CN116110599A - Apparatus, system and storage medium for screening analysis of mild cognitive impairment - Google Patents
Apparatus, system and storage medium for screening analysis of mild cognitive impairment Download PDFInfo
- Publication number
- CN116110599A CN116110599A CN202310382323.0A CN202310382323A CN116110599A CN 116110599 A CN116110599 A CN 116110599A CN 202310382323 A CN202310382323 A CN 202310382323A CN 116110599 A CN116110599 A CN 116110599A
- Authority
- CN
- China
- Prior art keywords
- screening
- cognitive impairment
- mild cognitive
- near infrared
- feature
- 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.)
- Pending
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
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
- A61B5/14553—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases specially adapted for cerebral tissue
-
- 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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Neurology (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Psychiatry (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Child & Adolescent Psychology (AREA)
- Primary Health Care (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Data Mining & Analysis (AREA)
- Psychology (AREA)
- Epidemiology (AREA)
- Physiology (AREA)
- Social Psychology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Neurosurgery (AREA)
- Optics & Photonics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Spectroscopy & Molecular Physics (AREA)
Abstract
The present application provides devices, systems, and storage media for screening assays for mild cognitive impairment. The device comprises an interface and a processor, wherein the interface is used for receiving near infrared data, the processor is configured to acquire blood oxygen concentration data based on the near infrared data, obtain first characteristic values and second characteristic values of a plurality of candidate characteristics based on the blood oxygen concentration data, conduct difference degree analysis to extract significant characteristics, conduct correlation analysis on the significant characteristics, take the significant characteristics with the correlation number meeting preset conditions as screening characteristics, determine screening weights based on the correlation coefficients of the screening characteristics, and combine the screening characteristics with the corresponding screening weights for screening analysis of mild cognitive impairment. In this way, screening features that can improve the accuracy of screening for mild cognitive impairment can be obtained.
Description
Technical Field
The present application relates to the field of medical technology, and in particular to an apparatus, system and storage medium for screening analysis of mild cognitive impairment.
Background
With the rapid growth of the aging world population, the risk of mild cognitive impairment (mild cognitive impairment, MCI) and alzheimer's disease (Alzheimer disease, AD) is also increasing. MCI is considered to be a transitional phase between healthy aging and dementia, as a precursor symptom that also retains functional independence, and is an attractive target for research on the physiological mechanism of AD and clinical predictive intervention.
At present, the cognitive scale is often used for diagnosing the AD clinically, the time consumption is long, the diagnosis depends on the professional ability of doctors, the subjectivity is strong, and the diagnosis is influenced by factors such as education degree. The diagnosis of AD based on imaging can improve the accuracy of diagnosis, but MRI/PET is sensitive to motion trail and has high price, and is only used in specific places, thus limiting the popularization and application of cognitive disorder screening. Efficient and accurate screening and diagnosis of MCI/AD for numerous people in communities and the like is not possible. Therefore, there is an urgent need for convenient, efficient, and suitable for large-scale screening early diagnosis methods and systems for Alzheimer's disease.
Disclosure of Invention
The present application is directed to the above-mentioned technical problems existing in the prior art. The application aims to provide a device, a system and a storage medium for screening analysis of mild cognitive impairment, which can efficiently and accurately screen the mild cognitive impairment of large-scale people, can improve the targeting of screening the mild cognitive impairment and improve the screening efficiency.
According to a first aspect of the present application, there is provided an apparatus for screening analysis of mild cognitive impairment, the apparatus comprising an interface configured to receive near infrared data of a preset brain region of a preset number of first subjects during performance of a VFT task acquired via a near infrared brain function imaging device, wherein the first subjects include healthy persons and mild cognitive impairment patients, and a processor configured to acquire blood oxygen concentration data of the preset brain region of the preset number of first subjects during performance of a reaction task in the VFT task based on the near infrared data, and to obtain first feature values of a plurality of candidate features of each brain region of each healthy person and second feature values of each brain region of each mild cognitive impairment patient corresponding to each candidate feature based on the blood oxygen concentration data; performing a degree of difference analysis on the first feature value and the second feature value of each candidate feature to extract therefrom salient features whose degree of significance is above a difference threshold; performing correlation analysis on the first characteristic value and the second characteristic value of the salient features and the reference value of the reference standard to obtain correlation coefficients of the salient features, and taking the salient features of which the correlation coefficients meet preset conditions as screening features; determining screening weights of the screening features based on the correlation coefficients of the screening features; and combining each screening characteristic with the corresponding screening weight for screening analysis of mild cognitive impairment.
