 (F1) includes the frequency component of the filter 2 (F2).
- Filter 2 (F2) is a low-pass filter having a cutoff frequency of 0.96 Hz.
- the signal that has passed through the filter 2 (F2) is obtained by extracting a fluctuation component (background noise) due to a pulse wave or blood pressure, and is a biological signal component of the autonomic nervous system that is not directly related to brain activity. do not do.
- Filter 3 is a low-pass filter having a cutoff frequency of 0.48 Hz.
- the signal that has passed through the filter 3 (F3) is the narrowest frequency component in the five signal sequences, with the noise mainly due to movements such as forehead opening / closing, eye movements, and forward neck flexion being removed. Is considered relatively strong.
- the filter 1-3 is a signal series obtained by subtracting the signal that has passed through the filter 3 (F3) from the signal that has passed through the filter 1 (F1).
- F1-3 is a signal series obtained by subtracting the signal that has passed through the filter 3 (F3) from the signal that has passed through the filter 1 (F1).
- the filter 2-3 (F2-3) is a signal series obtained by subtracting a signal that has passed through the filter 3 (F3) from a signal that has passed through the filter 1 (F2).
- the average value (mean) of the amplitude as the fNIRS feature amount represents the average level of brain activity (activation).
- the fundamental frequency (f0) as the fNIRS feature amount represents the number of vibrations (peak) of brain activity (activation).
- the frequency centroid (fc) as the fNIRS feature amount represents the number of vibrations (centroid) of brain activity (activation).
- the maximum value (max) of the amplitude as the fNIRS feature amount represents the maximum level of brain activity (activation).
- the minimum value (min) of the amplitude as the fNIRS feature amount represents the minimum level of brain activity (activation).
- the variance value (var) of the amplitude as the fNIRS feature amount represents a change in brain activity (activation).
- the average value (mean) of the amplitude as the fNIRS feature amount represents the average level of brain activity (activation).
- the slope (gr) of the approximate straight line as the fNIRS feature amount represents the tendency of brain activity (activation).
- the variance value (var) of the amplitude as the fNIRS feature amount represents a change in brain activity (activation).
- the feature amount extraction units 32c and 33c perform the above processing and store the numerical values (77 dimensions) converted into feature amounts in the explanatory variables.
- the data storage device 32 stores data in which the clinical diagnosis result (NC: healthy, MCI: mild cognitive dysfunction, AD: Alzheimer type dementia) is given as a target attribute in the clinical database 32d.
- the learning device 31 accumulates the data stored in the clinical database 32d in the above-described processing in the clinical database 31d, and constructs a model using this data (Learning).
- the learning device 31 uses the data accumulated in advance in the clinical database 32c, that is, data for 50 people (NC: 21 people, MCI: 19 people, AD: 10 people), and cognitive dysfunction A model for estimating the presence / absence and degree of discrimination is constructed.
- the learning device 31 constructs a Bayesian classifier using 77 fNIRS feature values extracted from the fNIRS measurement data of the subject as explanatory variables and the clinical diagnosis group as a target attribute.
- the classifier model is Naive-Bayes Classifier.
- the learning device 31 has a model for the discriminator NB NC / CI as a first stage for estimating whether or not the cognitive function is impaired, and a second stage for estimating the degree when the disorder is estimated.
- the discriminator NB MCI / AD model and two discriminator models are constructed and stored in the model storage unit 31e.
- the learning device 31 performs feature selection in advance of model construction by the feature selection unit 31a.
- fNIRS features that are highly causally related to the cognitive impairment of the elderly have not been identified, and there is no theory or prior knowledge useful for feature selection.
- calculating all combinations of extracted feature amounts increases the calculation cost.
- the feature selection unit 31a is generally used frequently as described in, for example, “Draper, N. and Smith, H .: Applied Regression Analysis (3rd edition), John Wiley & Sons (1998)”. Feature selection is performed using the forward stepwise method as the sequential selection method.
- the average value of the estimated correct answer rates for each of the two groups was used.
- the feature selection unit 31a includes an NC group And a sub-optimal combination of feature quantities for discriminating between the two groups of the CI group (MCI + AD group).
- the feature selection unit 31a uses the MCI group to automatically select a feature amount useful as a discrimination criterion for discriminating the degree of cognitive impairment (mild, dementia) in the Bayesian classifier (2) 33d ′′. A sub-optimal combination of feature quantities is obtained for discriminating AD groups.
- Table 3 shows an example in which two features are selected as useful features for discrimination criteria for discriminating between healthy individuals and cognitive impairments in the Bayesian classifier (1) 33d '.
- Table 3 shows an example in which three features are selected as useful feature amounts as discrimination criteria for discriminating the degree of cognitive impairment (mild, dementia) in the Bayesian classifier (2) 33d ′′.
- the filter 3 (F3) in the region Fr (the right front 7 channel) is passed.
- the maximum value (max) of the amplitude of the signal and the frequency centroid (fc) of the signal that has passed through the filter 1 (F1) in the region Lr (5 channels behind the left temporal lobe) are used.
- Multi-modal imaging predicts memory performance in normal aging and cognitive decline, Neurobiology of Aging, Vol. 31, No. 107,1 As described in), mainly in Alzheimer type dementia, a decrease in blood flow in the posterior cingulate cerebral region has been confirmed, and attention is paid to the fact that the function of working memory decreases due to impaired cognitive function This is because. Actually, it has been confirmed from the discrimination result in the present embodiment that when the blood flow in the prefrontal cortex is reduced and the activation period of the temporal posterior region is extended, it is discriminated as a disease group of cognitive impairment.
- the filter 1 in the region Fr (center 8 channels in the frontal area) is used as a feature amount useful for the criterion for discriminating the degree of cognitive impairment (mild, dementia) in the Bayesian classifier (2) 33d ′′. , 3 (F1, F3), the variance value (var) of the difference signal amplitude of each signal, and the average value of the amplitude of the signal that has passed through the filter 1 (F1) in the region Lf (5 channels ahead of the left parietal lobe) (Mean) and the variance value (var) of the difference signal amplitude of each signal that has passed through the filters 1 and 3 (F1 and F3) in the region Lf (5 channels in front of the left parietal lobe).
- the feature selection part 31a is as two feature-values used when discriminating a healthy person and cognitive impairment by a Bayesian classifier (1) 33d '.
- the frequency centroid (fc) of the passed signal is selected.
- the feature selection unit 31a uses the region Fr (the central portion 8 of the frontal whole area) as three feature amounts used when discriminating the degree of cognitive dysfunction (mild, dementia) by the Bayesian classifier (2) 33d ′′.
