CN116098587B - Cognition assessment method, device, equipment and medium based on eye movement - Google Patents
Cognition assessment method, device, equipment and medium based on eye movement Download PDFInfo
- Publication number
- CN116098587B CN116098587B CN202310065704.6A CN202310065704A CN116098587B CN 116098587 B CN116098587 B CN 116098587B CN 202310065704 A CN202310065704 A CN 202310065704A CN 116098587 B CN116098587 B CN 116098587B
- Authority
- CN
- China
- Prior art keywords
- cognitive
- subject
- eye movement
- test
- regression model
- 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
- 230000004424 eye movement Effects 0.000 title claims abstract description 156
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000019771 cognition Effects 0.000 title claims abstract description 28
- 230000001149 cognitive effect Effects 0.000 claims abstract description 187
- 238000012360 testing method Methods 0.000 claims abstract description 100
- 208000010877 cognitive disease Diseases 0.000 claims abstract description 81
- 238000011156 evaluation Methods 0.000 claims abstract description 43
- 208000028698 Cognitive impairment Diseases 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims description 45
- 230000004434 saccadic eye movement Effects 0.000 claims description 12
- 230000000007 visual effect Effects 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 210000001508 eye Anatomy 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000035484 reaction time Effects 0.000 description 3
- 241001112258 Moca Species 0.000 description 2
- 210000003710 cerebral cortex Anatomy 0.000 description 2
- 230000003920 cognitive function Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000035475 disorder Diseases 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 208000019022 Mood disease Diseases 0.000 description 1
- 208000001089 Multiple system atrophy Diseases 0.000 description 1
- 208000018737 Parkinson disease Diseases 0.000 description 1
- 208000037273 Pathologic Processes Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000004064 dysfunction Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 206010027175 memory impairment Diseases 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000009054 pathological process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 230000011273 social behavior Effects 0.000 description 1
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
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/163—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state by tracking eye movement, gaze, or pupil change
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/168—Evaluating attention deficit, hyperactivity
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Psychiatry (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Developmental Disabilities (AREA)
- Child & Adolescent Psychology (AREA)
- Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Artificial Intelligence (AREA)
- Social Psychology (AREA)
- Neurology (AREA)
- Educational Technology (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Neurosurgery (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The embodiment of the specification discloses a cognitive assessment method, device, equipment and medium based on eye movement, comprising the following steps: collecting eye movement data by an eye movement tracking device when the subject performs an eye movement test; inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject; if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject with cognitive disorder; and performing a cognitive test on the cognitive items of the subject with cognitive impairment to obtain a cognitive evaluation result of the subject. Compared with the method for directly performing the cognitive test scale on the subject, the embodiment of the specification can perform the primary evaluation of the cognitive disorder, perform the cognitive test on the cognitive item of the subject with the cognitive disorder after determining that the subject has the cognitive disorder, and can rapidly and accurately obtain the cognitive evaluation result of the subject.
Description
Technical Field
The specification relates to the technical field of computers, in particular to the technical field of intelligent medical treatment, and particularly relates to the technical field of cognitive evaluation, in particular to a cognitive evaluation method, device, equipment and medium based on eye movement.
Background
Cognition is an intelligent processing process for the body to recognize and acquire knowledge, and relates to a series of random, psychological and social behaviors such as learning, memory, language, thinking, spirit, emotion and the like. Cognitive impairment refers to a pathological process in which advanced intelligent processing of the brain related to learning, memory and thinking judgment is abnormal, so that serious learning, memory impairment is caused, and changes such as loss of speech or use or learning losing are accompanied. The basis of cognition is the normal function of the cerebral cortex, and any factor that causes dysfunction and structural abnormalities of the cerebral cortex can lead to cognitive dysfunction.
In the prior art, the cognitive evaluation is directly performed on the subject by using a cognitive detection scale (MoCA, MMSE), wherein the cognitive detection scale comprises a plurality of evaluation items, and a great amount of evaluation time of the subject may be required in the process.
Based on this, there is a need for a more efficient cognitive assessment method to reduce the assessment time of the subject.
Disclosure of Invention
One or more embodiments of the present disclosure provide a cognitive assessment method, apparatus, device, and medium based on eye movement, which are used to solve the technical problems set forth in the background art.