According to a second aspect of the present application, there is provided a system for screening analysis of mild cognitive impairment, the system comprising a near infrared brain function imaging device and an apparatus for screening analysis of mild cognitive impairment as described in various embodiments of the present application; the system is configured to: receiving first near infrared data of a preset brain region of a first examinee in a preset quantity acquired by the near infrared brain function imaging equipment during the process of performing the VFT task by using the device, and determining the screening characteristics according to the first near infrared data; acquiring screening characteristics of a second subject based on second near infrared data of a preset brain region of the second subject during the execution of the VFT task, wherein the second near infrared data is acquired by the near infrared brain function imaging device; based on the screening characteristics, screening analysis results are obtained for the second subject having a predisposition for mild cognitive impairment.
According to a third aspect of the present application, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps performed by the processor in the apparatus for screening analysis of mild cognitive impairment as described in various embodiments of the present application.
Compared with the prior art, the beneficial effects of the embodiment of the application are that:
the device for screening and analyzing the mild cognitive impairment, which is provided by the embodiment of the application, has lower requirements on the testee and the environment, and can be suitable for screening the mild cognitive impairment of large-scale people. And extracting characteristic values based on near infrared data of each brain region of healthy people and mild cognitive impairment patients, and performing difference analysis based on the extracted characteristics to determine significant characteristics. Screening features are further determined by correlation analysis of the salient features with reference values of the reference standard. The greater the correlation of the salient features with the reference values, the more favorable the salient features are for truly reflecting the correlation conditions of mild cognitive impairment. And further combining the weights of the screening features to obtain screening features with the weights, inputting the screening features with the weights into a classifier to obtain screening results, and if the screening results are better than those of the screening results adopting a cognitive scale, indicating that the screening features can be used for screening analysis of mild cognitive impairment. In this way, the targeting and accuracy of screening for mild cognitive impairment can be improved. Compared with the existing screening method for the light cognitive impairment of large-scale people based on the cognitive scale, the screening method has higher screening efficiency and obviously reduces the cost of manual screening. The screening characteristics obtained by screening the crowd in the local area through the screening analysis device provided by the embodiment of the application can also be used as the reference screening characteristics for screening the crowd in other areas with similar social environments as the local area, so that the efficiency of screening the mild cognitive impairment of the large-scale crowd in different areas with similar social environments is further improved.
The foregoing description is merely an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above description and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. Like reference numerals with letter suffixes or different letter suffixes may represent different examples of similar components. The drawings illustrate generally, by way of example, and not by way of limitation, various embodiments, and together with the description and claims serve to explain the disclosed embodiments. Such embodiments are illustrative and exemplary, and are not intended to be exhaustive or exclusive embodiments of the present apparatus, system, or non-transitory computer readable medium having instructions for carrying out the execution method of the present apparatus processor.
Fig. 1 (a) shows a schematic structural diagram of an apparatus for screening analysis of mild cognitive impairment according to an embodiment of the present application.
Fig. 1 (b) shows a flowchart of steps performed by a processor of an apparatus for screening analysis of mild cognitive impairment according to an embodiment of the application.
Fig. 2 shows a schematic diagram of a preset brain region according to an embodiment of the present application.
Fig. 3 shows a schematic structural diagram of a system for screening analysis of mild cognitive impairment according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions of the present application, the following detailed description of the present application is provided with reference to the accompanying drawings and the specific embodiments. Embodiments of the present application will now be described in further detail with reference to the accompanying drawings and specific examples, but are not intended to be limiting of the present application.
The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. As used in this application, the word "comprising" or "comprises" and the like means that elements preceding the word encompass the elements recited after the word, and that no other elements are excluded from the possible coverage. In the present application, the arrows shown in the figures of the respective steps are merely examples of the execution sequence, and the technical solution of the present application is not limited to the execution sequence described in the embodiments, and the respective steps in the execution sequence may be performed in a combined manner, may be performed in a split manner, and may be exchanged in order as long as the logical relationship of the execution content is not affected.