- Average value (mean) and variance value (var) of differential signal amplitude of each signal that has passed through filters 1 and 3 (F1 and F3) in region Lf (5 channels ahead of left parietal lobe) is doing.
- the learning device 31 builds a model for discriminating cognitive dysfunction in the Bayesian classifier 33d from the feature amount selected by the feature selection unit 31a and the feature amount stored in the clinical database 31d. And stored in the model storage unit 31e.
- the learning device 31 discriminates between the feature amounts and between the feature amounts using the clinical database 31d and the feature amount list shown in Table 3 narrowed down by the feature selection unit 31a by the learning unit 31b. Calculate probabilistic dependency with the goal. Thereby, the learning device 31 constructs the network structure and parameters (conditional probability distribution) of the classification function in the Bayesian classifier 33d and stores them in the model storage unit 31e.
- the discriminating device 33 discriminates whether or not the subject has a disorder in cognitive function using the model constructed by the learning device 31 in this way.
- a process for determining whether or not the subject has a disorder in the cognitive function by the determination device 33 will be described.
- the discrimination device 33 discriminates the cognitive function level of the person through the following processing from the cerebral blood flow data being executed.
- the discriminating device 33 first uses the original waveform signal acquisition unit 33 a provided in the discriminating device 33 to obtain the cerebral blood flow data of a plurality of parts measured by the fNIRS measuring device 20. take in.
- the primitive analysis unit 33b performs an analysis process on the captured cerebral blood flow data at a plurality of sites.
- the feature extraction part 33c calculates a feature-value from five series for every area
- the Bayesian classifier 33d discriminates NC, MCI, and AD for the subject by using a model that is constructed in advance by the learning device 31 and is used to determine the cognitive impairment accumulated in the model storage unit 33e.
- the discrimination device 33 first discriminates whether it is normal (NC) or cognitive dysfunction (CI) using a Bayesian classifier (1) 33d ′. To do.
- the Bayesian classifier (1) 33d sets a calculated value corresponding to the selected feature amount in the node, and executes NC / CI classification processing. As the output, probability values classified into the NC group and the CI group are obtained.
- the discriminating device 33 uses the Bayesian classifier (2) 33d ′′ to determine whether it is mild cognitive impairment (MCI) or Alzheimer's. It is discriminated whether it is type dementia (AD), and the degree of cognitive dysfunction is estimated.
- MCI mild cognitive impairment
- AD type dementia
- the Bayesian classifier (2) 33d ′′ sets the calculated value corresponding to the selected feature amount in the node, and performs MCI / AD classification processing.
- MCI mild cognitive impairment
- AD Alzheimer type dementia
- Table 3 shows a list of fNIRS feature values adopted by the Bayesian classifier (1) 33d 'and the Bayesian classifier (2) 33d ".
- Table 4 shows the cross-validation result of an experiment in which 50 subjects were subjected to discrimination processing by the cognitive impairment judging device according to the present embodiment.
- the estimated correct answer rate of MCI is 73.7%, and it can be said that the performance of the cognitive impairment determining apparatus according to the present embodiment is acceptable.
- the cognitive impairment determination device it is also easy to accept that 80% of the five erroneously determined are determined by the disease side (AD).
- the computer-readable storage medium for storing the program is a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a storage device such as a hard disk built in the computer system.
- FIG. 13 shows an example of processing operation by the data storage device 32.
- the data storage device 32 acquires fNIRS measurement data by the function of the original waveform signal acquisition unit 32a.
- step 1302 the data storage device 32 performs primitive analysis processing for filtering the fNIRS measurement data by the function of the primitive analysis unit 32b.
- step 1303 the data storage device 32 performs a feature amount extraction process on the fNIRS measurement data subjected to the primitive analysis process by the function of the feature amount extraction unit 32c.
- step 1304 the data storage device 32 stores the feature quantity for the fNIRS measurement data extracted by the function of the feature quantity extraction unit 32c in the clinical database 32d.
- FIG. 14 shows an example of the processing operation of the learning device 31.
- the learning device 31 uses the function of the feature selection unit 31a to select from the feature amounts for the fNIRS measurement data stored in the clinical database 31d. For example, the feature amount shown in Table 3 is selected as a discrimination criterion.
- step 1402 the learning device 31 extracts and lists the feature quantities selected as the discrimination criterion by the function of the feature selection unit 31a from the clinical database 31d, and lists them in step 1403 by the learning unit 31b.
- the network structure of the classification function and the model of the parameter are constructed and stored in the model storage unit 31e.
- FIG. 15 shows an example of the processing operation of the discriminating device 33.
- the discriminating device 33 acquires fNIRS measurement data by the function of the original waveform signal acquisition unit 33a.
- step 1502 the discriminating device 33 performs primitive analysis processing for performing filtering processing on the fNIRS measurement data by the function of the primitive analysis unit 33b.
- step 1503 the discriminating apparatus 33 performs a feature amount extraction process on the fNIRS measurement data subjected to the primitive analysis process by the function of the feature amount extraction unit 33c.
- step 1504 the discriminating device 33 uses the function of the Bayesian classifier 33d to extract the fNIRS measurement extracted by the function of the feature amount extraction unit 33c using the data copied and stored in the model storage unit 33e from the model storage unit 31e. The diagnosis result corresponding to the feature amount of the data is determined.
- the cognitive dysfunction determination device 10 acquires the cerebral blood flow data as biological signals of a plurality of regions of the brain of the subject who is executing the cognitive task. Whether or not the subject's cognitive function is impaired based on the extracted feature amount and the data used for the determination of cognitive impairment prepared in advance. Determine.
- the cognitive dysfunction discriminating apparatus 10 uses data used for the determination of cognitive dysfunction as biosignals of a plurality of regions of the brain that are executing cognitive tasks of a plurality of subjects whose cognitive functions are known in advance.
- the feature amount is extracted and is generated based on the extracted feature amount.
- the cognitive dysfunction discriminating device 10 selects a feature quantity used for the determination from the extracted feature quantities, and based on the selected feature quantity and the extracted feature quantity, the cognitive dysfunction as data used for the determination. Build a model for discrimination.
- the cognitive dysfunction discriminating apparatus 10 acquires biosignals of a plurality of regions of the brain of a subject who is executing a cognitive task, extracts feature values of the biosignals, Based on the data used for the determination of cognitive dysfunction obtained in advance, it is determined whether or not there is a disorder in the cognitive function of the subject, thereby enabling early screening for brain function.
- an example of constructing a model for discriminating cognitive dysfunction in the cognitive dysfunction discriminating apparatus has been shown.
- an apparatus (learning apparatus 31) that constructs a model for discriminating cognitive dysfunction is shown.