One or more embodiments of the present disclosure adopt the following technical solutions:
one or more embodiments of the present specification provide a cognitive assessment method based on eye movement, including:
when a subject performs an eye movement test, eye movement data is acquired through an eye movement tracking device;
inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject with cognitive disorder;
and performing a cognitive test on the cognitive items of the subject with cognitive impairment to obtain a cognitive evaluation result of the subject.
One or more embodiments of the present specification provide an eye movement-based cognitive assessment device, the device comprising:
an eye movement data acquisition unit for acquiring eye movement data by an eye movement tracking device when the subject performs an eye movement test;
a cognition condition determining unit, which inputs the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
a cognitive term determining unit, configured to input the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject having a cognitive disorder if the cognitive condition of the subject is a cognitive disorder;
and the evaluation result unit is used for carrying out cognitive test on the cognitive items of the subjects with cognitive disorder to obtain the cognitive evaluation result of the subjects.
One or more embodiments of the present specification provide an eye movement-based cognitive assessment device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
when a subject performs an eye movement test, eye movement data is acquired through an eye movement tracking device;
inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject with cognitive disorder;
and performing a cognitive test on a cognitive item of the subject with cognitive dysfunction to obtain a cognitive evaluation result of the subject.
One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to:
collecting eye movement data by an eye movement tracking device when the subject performs an eye movement test;
inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject with cognitive disorder;
and performing a cognitive test on the cognitive items of the subject with cognitive impairment to obtain a cognitive evaluation result of the subject.
The above-mentioned at least one technical scheme that this description embodiment adopted can reach following beneficial effect:
compared with the method for directly performing the cognitive test scale on the subject, the embodiment of the specification can perform the primary evaluation of the cognitive disorder, perform the cognitive test on the cognitive item of the subject with the cognitive disorder after determining that the subject has the cognitive disorder, and can rapidly and accurately obtain the cognitive evaluation result of the subject.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some of the embodiments described in the present description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a flow diagram of a cognitive eye movement-based assessment method according to one or more embodiments of the present disclosure;
fig. 2 is a schematic structural diagram of an eye movement-based cognitive assessment device according to one or more embodiments of the present disclosure;
fig. 3 is a schematic structural diagram of an eye movement-based cognitive assessment device according to one or more embodiments of the present disclosure.
Detailed Description
The embodiment of the specification provides a cognitive assessment method, device, equipment and medium based on eye movement.
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
Fig. 1 is a schematic flow diagram of a cognitive assessment method based on eye movement, which may be performed by a cognitive assessment system according to one or more embodiments of the present disclosure. Some input parameters or intermediate results in the flow allow for manual intervention adjustments to help improve accuracy.
The method flow steps of the embodiment of the present specification are as follows:
s102, when the subject performs eye movement test, eye movement data are acquired through an eye movement tracking device.
In the present examples, eye movement data may be collected by an eye movement detector EyeKnow when a subject is subjected to an eye movement test.
In the present description embodiments, the eye movement test may include a saccade test, a reverse saccade test, a smooth tracking test, a memory eye movement test, and a visual search test; wherein,,
the glance test is that the subject looks at the direction of the first target point, and the target points appear in different positions sequentially, for example, the first target point appears in the central position firstly, then the first target point disappears in the position, then the first target point appears randomly in a certain direction, and the subject is required to look at the first target point quickly in the process, so that the glance test is completed;
the reverse glance test is that the subject looks in the opposite direction of the second target point, the second target points appear in different positions sequentially, for example, the second target point appears in the central position first, then the second target point disappears in the position, then the second target point appears randomly in a certain direction, and the subject is required to look in the opposite direction of the second target point quickly in the process, so that the reverse glance test is completed;
the smooth tracking test tracks a third target point for the subject, wherein the third target point continuously moves, and the subject is required to quickly look at the continuously moving third target point in the process;
the memory eye movement test is that the subject looks at the positions of the fourth target points which appear in sequence according to the memory, the fourth target points appear in different positions in sequence, and the position of the fourth target points appearing in sequence is required to be memorized by the subject in the process;
the visual search test finds a specific pattern, for example, the letter L, among the patterns of the subject in front of the eyes.