All terms (including technical or scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless specifically defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein. Devices, systems known to those of ordinary skill in the relevant art may not be discussed in detail, but should be considered part of the specification where appropriate.
Fig. 1 (a) shows a schematic structural diagram of an apparatus for screening analysis of mild cognitive impairment according to an embodiment of the present application. The apparatus 100 for screening analysis includes an interface 101 and a processor 102. Wherein the interface 101 is configured to receive near infrared data of a preset brain region of a preset number of first subjects acquired via a near infrared brain function imaging device during performance of a VFT task, wherein the first subjects include healthy people and mild cognitive impairment patients. The near infrared brain function imaging device has at least a headgear for wearing over the head of the first subject. For example, the headgear may have a plurality of probes for transmitting near infrared light and/or receiving near infrared light. For another example, the headgear may be provided with a plurality of mounting locations for detachably mounting the respective probes, and in use, the probes may be mounted to the headgear by the mounting locations. Wherein each of the plurality of probes may be configured as either a transmitting probe (S) or a receiving probe (D), each pair of paired probes forming a channel. In some embodiments, one transmitting probe may correspond to multiple receiving probes, or vice versa, with a pairing relationship corresponding to the specific requirements of the probe's deployment location, brain function area to be detected, etc.
Further, the preset number is greater than a threshold number so that the number of the first subjects is sufficiently large, wherein the threshold number is not particularly limited and may be set by a doctor according to experience or according to statistical data. For example, for a large community, for screening for mild cognitive impairment in 3000 elderly people aged 45-80 years, 400 people in total can be screened out by using a cognitive scale method, the number of healthy people and the number of mild cognitive impairment patients are not greatly different, and near infrared data of 400 people are collected for determining screening characteristics for screening for mild cognitive impairment.
In this application, "VFT task" is intended to mean Verbal Fluency Test, the word fluency test, VFT finds application in clinical and scientific research for diagnosis and assessment of a variety of brain functional disorders. For example, the VFT task may require the first subject to speak as many words of a certain class as possible within a prescribed time, such as requiring the first subject to word as many words as possible in the daytime "white". Alternatively, the first subject is required to speak as many Chinese nouns of a particular category as possible within a prescribed time, e.g., the first subject is required to speak which categories of fruits include. The VFT task to be specifically executed is not limited.
In this embodiment, the preset brain region is not particularly limited and may be set by a doctor according to clinical experience, and as shown in fig. 2, the preset brain region may include at least one or more of left forehead Lobe (LPF), medial forehead lobe (MPF), right forehead lobe (RPF), left temporal Lobe (LT), top lobe (P), right temporal lobe (RT), left top lower Lobe (LIP), right top lower lobe (RIP), left occipital Lobe (LO), right occipital lobe (RO), thereby obtaining near infrared data of the first subject during performing the VFT task. Among these, near infrared data may be an oxygenated hemoglobin concentration (oxygenated hemoglobin, hbO 2), a deoxygenated hemoglobin concentration (deoxygenated hemoglobin, hbR), and a total hemoglobin concentration (HbT).
Specifically, the processor 102 is configured to perform the steps described in fig. 1 (b). In step S103, blood oxygen concentration data of a preset brain region of the first subject in the preset number during the execution of the reaction task in the VFT task is acquired based on the near infrared data, and first feature values of a plurality of candidate features of each brain region of each healthy person and second feature values of each corresponding candidate feature of each brain region of each mild cognitive impairment patient are obtained based on the blood oxygen concentration data. The first subject performs a VFT task, acquires near-infrared data of the first subject using the near-infrared brain function imaging device, and specifically, for example, parameters at the time of acquisition using the near-infrared brain function imaging device may include: the two wavelengths 760nm and 850nm,22 light sources and 31 detectors are arranged in a total of 71 channels, the distance between the light sources and the detectors is 3 cm, the sampling rate is 19Hz, and the channels are divided into left and right 10 brain areas according to the measured coordinates of a 3D positioning instrument and Brodmann subareas. Wherein, if the first subject requires to utilize "white" as many word-forming as possible within a prescribed time while performing the VFT task, performing the word-forming task can be understood as performing a reaction task in the VFT task. The near infrared data is processed to obtain blood oxygen concentration data, wherein the blood oxygen concentration data in the application can be one or more of oxyhemoglobin concentration data, deoxyhemoglobin concentration data and total hemoglobin concentration data.