- the data storage device 32) may be installed separately from the cognitive impairment determination device.
- a cognitive impairment determination system may be configured.
- the brain blood flow data obtained by the fNIRS measuring device is used as the brain biological signal.
- an electroencephalogram obtained by an electroencephalographic measuring device or the like may be used.
- the fNIRS measuring instrument manufactured by Shimadzu Corporation (R) is used, but not limited thereto, other NIRS measuring instruments may be used.
- 50 elderly people aged 64 to 92 are collectively used as subjects, but it is also possible to classify subjects into a plurality of groups in advance and determine the risk of dementia.
- cerebral blood flow data collected from an elderly person is classified in advance into a plurality of groups based on the similarity. Then, by calculating the weight based on the similarity of the distribution between the data of the unknown discrimination target and these groups, a weighted distribution suitable for discrimination of the discrimination target (individual difference adaptive distribution) is simulated. A calculation method is used to calculate and execute discriminant calculation on this weighted distribution. This makes it possible to determine the degree of dementia risk adapted to individual differences in cerebral blood flow data of elderly people.
- the above-mentioned plural groups generally take a means of classifying into an appropriate number of groups based on the similarity of the collected cerebral blood flow data. It is also possible to absorb gender and age differences by fixing to several groups according to age (age).
- the primitive analysis units 32b and 33b divide the measurement brain region into seven regions (frontal cortex: 3 regions, left and right temporal lobes: 2 regions each), and fNIRS time series signals in each region. Are averaged. However, it is recognized from within each region by applying blind source separation techniques such as principal component analysis (PCA), independent component analysis (ICA), singular value decomposition (SVD), and non-negative matrix factorization (NMF). It is also possible to separate and extract a signal that is effective for determining a functional failure. By using such a calculation technique, higher performance is expected.
- PCA principal component analysis
- ICA independent component analysis
- SVD singular value decomposition
- NMF non-negative matrix factorization
- the learning device 31 performs feature selection using the forward stepwise method as a commonly used sequential selection method in the feature quantity selection processing operation by the feature selection unit 31a.
- the learning device 31 includes, for example, a sequential selection method such as a variable increase method, a variable decrease method, and a variable increase / decrease method, an EM algorithm, a genetic algorithm (GA), particle swarm optimization (Particle Swarm Optimization, PSO), and Feature selection may be performed using a simultaneous selection method such as a method using evolutionary computation such as Evolutionarily Stable Strategy (ESS) or Differential evolution (DE).
- ESS Evolutionarily Stable Strategy
- DE Differential evolution
- the discriminating device 33 employs Naive-BayesBaClassifier as a classifier model in order to discriminate cognitive dysfunction, but is not limited to this.
- classification type estimation methods such as Bayesian network, canonical discriminant analysis, linear discriminant analysis, neural network, naive Bayes method, and support vector machine (SVM), multiple regression analysis, ridge regression, support vector regression (SV regression)
- numerical estimation methods such as kernel regression analysis may be used.
- the risk of dementia is determined based on which of the three groups of healthy (NC), suspected dementia (MCI), and dementia (AD) from speech data of elderly people. Determine.
- a numerical value equivalent to the score (0 to 30) of the cognitive function test such as a Hasegawa score is output, and the degree of risk of dementia is determined by the level of the numerical value.
- a computer-readable recording medium is a data acquisition unit that acquires biological signal data in a predetermined brain region of a subject measured when the computer is given a task for activating the brain. And a feature amount extraction unit that extracts a feature amount of the biological signal data acquired by the data acquisition unit, a feature amount extracted by the feature amount extraction unit, and a cognitive impairment determined in advance Based on the data, a program for functioning as a determination unit that determines the degree of cognitive impairment of the subject is stored.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Neurology (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Neurosurgery (AREA)