Further, in the embodiment of the present disclosure, when the subject performs an eye movement test, during the process of collecting eye movement data by the eye movement tracking device, the eye movement test described above may be described in detail:
when the subject performs the saccade test, eye movement data including saccade speed, saccade eye movement latency and saccade acceleration can be collected by an eye movement tracking device, the saccade eye movement latency being a time difference between a target presentation and the start of eye movement;
when the subject performs the reverse glance test, eye movement data including reverse glance latency and reverse glance accuracy may be collected by an eye movement tracking device;
when the subject performs the smooth tracking test, eye movement data including gaze stability and gaze offset may be collected by an eye movement tracking device;
when the subject performs the memory eye movement test, eye movement data including memory accuracy and response time can be acquired by an eye movement tracking device;
eye movement data, including search time and search range, may be collected by an eye movement tracking device while the subject is performing the visual search test.
S104, inputting the eye movement data into a first regression model trained in advance to obtain the cognitive condition of the subject.
In embodiments of the present disclosure, the cognitive situation may include a cognitive assessment result, which is whether the current subject has a cognitive disorder, and a cognitive score, which is a cognitive test score of the current subject. It is possible to quickly determine whether the current subject has cognitive impairment or to quickly determine a cognitive score of the current subject by the first regression model.
Further, in the embodiment of the present disclosure, before the eye movement data is input into the first regression model trained in advance, the first regression model needs to be trained, and two types of the cognitive situation are described in detail below:
when the cognition condition is a cognition evaluation result, a first training set can be acquired firstly, wherein the first training set comprises first training data of a plurality of testers, and the first training data of each tester comprises eye movement data and a cognition evaluation result corresponding to each tester;
then, the eye movement data corresponding to each tester is set as a first input variable of the regression model, and the cognitive assessment result corresponding to each tester is set as a first output variable of the regression model;
and finally, training the first regression model according to the first training set to obtain the association relationship between the first input variable and the first output variable so as to complete the training of the first regression model.
When the cognition condition is a cognition score, a second training set can be acquired first, wherein the second training set comprises second training data of a plurality of testers, and the second training data of each tester comprises eye movement data and a cognition scale score corresponding to each tester;
then, setting the eye movement data corresponding to each tester as a second input variable of the regression model, and setting the cognitive scale score corresponding to each tester as a second output variable of the regression model;
finally, training the first regression model according to the second training set to obtain the association relation between the second input variable and the second output variable so as to complete the training of the first regression model.
It should be noted that, according to the cognitive assessment result and the cognitive score, it can be determined whether the current subject is a cognitive disorder, and the cognitive assessment result can directly draw a conclusion, namely yes or no; the cognitive score may be used to determine whether the current subject is a cognitive disorder with a predetermined score threshold for cognitive disorders, e.g., a total score of 30 points, a score of 1-20 may indicate the presence of cognitive disorders, and a score of 21-30 may indicate the absence of cognitive disorders. In addition, the cognitive condition of the subject obtained through the first regression model is only rapidly estimated, and if the rapid estimation result of the current subject is cognitive impairment, subsequent cognitive estimation needs to be further carried out through subsequent steps; if the rapid evaluation result of the current subject is that the cognition is normal, the subsequent cognition evaluation can not be continued, but the current subject has obvious cognitive impairment characteristics, and the subsequent cognition evaluation can also be performed to obtain an accurate cognition evaluation result.
And S106, if the cognitive condition of the subject is cognitive impairment, inputting the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject with cognitive impairment.
In this embodiment of the present disclosure, before the eye movement data is input into the pre-trained second regression model, a third training set may be obtained first, where the third training set includes third training data of a plurality of testers, and the third training data of each tester includes eye movement data corresponding to each tester and a cognitive term with cognitive impairment;
then, the eye movement data corresponding to each tester is set as a third input variable of the regression model, and the cognitive term corresponding to each tester with cognitive impairment is set as a third output variable of the regression model;
and finally, training the second regression model according to the third training set to obtain the association relationship between the third input variable and the third output variable so as to complete the training of the second regression model.
S108, performing a cognitive test on the cognitive items of the subject with cognitive dysfunction to obtain a cognitive evaluation result of the subject.
In the embodiment of the specification, corresponding cognitive domain test items can be generated according to the cognitive items of the subject with cognitive disorder, wherein the cognitive domain test items are cognitive tests conducted on the cognitive items of the cognitive disorder; and performing cognitive testing on the subject according to the cognitive domain test item to obtain a cognitive evaluation result of the subject.