In step S104, a degree of difference analysis is performed on the first feature value and the second feature value of each candidate feature to extract therefrom a salient feature whose degree of significance differs from the first feature value and the second feature value by a difference threshold. Specifically, the difference of the feature values of the candidate features during the reaction task of performing the VFT task may be compared with the brain regions of the healthy person and the mild cognitive impairment patient, respectively, using the independent sample t test, and if the difference is large, the current candidate feature may be considered to be useful for reflecting the brain functional activity status of the mild cognitive impairment patient. For example, taking the candidate feature as the average blood oxygen concentration of the lower left leaflet, the difference between the value of the average blood oxygen concentration of the lower left leaflet and the value of the average blood oxygen concentration of the lower left leaflet of the patient with mild cognitive impairment is compared by using an independent sample t test, and if the difference between the two values is large, the average blood oxygen concentration of the lower left leaflet can be regarded as a significant feature. The difference threshold is not particularly limited, and may be set by a doctor.
In step S105, a correlation analysis is performed on the first feature value and the second feature value of the salient feature and the reference value of the reference standard, so as to obtain a correlation coefficient of the salient feature, and the salient feature of which the correlation coefficient meets a preset condition is used as a screening feature. In particular, the reference value of the reference standard may be understood as a data value obtained based on the scale score, or may be a data value of the first subject's behaviours during the execution of the reaction task in the VFT task. The data of the first examinee's behaviours including the accurate times, the repeated times and the error times can be counted by using the reaction task in the VFT task executed by the first examinee as the words of the fruit category which are spoken in the prescribed time. Taking the example of the significant characteristic as the average blood oxygen concentration of the left occipital lobe, the correlation analysis can be performed on the first characteristic value and the second characteristic value of the average blood oxygen concentration of the left occipital lobe of healthy people and mild cognitive impairment patients with the data of the behaviours based on the Pearson correlation coefficient (Pearson Correlation Coefficient) (see Adler J, parmryd I. Quantifying colocalization by correlation: the Pearson correlation coefficient is superior to the Mander's overlap coefficient [ J ]. Cytometric Part A, 2010, 77 (8): 733-742), respectively, wherein the preset condition can be that the correlation coefficient r satisfies 0< | < r| <1, indicating that there is linear correlation of different degrees, and if the correlation coefficient r=0.2804, p=0.0363 of the correlation analysis can be considered as the screening characteristic. Among them, the reference standard is not particularly limited, and may be an existing method that has been widely used for screening for mild cognitive impairment, such as by analyzing behavioral data of the first subject during the VFT task, or a general scale. The preset condition may be set based on an algorithm of the correlation analysis, which is not particularly limited.
In step S106, screening weights for each screening feature are determined based on the correlation coefficients for each screening feature. For example, taking the average blood oxygen concentration of the top left leaflet and the top right leaflet as significant features, performing correlation analysis on the first characteristic value and the second characteristic value of the average blood oxygen concentration of the top left leaflet and the top right leaflet of the healthy person and the mild cognitive impairment patient respectively based on Pearson correlation coefficients and the data of scale scores to obtain the correlation coefficients of the average blood oxygen concentration of the top left leaflet and the average blood oxygen concentration of the top right leaflet respectively as r=0.2804 and p=0.0363; r=0.2633, p=0.0499, then the screening weight for the average blood oxygen concentration of the lower left and lower right leaflet can be determined to be 0.2804 based on the correlation coefficient: 0.2633. that is, the extent to which each screening feature affects the predisposition to mild cognitive impairment may be analyzed based on the correlation coefficient of each screening feature. Further, the particular method of determining the screening weights for each screening feature is not limited, and this embodiment is but one implementation.
In step S107, each screening feature is combined with its corresponding screening weight for screening analysis of mild cognitive impairment. Thus, the obtained screening characteristics have remarkable targeting property for distinguishing the healthy first subject from the early-stage patients with Alzheimer's disease, and can effectively improve the accuracy of screening mild cognitive impairment.