- Psychology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Hematology (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Cardiology (AREA)
- Evolutionary Computation (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
Claims (9)
- 脳を活動させるための課題を与えているときに測定された被験者の予め定められた脳部位における生体信号データを取得するデータ取得部と、
前記データ取得部によって取得された生体信号データの特徴量を抽出する特徴量抽出部と、
前記特徴量抽出部によって抽出された特徴量と、予め求めておいた認知機能障害の判定に用いるデータとに基づいて、前記被験者の認知機能障害の程度を判別する判別部と、
を備える認知機能障害判別装置。 - 前記生体信号データは、前記予め定められた脳部位における血流を計測した脳血流データである請求項1記載の認知機能障害判別装置。
- 前記生体信号データは、前記予め定められた脳部位としての前頭前野、左側頭葉、右側頭葉、左頭頂葉、及び右頭頂葉の各々においてNIRS装置によりヘモグロビン流量を測定した脳血流データである請求項1記載の認知機能障害判別装置。
- 前記生体信号データは、前記予め定められた脳部位としての前頭前野における右領域、中央領域、及び左領域、前記予め定められた脳部位としての左頭頂葉における所定領域、及び左側頭葉における所定領域、並びに前記予め定められた脳部位としての右頭頂葉における所定領域、及び右側頭葉における所定領域、の各々の領域においてNIRS装置によりヘモグロビン流量を測定した脳血流データである請求項1記載の認知機能障害判別装置。
- 前記認知機能障害の程度が既知である複数の被験者に前記課題を与えているときに測定された前記生体信号データを取得する既知データ取得部と、
前記既知データ取得部によって取得された生体信号データの前記特徴量を抽出する既知データ特徴量抽出部と、
前記既知データ特徴量抽出部によって抽出された特徴量に基づいて、前記認知機能障害の判定に用いるデータを生成する判定データ生成部と、
を更に備える請求項1から請求項4のいずれか1項に記載の認知機能障害判別装置。 - 前記判定データ生成部は、
前記既知データ特徴量抽出部によって抽出された特徴量の中から、前記認知機能障害の判定に用いる特徴量を選択する選択部と、
前記選択部によって選択された特徴量と当該特徴量が抽出された被験者の前記認知機能障害の程度とを学習データとして用いて、前記判別部が前記特徴量に対応する前記認知機能障害の程度を判定するためのモデルを構築する学習部と、
を備える請求項5に記載の認知機能障害判別装置。 - 複数の低域通過フィルタを用いて前記入力された生体信号データのノイズ除去を行なうプリミティブ解析部を備え、
前記複数の低域通過フィルタは、環境光によるノイズを含むノイズを除去するのに用いる第1のフィルタ、脳波及び血圧を含む変動成分を抽出するのに用いる第2のフィルタ、及び、顎開閉及び眼球運動を含む運動によるノイズを除去するのに用いる第3のフィルタを含み、
前記データ特徴量抽出部は、
前記プリミティブ解析部が、前記第1のフィルタを用いてノイズ除去した前記生体信号データにおける振幅の平均値、基本周波数、及び周波数重心と、前記第3のフィルタを用いてノイズ除去した前記生体信号データにおける振幅の最大値、振幅の最小値、振幅の分散値、振幅の平均値、基本周波数、及び近似直線の傾きと、前記第1のフィルタを用いてノイズ除去した前記生体信号データと前記第3のフィルタを用いてノイズ除去した前記生体信号データとの差分データの振幅の分散値、及び、前記第2のフィルタを用いてノイズ除去した前記生体信号データと前記第3のフィルタを用いてノイズ除去した前記生体信号データとの差分データの分散値を、前記生体信号データの特徴量として抽出し、
前記判別部は、前記データ特徴量抽出部によって抽出された特徴量を対象に前記被験者の認知機能障害の程度の判別を行なう、
請求項1乃至請求項6のいずれか1項に記載の認知機能障害判別装置。 - 認知機能障害の程度が既知である複数の被験者に脳を活動させるための課題を与えているときに測定された予め定められた脳部位における生体信号データを取得する既知データ取得部、
前記既知データ取得部によって取得された生体信号データの特徴量を抽出する既知データ特徴量抽出部、
及び、前記既知データ特徴量抽出部によって抽出された特徴量に基づいて、前記認知機能障害の判定に用いるデータを生成する判定データ生成部、を含む判定データ生成装置と、
前記課題を与えているときに測定された、前記認知機能障害の程度が未知である被験者の前記予め定められた脳部位における生体信号データを取得するデータ取得部、
前記データ取得部によって取得された生体信号データの特徴量を抽出する特徴量抽出部、
及び、前記特徴量抽出部によって抽出された特徴量と前記判定データ生成装置によって生成されたデータとに基づいて、前記認知機能障害の程度が未知である被験者の認知機能障害の程度を判別する判別部、を含む認知機能障害判別装置と、
を備える認知機能障害判別システム。 - コンピュータを、
脳を活動させるための課題を与えているときに測定された、被験者の予め定められた脳部位における生体信号データを取得するデータ取得部と、
前記データ取得部によって取得された生体信号データの特徴量を抽出する特徴量抽出部と、
前記特徴量抽出部で抽出された特徴量と、予め求めておいた認知機能障害の判定に用いるデータとに基づいて、前記被験者の認知機能障害の程度を判別する判別部と、
として機能させるためのプログラム。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2013518182A JP5959016B2 (ja) | 2011-05-31 | 2012-05-31 | 認知機能障害判別装置、認知機能障害判別システム、およびプログラム |
| US14/122,786 US9131889B2 (en) | 2011-05-31 | 2012-05-31 | Cognitive impairment determination apparatus, cognitive impairment determination system and program |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2011-121241 | 2011-05-31 | ||
| JP2011121241 | 2011-05-31 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2012165602A1 true WO2012165602A1 (ja) | 2012-12-06 |
Family
ID=47259453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2012/064237 Ceased WO2012165602A1 (ja) | 2011-05-31 | 2012-05-31 | 認知機能障害判別装置、認知機能障害判別システム、およびプログラム |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US9131889B2 (ja) |
| JP (1) | JP5959016B2 (ja) |
| WO (1) | WO2012165602A1 (ja) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014178323A1 (ja) * | 2013-05-01 | 2014-11-06 | 株式会社国際電気通信基礎技術研究所 | 脳活動解析装置、脳活動解析方法およびバイオマーカー装置 |
| JP2015047449A (ja) * | 2013-09-04 | 2015-03-16 | 株式会社ノエビア | マッサージ法の評価法 |
| JP2015061827A (ja) * | 2013-08-21 | 2015-04-02 | Shiodaライフサイエンス研究所株式会社 | 経鼻的脳機能調整剤及び脳神経疾患を評価するためのデータを提供する方法 |
| JP2015171499A (ja) * | 2014-03-12 | 2015-10-01 | サッポロビール株式会社 | 食感刺激評価方法 |
| CN105051647A (zh) * | 2013-03-15 | 2015-11-11 | 英特尔公司 | 基于生物物理信号的搜集时间和空间模式的大脑计算机接口(bci)系统 |
| WO2016038937A1 (ja) * | 2014-09-08 | 2016-03-17 | 国立大学法人大阪大学 | 精神疾患判定装置、及び、精神疾患判定方法 |
| JP2016106940A (ja) * | 2014-12-09 | 2016-06-20 | 株式会社Nttデータ・アイ | 脳疾患診断支援システム、脳疾患診断支援方法及びプログラム |
| JP2017006649A (ja) * | 2015-06-17 | 2017-01-12 | ゼロックス コーポレイションXerox Corporation | 被検体の映像からの呼吸パターンの判定 |
| KR20170050150A (ko) * | 2015-10-29 | 2017-05-11 | 서울대학교산학협력단 | 소아 청소년의 뇌 건강 상태 진단 방법 및 이를 수행하기 위한 장치 |
| JP2017189471A (ja) * | 2016-04-14 | 2017-10-19 | パナソニックIpマネジメント株式会社 | 生体信号計測システム |