It should be noted that the cognitive domain test item may include a plurality of test questions, and a more accurate test may be performed on a cognitive item of a subject with cognitive impairment, so that a cognitive evaluation result of the subject is more accurate.
It should be noted that, compared with directly performing the cognitive test scale on the subject, the embodiment of the specification can perform the primary evaluation of the cognitive disorder, and perform the cognitive test on the cognitive item of the subject with the cognitive disorder after determining that the subject has the cognitive disorder, so as to quickly and accurately obtain the cognitive evaluation result of the subject.
Based on the technical features described above, the embodiments of the present disclosure may be implemented by the following specific matters:
1. selecting an alternative subject:
each of 50 subjects with cognitive impairment and normal control groups was selected.
(1) Inclusion criteria:
age 55 years to 75 years;
normal eyeball movement and no serious vision impairment.
(2) Exclusion criteria:
the information acquisition cannot be completed due to the fact that factors such as serious mental diseases, nerve diseases, affective disorders, audiovisual disorders and the like cannot be understood;
diseases that seriously affect the function of eye movements (parkinson's disease, multiple system atrophy, etc.).
2. Clinical information acquisition
(1) Subject numbering
(2) Collecting subject demographic information such as: sex, date of birth, height, weight and cultural degree
3. Task testing for eye movement
Glance test: the target point appears at the central position firstly, then the central target point disappears, the target point appears at random in a certain direction, the test is completed by requiring the subject to quickly look at the target point, the scanning speed Sv, the scanning eye movement latency period Sl and the scanning acceleration Sa are acquired.
For example: overlapping toward eye jump: the target point appears at the center position first, then disappears at the center position after 1.2 seconds, but before 0.2 seconds of the disappearance of the center position, the target point appears at random at 15 degrees at the upper, lower, left and right angles. When the target point appears, the patient is required to quickly look at this point, for a total of 20 times.
Reverse glance test: the target point appears at the central position at first, and the target point appears at random in a certain direction, and the test is completed by requiring the subject to quickly look at the opposite direction of the target point at the moment, so that the anti-saccade latency period Al and the anti-saccade accuracy Ac are acquired.
For example: reverse eye jump: the target point appears at the central position firstly, then the central position disappears after 1 second, and the target system point appears at 15 degrees at random. When the target point appears up, down, left and right, the patient is required to quickly look in the opposite direction to the point, and the test is performed 20 times.
Smooth trace test: the subject is required to continuously watch a moving object, continuously watch smoothly, collect the fixation stability Ps and the fixation offset Po.
For example: horizontal smoothing tracking: the circular bright spots move in the horizontal direction at a sinusoidal rate with an amplitude of 20 deg. and a frequency of 0.2hz, and the subject needs to remain as continuously gazing as possible for 30 seconds.
Vertical smoothing tracking: the circular bright spot moves in the vertical direction with a sinusoidal velocity with an amplitude of 20 ° and a frequency of 0.2hz, and the subject needs to remain as continuously gazed as possible for 30 seconds.
Memory eye movement test: the subjects were asked to follow the memory to look sequentially at the positions of the points that occurred, the memory accuracy Mp, the response time Mr was acquired.
Visual search test: the subject needs to find a specific figure or number/letter in the front of the eye, collect the search time Vt, search range Ve.
4. Assessment of classical cognitive function
Subjects were scored for cognitive function using the MoCA scale and the values were recorded. The evaluation of whether the subject is cognition disorder is performed according to the existing medical diagnosis standard for the score, and the evaluation conclusion is recorded.
5. Training of eye movement index-cognition score regression model
Inputting parameters:
glance speed Sv, glance eye movement latency Sl, glance acceleration Sa, anti-glance latency Al, anti-glance accuracy Ac, fixation stability Ps, fixation offset Po, memory accuracy Mp, reaction time Mr, search time Vt, search range Ve.
Output parameters: cognitive score.
6. Training of regression model of eye movement index-cognition assessment result
Inputting parameters:
glance speed Sv, glance eye movement latency Sl, glance acceleration Sa, anti-glance latency Al, anti-glance accuracy Ac, fixation stability Ps, fixation offset Po, memory accuracy Mp, reaction time Mr, search time Vt, search range Ve.
Output parameters: a value of 0 or 1 (0-non-cognitive impairment, 1-cognitive impairment).