Further, the preset number of first subjects may be screened for mild cognitive impairment based on each screening feature in combination with its corresponding screening weight, and in the case that the quality of the screening result is greater than a threshold index, each screening feature is used for screening analysis of mild cognitive impairment. The quality of the screening result may include one or more of accuracy, sensitivity, and specificity, among others, which are not particularly limited. The threshold index may be set by the doctor according to the statistical calculation result, or may be a scoring quality result scored by a scale or behavioristic data of the first statistical subject in executing the VFT task, which is not limited specifically. In the event that the quality of the screening result is greater than a threshold indicator, the individual screening features may be used in a screening assay for mild cognitive impairment.
In some embodiments of the present application, the candidate features include at least one or more of an average blood oxygen concentration of each preset brain region, a variance of the average blood oxygen concentration of each preset brain region, and an area under the blood oxygen concentration curve of each preset brain region. For example, if the predetermined brain region is left, medial, and right forehead lobes, the candidate features may be the average blood oxygen concentration of the left, medial, and right forehead lobes, as well as the variance of the average blood oxygen concentrations of the left, medial, and right forehead lobes and the area under the curves of the left, medial, and right forehead lobes. Specifically, reference may be made to Zhang S, zheng Y, wang D, et al Application of a common spatial pattern-based algorithm for an fNIRS-based motor imagery brain-computer interface [ J ] Neuroscience letters, 2017, 655:35-40 and Chao J, zheng S, wu H, et al fNIRS evidence for distinguishing patients with major depression and healthy controls [ J ] IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29:2211-2221 for calculation of average blood oxygen concentration, variance of average blood oxygen concentration and area under the curve.
In some embodiments of the present application, the reference criteria comprises a scale for screening for mild cognitive impairment and/or behavioural data of the first subject during performance of a reaction task in the VFT task. The scales can be a simple mental state examination scale (Mini-mental State Examination, MMSE) and a Montreal cognitive assessment scale (MontrealCognitiveAssessment, MOCA scale). The behavioural data of the first subject during the execution of the reaction tasks in the VFT task may be set by the doctor itself according to the specific reaction tasks performed by the first subject, and may include, for example, one or more of the exact number, repetition number or error number of reactions the first subject makes as required within a prescribed time, which embodiment does not constitute a limitation to the specific behavioural data, but is merely regarded as one of the implementation modes.
In some embodiments of the present application, determining screening weights for each screening feature based on the correlation coefficients for each screening feature specifically includes: and carrying out equal ratio weight assignment on each screening feature according to the correlation coefficient of each screening feature. For example, taking the significant features as the average blood oxygen concentration of the left occipital lobe and the right occipital lobe as an example, carrying out correlation analysis on the data of the first characteristic value and the second characteristic value of the average blood oxygen concentration of the left occipital lobe and the right occipital lobe of the healthy person and the mild cognitive impairment patient respectively based on Pearson correlation coefficients to obtain the correlation coefficients of the average blood oxygen concentration of the left occipital lobe and the average blood oxygen concentration of the right occipital lobe as r=0.2804 and p=0.0363 respectively; r= -0.2840, p= 0.0399, then the screening weight of the average blood oxygen concentration of the left occipital leaf and the right occipital leaf can be determined to be 0.2804 based on the correlation coefficient: 0.2840, the equal ratio weight assignment can be realized.
In some embodiments of the present application, the processor 102 is further configured to perform a correlation analysis on the first feature value and the second feature value of the salient feature and a reference value of a reference standard, so as to obtain a correlation coefficient of the salient feature, and when the correlation coefficient of the salient feature does not meet a preset condition, take the salient feature as a screening feature, and perform equal weight assignment on each screening feature. For example, based on Pearson correlation coefficients, correlation analysis is performed on the first feature value and the second feature value of each salient feature and the reference value of the reference standard, and if the correlation coefficients of each salient feature do not meet the preset conditions, the salient features can be directly used as screening features, and equal weight assignment is performed on each screening feature. Specifically, taking the remarkable characteristics as the average blood oxygen concentration of the left occipital lobe and the right occipital lobe as an example, if the Pearson correlation coefficient is used to calculate the correlation coefficient between the average blood oxygen concentration of the left occipital lobe and the right occipital lobe and the MOCA scale, and the obtained correlation coefficient r does not meet the preset condition, taking the average blood oxygen concentration of the left occipital lobe and the right occipital lobe as screening characteristics, and simultaneously, carrying out weight assignment on the weights of the average blood oxygen concentration of the left occipital lobe and the average blood oxygen concentration of the right occipital lobe according to the weight of 0.5, so that the effects of each screening characteristic on evaluating mild cognitive impairment occupy the same specific gravity.