| JP2018055333A (ja) * | 2016-09-28 | 2018-04-05 | 学校法人日本大学 | 認知症判定得点算出装置及びそのプログラム |
| WO2018168915A1 (ja) * | 2017-03-14 | 2018-09-20 | 学校法人日本大学 | 生体機能についての医学的検査の得点判定装置、及びプログラム |
| JP2019041754A (ja) * | 2017-08-31 | 2019-03-22 | 株式会社Nttドコモ | 予測装置及び予測方法 |
| JP2019063551A (ja) * | 2018-12-05 | 2019-04-25 | サッポロビール株式会社 | 食感刺激の嗜好性評価方法 |
| KR20190075899A (ko) * | 2016-08-03 | 2019-07-01 | 아킬리 인터랙티브 랩스 인크. | 컴퓨터화된 연상 엘리먼트를 포함하는 인지 플랫폼 |
| TWI665657B (zh) * | 2017-11-02 | 2019-07-11 | Panasonic Intellectual Property Management Co., Ltd. | 認知功能評估裝置、認知功能評估系統、認知功能評估方法及記錄媒體 |
| KR20200018626A (ko) | 2017-07-07 | 2020-02-19 | 가부시키가이샤 시마쓰세사쿠쇼 | 인지 기능 판정 방법 |
| CN110876626A (zh) * | 2019-11-22 | 2020-03-13 | 兰州大学 | 基于多导联脑电最优导联选择的抑郁检测系统 |
| JP2020127703A (ja) * | 2018-07-24 | 2020-08-27 | 日本テクトシステムズ株式会社 | 軽度の認知機能障害の推定システム及び軽度の認知機能障害の推定装置 |
| CN111588348A (zh) * | 2019-02-20 | 2020-08-28 | 株式会社岛津制作所 | 认知功能的指标化方法 |
| CN111588347A (zh) * | 2019-02-21 | 2020-08-28 | 株式会社岛津制作所 | 脑活动特征量的提取方法 |
| JP2020140724A (ja) * | 2020-05-07 | 2020-09-03 | ハルメク・ベンチャーズ株式会社 | 認知症判定得点算出装置及びそのプログラム |
| JPWO2020218013A1 (ja) * | 2019-04-25 | 2020-10-29 | ||
| US11304657B2 (en) | 2016-08-26 | 2022-04-19 | Akili Interactive Labs, Inc. | Cognitive platform coupled with a physiological component |
| JP2022528277A (ja) * | 2019-04-12 | 2022-06-09 | コリア アドヴァンスド インスティテュート オブ サイエンス アンド テクノロジー | マシンラーニングを利用して頭に関する生体情報を推定するための方法、システムおよび非一過性のコンピュータ読み取り可能な記録媒体 |
| WO2022191367A1 (ko) * | 2021-03-12 | 2022-09-15 | 주식회사 아이메디신 | 뇌파 데이터 분석을 통한 중증인지장애 환자 분류 방법, 서버 및 컴퓨터프로그램 |
| KR102492373B1 (ko) * | 2021-08-10 | 2023-01-27 | 주식회사 엔서 | 딥러닝 모델을 이용해 치매를 진단하는 치매 진단장치 |
| WO2023054643A1 (ja) * | 2021-09-30 | 2023-04-06 | ダイキン工業株式会社 | 不穏およびせん妄センシング装置並びに不穏およびせん妄センシング方法 |
| US11766209B2 (en) | 2017-08-28 | 2023-09-26 | Panasonic Intellectual Property Management Co., Ltd. | Cognitive function evaluation device, cognitive function evaluation system, and cognitive function evaluation method |
| WO2023214545A1 (ja) * | 2022-05-02 | 2023-11-09 | 国立大学法人大阪大学 | 認知機能評価システム |
| CN117243569A (zh) * | 2023-10-12 | 2023-12-19 | 国家康复辅具研究中心 | 一种基于多源信息融合的认知功能评估方法和系统 |
| US11918372B2 (en) | 2017-11-02 | 2024-03-05 | Panasonic Intellectual Property Management Co., Ltd. | Cognitive function evaluation system, method, and storage medium for dementia by analyzing voice of evaluatee for recognition, remembering or jugment capabilities |
| WO2024085282A1 (ko) * | 2022-10-20 | 2024-04-25 | (주)오비이랩 | 인지 기능 개선을 위한 개인 맞춤형 광자극을 제공하는 방법, 장치 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
| KR20240055980A (ko) * | 2022-10-20 | 2024-04-30 | (주)오비이랩 | 인지 기능 개선을 위한 개인 맞춤형 광자극을 제공하는 방법, 장치 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
| US12020427B2 (en) | 2017-10-03 | 2024-06-25 | Advanced Telecommunications Research Institute International | Differentiation device, differentiation method for depression symptoms, determination method for level of depression symptoms, stratification method for depression patients, determination method for effects of treatment of depression symptoms, and brain activity training device |
| CN119028583A (zh) * | 2024-08-12 | 2024-11-26 | 江苏省人民医院(南京医科大学第一附属医院) | 体外循环心脏手术患者神经认知障碍的预测数据处理方法 |
Families Citing this family (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9269046B2 (en) | 2012-01-18 | 2016-02-23 | Brainscope Company, Inc. | Method and device for multimodal neurological evaluation |
| US8792974B2 (en) | 2012-01-18 | 2014-07-29 | Brainscope Company, Inc. | Method and device for multimodal neurological evaluation |
| WO2015037089A1 (ja) * | 2013-09-11 | 2015-03-19 | 日立コンシューマエレクトロニクス株式会社 | 脳機能障害評価方法、脳機能障害評価装置およびそのプログラム |
| US9474481B2 (en) * | 2013-10-22 | 2016-10-25 | Mindstrong, LLC | Method and system for assessment of cognitive function based on electronic device usage |
| WO2015187401A1 (en) * | 2014-06-04 | 2015-12-10 | Neil Rothman | Method and device for multimodal neurological evaluation |
| KR101703547B1 (ko) * | 2015-04-09 | 2017-02-07 | 대한민국 | 기능적 근적외선 분광법의 뇌활성도 측정에 따른 유효 채널 추출 방법 및 장치 |
| WO2017030539A1 (en) * | 2015-08-14 | 2017-02-23 | Hewlett-Packard Development Company, L.P. | Biometric data to facilitate learning |
| EP3381361B1 (en) * | 2015-11-24 | 2023-12-27 | Advanced Telecommunications Research Institute International | Brain activity analysis device, brain activity analysis method, program, and biomarker device |
| US10791981B2 (en) * | 2016-06-06 | 2020-10-06 | S Square Detect Medical Devices | Neuro attack prevention system, method, and apparatus |
| CN118714460A (zh) * | 2016-12-15 | 2024-09-27 | 松下知识产权经营株式会社 | 摄像装置、摄像方法及计算机程序产品 |