7. Training of eye movement index-cognitive term regression model with cognitive impairment
Inputting parameters:
glance speed Sv, glance eye movement latency Sl, glance acceleration Sa, anti-glance latency Al, anti-glance accuracy Ac, fixation stability Ps, fixation offset Po, memory accuracy Mp, reaction time Mr, search time Vt, search range Ve.
Output parameters: cognitive terms for cognitive disorders exist, wherein the cognitive terms include memory-related cognitive terms, attention-related cognitive terms, and vision space construction-related cognitive terms.
8. Evaluation based on eye movement tasks is carried out on the subjects by using the three sets of models completed above, and a cognitive evaluation result is obtained. The evaluator can directly refer to the cognitive evaluation result of the model, can also refer to the cognitive score to automatically judge whether the subject is cognitive disorder, and can obtain the cognitive evaluation result through a cognitive item regression model with cognitive disorder after determining that the subject is cognitive disorder.
Fig. 2 is a schematic structural diagram of an eye movement-based cognitive assessment device according to one or more embodiments of the present disclosure, where the device includes: an eye movement data acquisition unit 202, a cognitive situation determination unit 204, a disorder cognitive term determination unit 206, and an evaluation result unit 208.
An eye movement data acquisition unit 202 that acquires eye movement data by an eye movement tracking device when the subject performs an eye movement test;
a cognitive condition determining unit 204, configured to input the eye movement data into a first regression model trained in advance, to obtain a cognitive condition of the subject;
a cognitive term determining unit 206, configured to input the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject having a cognitive disorder if the cognitive condition of the subject is a cognitive disorder;
and an evaluation result unit 208, which performs a cognitive test on the cognitive items of the subject with cognitive disorder to obtain a cognitive evaluation result of the subject.
Fig. 3 is a schematic structural diagram of an eye movement-based cognitive assessment device according to one or more embodiments of the present disclosure, including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
collecting eye movement data by an eye movement tracking device when the subject performs an eye movement test;
inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject with cognitive disorder;
and performing a cognitive test on the cognitive items of the subject with cognitive impairment to obtain a cognitive evaluation result of the subject.
One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to:
collecting eye movement data by an eye movement tracking device when the subject performs an eye movement test;
inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain a cognitive term of the subject with cognitive disorder;
and performing a cognitive test on the cognitive items of the subject with cognitive impairment to obtain a cognitive evaluation result of the subject.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.
Claims (9)
1. A method of eye movement based cognitive assessment, the method comprising:
when a subject performs an eye movement test, eye movement data is acquired through an eye movement tracking device;
inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain cognitive items of the subject with cognitive disorder, wherein the cognitive items comprise memory-related cognitive items, attention-related cognitive items and vision space construction-related cognitive items;
performing a cognitive test on a cognitive term of the subject in which a cognitive disorder exists to obtain a cognitive assessment result of the subject, including:
generating corresponding cognitive domain test items according to cognitive items of the subject with cognitive disorder;
and performing cognitive testing on the subject according to the cognitive domain test item to obtain a cognitive evaluation result of the subject.
2. The method of claim 1, wherein the eye movement test comprises one or more of a glance test, a reverse glance test, a smooth tracking test, a memory eye movement test, and a visual search test; wherein,,
the glance test is that the subject looks at a first target point direction, and the target points appear in different positions successively;
the reverse glance test is that the subject looks in the opposite direction of a second target point, and the second target point appears at different positions in sequence;
the smooth tracking test tracks a third target point for the subject, the third target point continuously moving;
the memory eye movement test is that the subject looks at the positions of fourth target points which appear in sequence according to memory, and the fourth target points appear in different positions in sequence;
the visual search test finds a particular pattern among the patterns of the subject in front of the eyes.
3. The method of claim 2, wherein the collecting eye movement data by the eye movement tracking device while the subject is performing an eye movement test comprises:
collecting, by an eye-tracking device, eye-movement data including saccade speed, saccade eye-movement latency and saccade acceleration while the subject is performing the saccade test;
collecting eye movement data including anti-saccade latency and anti-saccade accuracy by an eye movement tracking device while the subject is performing the reverse saccade test;
when the subject performs the smooth tracking test, acquiring eye movement data including gaze stability and gaze offset by an eye movement tracking device;
when the subject performs the memory eye movement test, acquiring eye movement data including memory accuracy and response time through an eye movement tracking device;
when the subject performs the visual search test, collecting eye movement data by an eye movement tracking device includes a search time and a search range.