In some embodiments of the present application, the processor 102 is further configured to, when determining the screening weight for each screening feature, pre-normalize each screening feature such that the individual variance of each screening feature is less than a preset variance. For example, the screening features may be normalized using a min-max normalization formula (reference De A, konar A, samanta A, et al An fNIRs study to classify stages of learning from visual stimuli using prefrontal hemodynamics [ C ]//2017 Third International Conference on Biosignals, images and Instrumentation (ICBSII). IEEE, 2017:1-7.) to reduce the effect of individual differences of the individual first subjects on the analysis results. And then multiplying each screening characteristic by each screening weight according to the correlation coefficient. The preset difference is not particularly limited, and can be set by a doctor.
In some embodiments of the present application, the screening feature comprises one or more of an average oxyhemoglobin concentration of the lower left leaflet, an average oxyhemoglobin concentration of the lower right leaflet, an average oxyhemoglobin concentration of the left occipital leaflet, and an average oxyhemoglobin concentration of the right occipital leaflet. Based on the screening characteristics, the accuracy and targeting of screening mild cognitive impairment can be improved. Based on the device 100 for screening analysis of mild cognitive impairment according to various embodiments of the present application, the efficiency and accuracy of screening a large-scale population can be improved, by sampling a part of population in the large-scale population as sample data, then screening analysis of the first subjects in the samples is performed to obtain screening features of mild cognitive impairment, which can be used for screening the large-scale population, and then screening of mild cognitive impairment is performed on the whole large-scale population based on the screening features, so that the screening efficiency is greatly improved, and the labor cost is reduced.
As shown in fig. 3, some embodiments of the present application also provide a system 300 for screening analysis of mild cognitive impairment, the system comprising a near infrared brain function imaging device 301 and an apparatus 302 for screening analysis of mild cognitive impairment as described in various embodiments of the present application. The system is configured to: the device is used for receiving first near infrared data of a preset brain region of a first examinee, which is acquired by the near infrared brain function imaging equipment 301, in the period of performing the VFT task, determining the screening characteristics according to the first near infrared data, acquiring the screening characteristics of a second examinee based on the second near infrared data of the preset brain region of the second examinee, which is acquired by the near infrared brain function imaging equipment 301, in the period of performing the VFT task, and acquiring a screening analysis result of the second examinee, which has a slight cognitive impairment disease tendency, based on the screening characteristics.
Specifically, for example, 100 healthy persons and 100 mild cognitive impairment patients as the first subjects perform the VFT task, and the overall VFT task includes a resting state of 1 minute and three kinds of reaction tasks, with a total duration of 4 minutes. Each category reaction task includes a rest time of 30s and a category reaction task time of 30s, which is 60s in total. During the rest time, the first examinee directly looks at the "+" sign on the screen, and the category reaction task, the first examinee completes corresponding operation according to the screen indication. In the category response task, the first subject is required to speak Chinese nouns of a specific category ("fruit", "ball", "animal") and to avoid repeating the phrase as much as possible. Recording the number of the given word groups, including the number of correct words meeting the requirements, the number of incorrect words not meeting the requirements and the number of repeated words, of the first testee in the process of executing the category reaction task so as to measure the task performance.
The method comprises the steps of processing recorded first subject behavioural data and first near infrared data, counting the correct word number, the wrong word number and the repeated word number in a category reaction task executed by a first subject, performing optical signal conversion on the first near infrared data, removing motion artifacts by using a spline interpolation and spike removal method, removing physiological noise such as respiratory heartbeat through filtering by a high-low pass filter (0.1 Hz and 0.01Hz respectively), converting optical density into oxyhemoglobin (HBO 2) and deoxyhemoglobin (HBR) concentrations according to a modified Beer-lambert law, calculating the HBO2 and HBR concentrations of all channels (71 channels) of the first subject in a task category reaction task stage (3 channels and 30 s), and respectively calculating the average blood oxygen concentration of each preset brain area, the variance of the average blood oxygen concentration of each preset brain area and the area under the blood oxygen concentration curve of each preset brain area according to preset brain area, and taking the average blood oxygen concentration of each preset brain area as candidate characteristics. For example, the average blood oxygen concentration of each preset brain region may be understood as the average blood oxygen concentration of a plurality of channels of each preset brain region.