| CN110520041B (zh) | 2017-04-28 | 2022-07-05 | 麦克赛尔株式会社 | 脑波数据分析系统、信息处理终端、电子设备以及用于认知症检查的信息的呈现方法 |
| EP3669343B1 (en) * | 2017-08-15 | 2023-12-13 | Akili Interactive Labs, Inc. | Cognitive platform including computerized elements |
| KR102090671B1 (ko) * | 2017-09-15 | 2020-03-18 | 재단법인 대구경북과학기술원 | 다채널 fNIRS 신호에서 동잡음을 제거하는 방법 및 장치 |
| WO2019086555A1 (en) | 2017-10-31 | 2019-05-09 | Ge Healthcare Limited | Medical system for diagnosing cognitive disease pathology and/or outcome |
| KR102257291B1 (ko) * | 2018-09-14 | 2021-05-28 | 주식회사 아이메디신 | 인지 장애 판별 방법 및 컴퓨터 프로그램 |
| US12307455B2 (en) * | 2019-08-01 | 2025-05-20 | Panasonic Intellectual Property Management Co., Ltd. | Evaluation system, evaluation method, program, server device, and terminal device |
| WO2021034619A1 (en) * | 2019-08-16 | 2021-02-25 | The Regents Of The University Of California | Neurofeedback training to promote sharp wave ripples |
| CN110680282B (zh) * | 2019-10-09 | 2020-10-27 | 黑龙江洛唯智能科技有限公司 | 一种大脑暂时性异常态的检测方法、装置和系统 |
| US11464443B2 (en) * | 2019-11-26 | 2022-10-11 | The Chinese University Of Hong Kong | Methods based on an analysis of drawing behavior changes for cognitive dysfunction screening |
| CN110859616A (zh) * | 2019-12-12 | 2020-03-06 | 科大讯飞股份有限公司 | 一种对象的认知评估方法、装置、设备及存储介质 |
| CN114176605B (zh) * | 2021-12-16 | 2023-08-29 | 中国人民解放军火箭军工程大学 | 一种多通道脑电信号眼电伪迹自动去除方法及存储介质 |
| CN114420299B (zh) * | 2021-12-28 | 2025-10-28 | 中山大学中山眼科中心 | 基于眼动测试的认知功能筛查方法、系统、设备和介质 |
| CN116189668B (zh) * | 2023-04-24 | 2023-07-25 | 科大讯飞股份有限公司 | 语音分类、认知障碍检测方法、装置、设备及介质 |
| CN120319451B (zh) * | 2025-04-01 | 2025-10-10 | 夏文广 | 基于多任务范式融合下fNIRS数据的轻度认知障碍识别方法及系统 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003275191A (ja) * | 2002-03-26 | 2003-09-30 | Hitachi Medical Corp | 生体光計測装置 |
| WO2005025421A1 (ja) * | 2003-09-11 | 2005-03-24 | Hitachi Medical Corporation | 生体光計測装置 |
| WO2005096951A1 (ja) * | 2004-04-09 | 2005-10-20 | Hitachi Medical Corporation | 生体光計測装置 |
| WO2005120349A1 (ja) * | 2004-06-14 | 2005-12-22 | Hitachi Medical Corporation | 生体光計測装置、生体光計測方法およびプログラム |
| WO2006132313A1 (ja) * | 2005-06-09 | 2006-12-14 | Hitachi Medical Corporation | 疾患判定支援システム |
| WO2007144977A1 (ja) * | 2006-06-15 | 2007-12-21 | Hitachi Medical Corporation | 生体光計測装置 |
| WO2008142878A1 (ja) * | 2007-05-21 | 2008-11-27 | Hitachi Medical Corporation | 生体光計測装置 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4876207B2 (ja) | 2010-06-11 | 2012-02-15 | 国立大学法人 名古屋工業大学 | 認知機能障害危険度算出装置、認知機能障害危険度算出システム、及びプログラム |
-
2012
- 2012-05-31 JP JP2013518182A patent/JP5959016B2/ja not_active Expired - Fee Related
- 2012-05-31 US US14/122,786 patent/US9131889B2/en not_active Expired - Fee Related
- 2012-05-31 WO PCT/JP2012/064237 patent/WO2012165602A1/ja not_active Ceased
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003275191A (ja) * | 2002-03-26 | 2003-09-30 | Hitachi Medical Corp | 生体光計測装置 |
| WO2005025421A1 (ja) * | 2003-09-11 | 2005-03-24 | Hitachi Medical Corporation | 生体光計測装置 |
| WO2005096951A1 (ja) * | 2004-04-09 | 2005-10-20 | Hitachi Medical Corporation | 生体光計測装置 |
| WO2005120349A1 (ja) * | 2004-06-14 | 2005-12-22 | Hitachi Medical Corporation | 生体光計測装置、生体光計測方法およびプログラム |
| WO2006132313A1 (ja) * | 2005-06-09 | 2006-12-14 | Hitachi Medical Corporation | 疾患判定支援システム |
| WO2007144977A1 (ja) * | 2006-06-15 | 2007-12-21 | Hitachi Medical Corporation | 生体光計測装置 |
| WO2008142878A1 (ja) * | 2007-05-21 | 2008-11-27 | Hitachi Medical Corporation | 生体光計測装置 |
Cited By (66)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105051647A (zh) * | 2013-03-15 | 2015-11-11 | 英特尔公司 | 基于生物物理信号的搜集时间和空间模式的大脑计算机接口(bci)系统 |
| JP2016513319A (ja) * | 2013-03-15 | 2016-05-12 | インテル コーポレイション | 収集された生物物理的信号の時間的パターンおよび空間的パターンに基づく脳‐コンピューターインターフェース(bci)システム |
| US10357181B2 (en) | 2013-05-01 | 2019-07-23 | Advanced Telecommunications Research Institute International | Brain activity analyzing apparatus, brain activity analyzing method and biomarker apparatus |
| JP2015062817A (ja) * | 2013-05-01 | 2015-04-09 | 株式会社国際電気通信基礎技術研究所 | 脳活動解析装置、脳活動解析方法およびバイオマーカー装置 |
| JP5691086B1 (ja) * | 2013-05-01 | 2015-04-01 | 株式会社国際電気通信基礎技術研究所 | 脳活動解析装置、脳活動解析方法およびバイオマーカー装置 |
| CN105163659A (zh) * | 2013-05-01 | 2015-12-16 | 株式会社国际电气通信基础技术研究所 | 脑活动分析装置、脑活动分析方法以及生物标记物装置 |
| CN105163659B (zh) * | 2013-05-01 | 2018-10-23 | 株式会社国际电气通信基础技术研究所 | 脑活动分析装置、脑活动分析方法以及生物标记物装置 |
| WO2014178323A1 (ja) * | 2013-05-01 | 2014-11-06 | 株式会社国際電気通信基礎技術研究所 | 脳活動解析装置、脳活動解析方法およびバイオマーカー装置 |
| US12396652B2 (en) | 2013-05-01 | 2025-08-26 | Advanced Telecommunications Research Institute International | Brain activity analyzing apparatus, brain activity analyzing method and biomarker apparatus |