4. The method of claim 1, wherein the cognitive situation is a cognitive assessment result;
before the inputting the eye movement data into the pre-trained first regression model, the method further comprises:
acquiring a first training set, wherein the first training set comprises first training data of a plurality of testers, and the first training data of each tester comprises eye movement data and a cognition assessment result corresponding to each tester;
setting the eye movement data corresponding to each tester as a first input variable of the regression model, and setting the cognitive assessment result corresponding to each tester as a first output variable of the regression model;
and training the first regression model according to the first training set to obtain the association relationship between the first input variable and the first output variable so as to complete the training of the first regression model.
5. The method of claim 1, wherein the cognitive situation is a cognitive score;
before the inputting the eye movement data into the pre-trained first regression model, the method further comprises:
acquiring a second training set, wherein the second training set comprises second training data of a plurality of testers, and the second training data of each tester comprises eye movement data and cognitive scale scores corresponding to each tester;
setting the eye movement data corresponding to each tester as a second input variable of the regression model, and setting the cognitive scale score corresponding to each tester as a second output variable of the regression model;
and training the first regression model according to the second training set to obtain the association relation between the second input variable and the second output variable so as to complete the training of the first regression model.
6. The method of claim 1, wherein before said inputting the eye movement data into the pre-trained second regression model, the method further comprises:
acquiring a third training set, wherein the third training set comprises third training data of a plurality of testers, and the third training data of each tester comprises eye movement data corresponding to each tester and cognitive items with cognitive disorder;
setting the eye movement data corresponding to each tester as a third input variable of the regression model, and setting the cognitive term with cognitive impairment corresponding to each tester as a third output variable of the regression model;
and training the second regression model according to the third training set to obtain the association relationship between the third input variable and the third output variable so as to complete the training of the second regression model.
7. An eye movement based cognitive assessment device, the device comprising:
an eye movement data acquisition unit for acquiring eye movement data by an eye movement tracking device when the subject performs an eye movement test;
a cognition condition determining unit, which inputs the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
a cognitive impairment term determining unit, configured to input the eye movement data into a pre-trained second regression model to obtain a cognitive impairment term of the subject, where the cognitive impairment term includes a memory-related cognitive term, an attention-related cognitive term, and a vision space construction-related cognitive term, if the cognitive condition of the subject is a cognitive impairment;
an evaluation result unit, for performing a cognitive test on a cognitive term of the subject with cognitive impairment to obtain a cognitive evaluation result of the subject, including:
generating corresponding cognitive domain test items according to cognitive items of the subject with cognitive disorder;
and performing cognitive testing on the subject according to the cognitive domain test item to obtain a cognitive evaluation result of the subject.
8. An eye movement based cognitive assessment device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
when a subject performs an eye movement test, eye movement data is acquired through an eye movement tracking device;
inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain cognitive items of the subject with cognitive disorder, wherein the cognitive items comprise memory-related cognitive items, attention-related cognitive items and vision space construction-related cognitive items;
performing a cognitive test on a cognitive term of the subject in which a cognitive disorder exists to obtain a cognitive assessment result of the subject, including:
generating corresponding cognitive domain test items according to cognitive items of the subject with cognitive disorder;
and performing cognitive testing on the subject according to the cognitive domain test item to obtain a cognitive evaluation result of the subject.