And activating the difference of the concentration of HBO2 and HBR in the category task of each preset brain region of the first subject by using the independent sample t test, and taking the candidate characteristic with obvious difference as the obvious characteristic. This example study of the present application found that the parietal lobe (p=0.0084), left parietal lobe (p=0.0071), right parietal lobe (p=0.0044), left occipital lobe (p=0.0106) and right occipital lobe (p=0.0116) had HBO2 mean blood oxygen level activation characteristics that were significantly different between groups. By performing independent sample t-test of the area under the curve, the parietal lobe (p=0.0085), left parietal lobe (p=0.0072), right parietal lobe (p=0.0045), left occipital lobe (p=0.0107) and right occipital lobe (p=0.0117) were found to have significant area under the curve activation characteristics. Thus, the average blood oxygen concentration and the area under the curve of the left top leaflet, the right top leaflet, the left occipital leaflet, and the right occipital leaflet can be taken as significant features. And carrying out correlation analysis on MMSE, MOCA scale and behavioural data by using the Pearson correlation coefficient. The correlation coefficients r=0.2639, p=0.0494, r=0.2633, p=0.0499, the correlation coefficients r=0.2804, p=0.0363, r= -0.2840, p= 0.0339, and the correlation coefficients r=0.2641, p=0.492, respectively, obtained by performing correlation analysis on the average blood oxygen concentration of the left and right occipital leaves and the number of wrong words. The mean blood oxygen concentrations of the left top leaflet, right top leaflet, left occipital leaflet and right occipital leaflet were then used as screening features and as per 0.2639:0.2633:0.2804:0.2840:0.2641 performing equal-ratio weight assignment to obtain a weight value=0.19: 0.19:0.215:0.215:0.19, wherein the two specific gravities of the left occipital lobe are 0.215 and 0.19, respectively, then add to 0.405, i.e. the specific gravity of the last 4 brain regions is the left top lower leaflet: lower right top leaflet: left occipital leaf: right occipital leaf = 0.19:0.19:0.405:0.215 to obtain screening characteristics after weight assignment, and then inputting the screening characteristics after weight assignment into a LDA (Linear Discriminant Analysis) linear classifier, and classifying mild cognitive impairment based on the average blood oxygen concentration of the left top lower leaflet, the right top lower leaflet, the left occipital leaflet and the right occipital leaflet of the first subject of each sample, wherein the results are shown in a column B of table 1. To demonstrate the advantages of the embodiments of the present application, the significant features that were not subjected to correlation analysis and were not weighted were input into the LDA linear classifier for analysis against significant features, and the results are shown in column a of table 1.
TABLE 1 LDA Linear Classification results
Therefore, based on the technical scheme provided by the embodiment of the application, the accuracy, the sensitivity and the specificity of screening the mild cognitive impairment can be greatly improved, and the accuracy of screening the mild cognitive impairment can be improved based on the screening characteristics and considering the weight of the screening characteristics.
In this embodiment, the first and second subjects may be the same or different, e.g., the first subject may be part or all of the second subject. After obtaining the screening feature based on the first subject, a second subject may be screened for mild cognitive impairment based on the screening feature, specifically, second near infrared data of the second subject may be obtained based on the near infrared brain function imaging device 301, and screening features of each second subject, in which weight is considered, may be respectively input into a classifier for analysis, and a screening analysis result regarding a predisposition to mild cognitive impairment may be obtained, for example, a probability that the second subject has a predisposition to mild cognitive impairment may be given to 80%. The doctor can count the mild cognitive impairment predisposition of each second subject according to the screening analysis result, and carry out subsequent detailed disease analysis and treatment.
Analysis, computation of near infrared data acquired by near infrared brain function imaging device 301 is performed using a processor, which may be a processing device including one or more general purpose processing devices, such as a microprocessor, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or the like. More specifically, the processor may be a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, a processor running other instruction sets, or a processor running a combination of instruction sets. The processor may also be one or more special purpose processing devices such as an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), a system on a chip (SoC), or the like. The processor may be included in the near infrared brain function imaging device 301 or may be disposed outside the near infrared brain function imaging device 301, and perform related data analysis and processing in cooperation with the near infrared brain function imaging device 301.