| JP2015061827A (ja) * | 2013-08-21 | 2015-04-02 | Shiodaライフサイエンス研究所株式会社 | 経鼻的脳機能調整剤及び脳神経疾患を評価するためのデータを提供する方法 |
| JP2019177140A (ja) * | 2013-08-21 | 2019-10-17 | Shiodaライフサイエンス株式会社 | 経鼻的脳機能調整剤及び脳神経疾患を評価するためのデータを提供する方法 |
| JP2015047449A (ja) * | 2013-09-04 | 2015-03-16 | 株式会社ノエビア | マッサージ法の評価法 |
| JP2015171499A (ja) * | 2014-03-12 | 2015-10-01 | サッポロビール株式会社 | 食感刺激評価方法 |
| WO2016038937A1 (ja) * | 2014-09-08 | 2016-03-17 | 国立大学法人大阪大学 | 精神疾患判定装置、及び、精神疾患判定方法 |
| JP2016054839A (ja) * | 2014-09-08 | 2016-04-21 | 国立大学法人京都大学 | 精神疾患判定装置、及び、精神疾患判定方法 |
| JP2016106940A (ja) * | 2014-12-09 | 2016-06-20 | 株式会社Nttデータ・アイ | 脳疾患診断支援システム、脳疾患診断支援方法及びプログラム |
| JP2017006649A (ja) * | 2015-06-17 | 2017-01-12 | ゼロックス コーポレイションXerox Corporation | 被検体の映像からの呼吸パターンの判定 |
| KR20170050150A (ko) * | 2015-10-29 | 2017-05-11 | 서울대학교산학협력단 | 소아 청소년의 뇌 건강 상태 진단 방법 및 이를 수행하기 위한 장치 |
| KR102461705B1 (ko) * | 2015-10-29 | 2022-11-01 | 서울대학교산학협력단 | 소아 청소년의 뇌 건강 상태에 대한 정보를 제공하는 방법 및 이를 수행하기 위한 장치 |
| JP2017189471A (ja) * | 2016-04-14 | 2017-10-19 | パナソニックIpマネジメント株式会社 | 生体信号計測システム |
| US11116452B2 (en) | 2016-04-14 | 2021-09-14 | Panasonic Intellectual Property Management Co., Ltd. | Biological signal measurement system |
| KR20190075899A (ko) * | 2016-08-03 | 2019-07-01 | 아킬리 인터랙티브 랩스 인크. | 컴퓨터화된 연상 엘리먼트를 포함하는 인지 플랫폼 |
| KR102369850B1 (ko) | 2016-08-03 | 2022-03-03 | 아킬리 인터랙티브 랩스 인크. | 컴퓨터화된 연상 엘리먼트를 포함하는 인지 플랫폼 |
| JP2019533215A (ja) * | 2016-08-03 | 2019-11-14 | アキリ・インタラクティヴ・ラブズ・インコーポレイテッド | コンピュータ化された喚起要素を含む認知プラットフォーム |
| JP7473338B2 (ja) | 2016-08-03 | 2024-04-23 | アキリ・インタラクティヴ・ラブズ・インコーポレイテッド | コンピュータ化された喚起要素を含む認知プラットフォーム |
| US11304657B2 (en) | 2016-08-26 | 2022-04-19 | Akili Interactive Labs, Inc. | Cognitive platform coupled with a physiological component |
| JP2018055333A (ja) * | 2016-09-28 | 2018-04-05 | 学校法人日本大学 | 認知症判定得点算出装置及びそのプログラム |
| JP2018149168A (ja) * | 2017-03-14 | 2018-09-27 | 学校法人日本大学 | 生体機能についての医学的検査の得点判定装置、及びプログラム |
| WO2018168915A1 (ja) * | 2017-03-14 | 2018-09-20 | 学校法人日本大学 | 生体機能についての医学的検査の得点判定装置、及びプログラム |
| US12263004B2 (en) | 2017-07-07 | 2025-04-01 | Shimadzu Corporation | Cognitive function determination method |
| KR20200018626A (ko) | 2017-07-07 | 2020-02-19 | 가부시키가이샤 시마쓰세사쿠쇼 | 인지 기능 판정 방법 |
| US11766209B2 (en) | 2017-08-28 | 2023-09-26 | Panasonic Intellectual Property Management Co., Ltd. | Cognitive function evaluation device, cognitive function evaluation system, and cognitive function evaluation method |
| JP2019041754A (ja) * | 2017-08-31 | 2019-03-22 | 株式会社Nttドコモ | 予測装置及び予測方法 |
| US12020427B2 (en) | 2017-10-03 | 2024-06-25 | Advanced Telecommunications Research Institute International | Differentiation device, differentiation method for depression symptoms, determination method for level of depression symptoms, stratification method for depression patients, determination method for effects of treatment of depression symptoms, and brain activity training device |
| TWI665657B (zh) * | 2017-11-02 | 2019-07-11 | Panasonic Intellectual Property Management Co., Ltd. | 認知功能評估裝置、認知功能評估系統、認知功能評估方法及記錄媒體 |
| US11918372B2 (en) | 2017-11-02 | 2024-03-05 | Panasonic Intellectual Property Management Co., Ltd. | Cognitive function evaluation system, method, and storage medium for dementia by analyzing voice of evaluatee for recognition, remembering or jugment capabilities |
| US11826161B2 (en) | 2017-11-02 | 2023-11-28 | Panasonic Intellectual Property Management Co., Ltd. | Cognitive function evaluation device, cognitive function evaluation system, cognitive function evaluation method, and non-transitory computer-readable storage medium |
| JP2020127703A (ja) * | 2018-07-24 | 2020-08-27 | 日本テクトシステムズ株式会社 | 軽度の認知機能障害の推定システム及び軽度の認知機能障害の推定装置 |
| JP2019063551A (ja) * | 2018-12-05 | 2019-04-25 | サッポロビール株式会社 | 食感刺激の嗜好性評価方法 |
| JP7156081B2 (ja) | 2019-02-20 | 2022-10-19 | 株式会社島津製作所 | 認知機能の指標化方法 |
| CN111588348A (zh) * | 2019-02-20 | 2020-08-28 | 株式会社岛津制作所 | 认知功能的指标化方法 |
| JP2020130630A (ja) * | 2019-02-20 | 2020-08-31 | 株式会社島津製作所 | 認知機能の指標化方法 |
| JP2020130724A (ja) * | 2019-02-21 | 2020-08-31 | 株式会社島津製作所 | 脳活動特徴量の抽出方法 |
| CN111588347A (zh) * | 2019-02-21 | 2020-08-28 | 株式会社岛津制作所 | 脑活动特征量的提取方法 |
| JP7147623B2 (ja) | 2019-02-21 | 2022-10-05 | 株式会社島津製作所 | 脳血流量の特徴量の抽出方法 |
| CN111588347B (zh) * | 2019-02-21 | 2023-04-28 | 株式会社岛津制作所 | 脑活动特征量的提取方法 |
| US11678833B2 (en) | 2019-02-21 | 2023-06-20 | Shimadzu Corporation | Brain activity feature amount extraction method |
| JP2022528277A (ja) * | 2019-04-12 | 2022-06-09 | コリア アドヴァンスド インスティテュート オブ サイエンス アンド テクノロジー | マシンラーニングを利用して頭に関する生体情報を推定するための方法、システムおよび非一過性のコンピュータ読み取り可能な記録媒体 |
| JP7227657B2 (ja) | 2019-04-12 | 2023-02-22 | コリア アドヴァンスド インスティテュート オブ サイエンス アンド テクノロジー | マシンラーニングを利用して頭に関する生体情報を推定するための方法、システムおよび非一過性のコンピュータ読み取り可能な記録媒体 |