9. A non-transitory computer storage medium storing computer-executable instructions configured to:
when a subject performs an eye movement test, eye movement data is acquired through an eye movement tracking device;
inputting the eye movement data into a first regression model trained in advance to obtain the cognition condition of the subject;
if the cognitive condition of the subject is cognitive disorder, inputting the eye movement data into a pre-trained second regression model to obtain cognitive items of the subject with cognitive disorder, wherein the cognitive items comprise memory-related cognitive items, attention-related cognitive items and vision space construction-related cognitive items;
performing a cognitive test on a cognitive term of the subject in which a cognitive disorder exists to obtain a cognitive assessment result of the subject, including:
generating corresponding cognitive domain test items according to cognitive items of the subject with cognitive disorder;
and performing cognitive testing on the subject according to the cognitive domain test item to obtain a cognitive evaluation result of the subject.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310065704.6A CN116098587B (en) | 2023-01-13 | 2023-01-13 | Cognition assessment method, device, equipment and medium based on eye movement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310065704.6A CN116098587B (en) | 2023-01-13 | 2023-01-13 | Cognition assessment method, device, equipment and medium based on eye movement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116098587A CN116098587A (en) | 2023-05-12 |
| CN116098587B true CN116098587B (en) | 2023-10-10 |
Family
ID=86263423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310065704.6A Active CN116098587B (en) | 2023-01-13 | 2023-01-13 | Cognition assessment method, device, equipment and medium based on eye movement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116098587B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2803443A1 (en) * | 2013-01-30 | 2014-07-30 | Mark Gierl | Automatic item generation (aig) manufacturing process and system |
| CN106256312A (en) * | 2015-06-16 | 2016-12-28 | 日立数字映像(中国)有限公司 | Cognitive dysfunction evaluating apparatus |
| CN106691476A (en) * | 2017-01-16 | 2017-05-24 | 清华大学 | Image recognition Mentality Analysis System based on features of eye movements |
| KR102013142B1 (en) * | 2018-07-31 | 2019-08-22 | 도로교통공단 | A method for evaluating driving ability based on cognitive test using driving ability evaluation system |
| CN110801237A (en) * | 2019-11-10 | 2020-02-18 | 中科搏锐（北京）科技有限公司 | Cognitive ability assessment system and method based on eye movement and electroencephalogram characteristics |
| CN112086108A (en) * | 2020-08-04 | 2020-12-15 | 科大讯飞股份有限公司 | Cognitive disorder prediction method, electronic device and storage device |
| CN112971782A (en) * | 2021-01-27 | 2021-06-18 | 厦门市儿童医院 | Method, device, equipment and storage medium for testing children neural behaviors |
| CN113558603A (en) * | 2021-06-11 | 2021-10-29 | 杭州电子科技大学 | Multi-modal cognitive impairment recognition method based on deep learning |
| CN114343585A (en) * | 2022-01-13 | 2022-04-15 | 平安科技（深圳）有限公司 | Early warning method, device, equipment and storage medium for cognitive and behavioral disorders |
| WO2022186915A1 (en) * | 2021-03-05 | 2022-09-09 | Evolution Optiks Limited | Head-mountable oculomotor assessment device and system, and method of using same |
| CN115047969A (en) * | 2022-06-10 | 2022-09-13 | 北京大学 | Cognitive function evaluation system based on eye movement and evaluation method thereof |
| CN115040086A (en) * | 2021-06-11 | 2022-09-13 | 合肥工业大学 | Data processing system and method based on digital biomarkers |
| CN115089112A (en) * | 2022-05-06 | 2022-09-23 | 清华大学 | Method and device for establishing post-stroke cognitive disorder risk assessment model and electronic equipment |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2003900035A0 (en) * | 2003-01-07 | 2003-01-23 | Monash University | Detecting subtle cognitive impairment |
| WO2009114795A2 (en) * | 2008-03-14 | 2009-09-17 | Medical Care Corporation | Non-natural pattern identification for cognitive assessment |
| GB201200122D0 (en) * | 2012-01-05 | 2012-02-15 | Univ Aberdeen | An apparatus and a method for psychiatric evaluation |
| CA3081199A1 (en) * | 2017-11-14 | 2019-05-23 | Osaka University | Cognitive impairment diagnostic apparatus and cognitive impairment diagnostic program |
| US20210313020A1 (en) * | 2018-03-26 | 2021-10-07 | Aimmed Co., Ltd. | Method and apparatus for rehabilitation training of cognitive function |
| US20220293266A1 (en) * | 2021-03-09 | 2022-09-15 | The Hong Kong Polytechnic University | System and method for detection of impairment in cognitive function |
| KR102287191B1 (en) * | 2021-03-12 | 2021-08-09 | 주식회사 아이메디신 | Method, server and computer program for classifying severe cognitive impairment patients by analyzing eeg data |