| JP7653688B2 (ja) | 2019-04-25 | 2025-03-31 | 国立大学法人大阪大学 | 情報処理装置、判定方法、および判定プログラム |
| JPWO2020218013A1 (ja) * | 2019-04-25 | 2020-10-29 | ||
| CN110876626A (zh) * | 2019-11-22 | 2020-03-13 | 兰州大学 | 基于多导联脑电最优导联选择的抑郁检测系统 |
| CN110876626B (zh) * | 2019-11-22 | 2022-08-12 | 兰州大学 | 基于多导联脑电最优导联选择的抑郁检测系统 |
| JP2020140724A (ja) * | 2020-05-07 | 2020-09-03 | ハルメク・ベンチャーズ株式会社 | 認知症判定得点算出装置及びそのプログラム |
| JP7109499B2 (ja) | 2020-05-07 | 2022-07-29 | 一般社団法人脳と心の健康科学研究所 | 認知症判定得点算出装置及びそのプログラム |
| WO2022191367A1 (ko) * | 2021-03-12 | 2022-09-15 | 주식회사 아이메디신 | 뇌파 데이터 분석을 통한 중증인지장애 환자 분류 방법, 서버 및 컴퓨터프로그램 |
| KR102492364B1 (ko) * | 2021-08-10 | 2023-01-27 | 주식회사 엔서 | 치매 등급 분류를 위해 장착되는 치매 검사장치 및 검사결과를 토대로 머신러닝 모델을 이용해 치매를 진단하는 치매 진단장치 |
| KR102492373B1 (ko) * | 2021-08-10 | 2023-01-27 | 주식회사 엔서 | 딥러닝 모델을 이용해 치매를 진단하는 치매 진단장치 |
| WO2023054643A1 (ja) * | 2021-09-30 | 2023-04-06 | ダイキン工業株式会社 | 不穏およびせん妄センシング装置並びに不穏およびせん妄センシング方法 |
| WO2023214545A1 (ja) * | 2022-05-02 | 2023-11-09 | 国立大学法人大阪大学 | 認知機能評価システム |
| KR20240055980A (ko) * | 2022-10-20 | 2024-04-30 | (주)오비이랩 | 인지 기능 개선을 위한 개인 맞춤형 광자극을 제공하는 방법, 장치 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
| WO2024085282A1 (ko) * | 2022-10-20 | 2024-04-25 | (주)오비이랩 | 인지 기능 개선을 위한 개인 맞춤형 광자극을 제공하는 방법, 장치 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
| KR102864150B1 (ko) | 2022-10-20 | 2025-09-26 | (주)오비이랩 | 인지 기능 개선을 위한 개인 맞춤형 광자극을 제공하는 방법, 장치 및 비일시성의 컴퓨터 판독 가능한 기록 매체 |
| CN117243569B (zh) * | 2023-10-12 | 2024-05-07 | 国家康复辅具研究中心 | 一种基于多源信息融合的认知功能评估方法和系统 |
| CN117243569A (zh) * | 2023-10-12 | 2023-12-19 | 国家康复辅具研究中心 | 一种基于多源信息融合的认知功能评估方法和系统 |
| CN119028583A (zh) * | 2024-08-12 | 2024-11-26 | 江苏省人民医院(南京医科大学第一附属医院) | 体外循环心脏手术患者神经认知障碍的预测数据处理方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| US9131889B2 (en) | 2015-09-15 |
| JP5959016B2 (ja) | 2016-08-02 |
| JPWO2012165602A1 (ja) | 2015-02-23 |
| US20140107494A1 (en) | 2014-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5959016B2 (ja) | 認知機能障害判別装置、認知機能障害判別システム、およびプログラム | |
| Sawangjai et al. | EEGANet: Removal of ocular artifacts from the EEG signal using generative adversarial networks | |
| Diaconescu et al. | Visual dominance and multisensory integration changes with age | |
| Zhang et al. | Multimodal depression detection: Fusion of electroencephalography and paralinguistic behaviors using a novel strategy for classifier ensemble | |
| Karthikeyan et al. | Detection of human stress using short-term ECG and HRV signals | |
| Neto et al. | EEG spectral features discriminate between Alzheimer’s and vascular dementia | |
| Xu et al. | Differentiating between psychogenic nonepileptic seizures and epilepsy based on common spatial pattern of weighted EEG resting networks | |
| Otero-Millan et al. | Unsupervised clustering method to detect microsaccades | |
| KR102378278B1 (ko) | 생체 신호 분석 시스템 및 이를 이용한 생체 신호 분석 방법 | |
| US11670423B2 (en) | Method and system for early detection of neurodegeneration using progressive tracking of eye-markers | |
| CN106413541B (zh) | 用于诊断睡眠的系统和方法 | |
| WO2016163594A1 (ko) | 동영상 기반 생리 신호 검출을 이용한 왜곡에 대한 정신생리적 탐지 (거짓말 탐지) 방법 및 장치 | |
| JP2005514096A (ja) | Eegバイスペクトルを用いて神経学的症状を評価する系および方法 | |
| JP2005514096A5 (ja) | ||
| Newman et al. | 1D convolutional neural networks for detecting nystagmus | |
| Kato et al. | Early detection of cognitive impairment in the elderly based on Bayesian mining using speech prosody and cerebral blood flow activation | |
| Miao et al. | Dynamic theta/beta ratio of clinical EEG in Alzheimer's disease | |
| CN112587796A (zh) | 脑深部电刺激促醒效果量化方法及设备 | |
| EP4590175A1 (en) | Analyzing method for and apparatus of intracranial dynamics | |
| KR20160031124A (ko) | 뇌파 분석을 통한 조현병 환자 또는 정신질환 환자의 증상 심각도를 예측하는 방법 및 장치 | |
| Touryan et al. | Isolating discriminant neural activity in the presence of eye movements and concurrent task demands | |
| US8579438B2 (en) | Apparatus and method for diagnosing disease involving optic nerve | |
| Cid-Fernández et al. | The importance of age in the search for ERP biomarkers of aMCI | |
| EP3182892B1 (en) | Method and system for eeg signal processing | |
| US10070812B2 (en) | Method for improved seizure detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12792180 Country of ref document: EP Kind code of ref document: A1 |
|
| DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
| ENP | Entry into the national phase |
Ref document number: 2013518182 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 14122786 Country of ref document: US |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 12792180 Country of ref document: EP Kind code of ref document: A1 |