-
2023
- 2023-01-13 CN CN202310065704.6A patent/CN116098587B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2803443A1 (en) * | 2013-01-30 | 2014-07-30 | Mark Gierl | Automatic item generation (aig) manufacturing process and system |
| CN106256312A (en) * | 2015-06-16 | 2016-12-28 | 日立数字映像(中国)有限公司 | Cognitive dysfunction evaluating apparatus |
| CN106691476A (en) * | 2017-01-16 | 2017-05-24 | 清华大学 | Image recognition Mentality Analysis System based on features of eye movements |
| KR102013142B1 (en) * | 2018-07-31 | 2019-08-22 | 도로교통공단 | A method for evaluating driving ability based on cognitive test using driving ability evaluation system |
| CN110801237A (en) * | 2019-11-10 | 2020-02-18 | 中科搏锐（北京）科技有限公司 | Cognitive ability assessment system and method based on eye movement and electroencephalogram characteristics |
| CN112086108A (en) * | 2020-08-04 | 2020-12-15 | 科大讯飞股份有限公司 | Cognitive disorder prediction method, electronic device and storage device |
| CN112971782A (en) * | 2021-01-27 | 2021-06-18 | 厦门市儿童医院 | Method, device, equipment and storage medium for testing children neural behaviors |
| WO2022186915A1 (en) * | 2021-03-05 | 2022-09-09 | Evolution Optiks Limited | Head-mountable oculomotor assessment device and system, and method of using same |
| CN113558603A (en) * | 2021-06-11 | 2021-10-29 | 杭州电子科技大学 | Multi-modal cognitive impairment recognition method based on deep learning |
| CN115040086A (en) * | 2021-06-11 | 2022-09-13 | 合肥工业大学 | Data processing system and method based on digital biomarkers |
| CN114343585A (en) * | 2022-01-13 | 2022-04-15 | 平安科技（深圳）有限公司 | Early warning method, device, equipment and storage medium for cognitive and behavioral disorders |
| CN115089112A (en) * | 2022-05-06 | 2022-09-23 | 清华大学 | Method and device for establishing post-stroke cognitive disorder risk assessment model and electronic equipment |
| CN115047969A (en) * | 2022-06-10 | 2022-09-13 | 北京大学 | Cognitive function evaluation system based on eye movement and evaluation method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116098587A (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11452475B2 (en) | Systems and methods for assessing and improving sustained attention | |
| KR101247748B1 (en) | Apparatus for analysing focus and nonfocus states and method therof | |
| KR102477327B1 (en) | Processor-implemented systems and methods for measuring cognitive ability | |
| US11426069B2 (en) | Enhanced neuropsychological assessment with eye tracking | |
| JP7442454B2 (en) | Systems and methods for detecting neurological disorders and measuring general cognitive abilities | |
| JP2007502630A (en) | Cognitive processing | |
| EP2800507A1 (en) | An apparatus and a method for psychiatric evaluation | |
| Werth | What causes dyslexia? Identifying the causes and effective compensatory therapy | |
| Toivanen et al. | A probabilistic real-time algorithm for detecting blinks, saccades, and fixations from EOG data | |
| Saisara et al. | Strabismus screening by Eye Tracker and games | |
| CN111743553B (en) | Emotion feature extraction method and system based on eye movement data | |
| Kaur et al. | Using virtual reality to examine the neural and physiological anxiety-related responses to balance-demanding target-reaching leaning tasks | |
| Muller-Gass et al. | Brain states predict individual differences in perceptual learning | |
| CN116098587B (en) | Cognition assessment method, device, equipment and medium based on eye movement | |
| CN115868939A (en) | Cognitive assessment method, device, equipment, medium and computer program product | |
| Korda et al. | Automatic identification of oculomotor behavior using pattern recognition techniques | |
| Swati et al. | Machine learning systems for detecting schizophrenia | |
| Simonovic et al. | Pupil dilation and cognitive reflection as predictors of performance on the iowa gambling task | |
| Jadhav et al. | Analysis of effect of meditation on cognitive load using higher order crossing features | |
| Kunimasa et al. | An estimation method of intellectual work performance by using physiological indices | |
| Gambiraža et al. | Classification of Cognitive Load based on Oculometric Features | |
| CN114190929B (en) | Spasm quantitative evaluation method, device and system | |
| Borys et al. | Classification of user performance in the Ruff Figural Fluency Test based on eye-tracking features | |
| US20230148922A1 (en) | Systems and methods for screening subjects for neuropathology associated with covid-19 utilizing a mobile device | |
| US20230368919A1 (en) | Method for identifying specific alterations in subjects with defined diseases analyzing oculomotor patterns when using specific visual stimuli, where a specific drug or treatment would enhance visual processing, cognitive performance and related brain activities |
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 |