The present application describes various operations or functions that may be implemented or defined as software code or instructions. Such content may be source code or differential code ("delta" or "patch" code) that may be executed directly ("first subject" or "executable" form). The software code or instructions may be stored in a computer readable storage medium and, when executed, may cause a machine to perform the functions or operations described and include any mechanism that stores information in a form accessible by a machine (e.g., computing device, electronic system, etc.), such as recordable or non-recordable media (e.g., read Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, etc.).
The exemplary methods described herein may be implemented at least in part by a machine or computer. In some embodiments, a computer readable storage medium has stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps performed by the processor in the apparatus for screening analysis of mild cognitive impairment described in various embodiments of the present application. Implementation of such steps may include software code, such as microcode, assembly language code, higher-level language code, or the like. Various software programming techniques may be used to create various programs or program modules. For example, program portions or program modules may be designed in or with the aid of Java, python, C, C ++, assembly language, or any known programming language. One or more of such software portions or modules may be integrated into a computer system and/or computer readable medium. Such software code may include computer readable instructions for performing various methods. The software code may form part of a computer program product or a computer program module. Furthermore, in examples, the software code may be tangibly stored on one or more volatile, non-transitory, or non-volatile tangible computer-readable media, such as during execution or at other times. Examples of such tangible computer-readable media may include, but are not limited to, hard disks, removable magnetic disks, removable optical disks (e.g., optical disks and digital video disks), magnetic cassettes, memory cards or sticks, random Access Memories (RAMs), read Only Memories (ROMs), and the like.
Furthermore, although exemplary embodiments have been described herein, the scope thereof includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of the various embodiments across), adaptations or alterations as pertains to the present application. Elements in the claims are to be construed broadly based on the language employed in the claims and are not limited to examples described in the present specification or during the practice of the present application, which examples are to be construed as non-exclusive. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the above detailed description, various features may be grouped together to streamline the application. This is not to be interpreted as an intention that the disclosed features not being claimed are essential to any claim. Rather, the subject matter of the present application is capable of less than all of the features of a particular disclosed embodiment. Thus, the claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with one another in various combinations or permutations. The scope of the application should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application, the scope of which is defined by the claims. Various modifications and equivalent arrangements may be made to the present application by those skilled in the art, which modifications and equivalents are also considered to be within the scope of the present application.
Claims (10)
1. An apparatus for screening analysis of mild cognitive impairment, the apparatus comprising:
an interface configured to receive near infrared data of a preset brain region of a preset number of first subjects acquired via a near infrared brain function imaging device during performance of a VFT task, wherein the first subjects include healthy persons and mild cognitive impairment patients;
a processor configured to:
acquiring blood oxygen concentration data of a preset brain region of the first detected person in the preset quantity during the reaction task in the VFT task based on the near infrared data, and acquiring first characteristic values of a plurality of candidate characteristics of each brain region of each healthy person and second characteristic values of corresponding candidate characteristics of each brain region of each mild cognitive impairment patient based on the blood oxygen concentration data;
performing a degree of difference analysis on the first feature value and the second feature value of each candidate feature to extract therefrom salient features whose degree of significance is above a difference threshold;
performing correlation analysis on the first characteristic value and the second characteristic value of the salient features and the reference value of the reference standard to obtain correlation coefficients of the salient features, and taking the salient features of which the correlation coefficients meet preset conditions as screening features;
determining screening weights of the screening features based on the correlation coefficients of the screening features;
and combining each screening characteristic with the corresponding screening weight for screening analysis of mild cognitive impairment.
2. The device of claim 1, wherein the pre-set brain region comprises at least one or more of a left forehead lobe, a medial forehead lobe, a right forehead lobe, a left temporal lobe, a top lobe, a right temporal lobe, a left top inferior leaflet, a right top inferior leaflet, a left occipital lobe, a right occipital lobe.
3. The apparatus of claim 1, wherein the candidate features comprise at least one or more of an average blood oxygen concentration for each preset brain region, a variance of the average blood oxygen concentration for each preset brain region, and an area under a blood oxygen concentration curve for each preset brain region.
4. The apparatus of claim 1, wherein the reference criteria comprises a scale for screening for mild cognitive impairment and/or behavioural data of the first subject during performance of a reaction task in a VFT task.
5. The apparatus of claim 1, wherein determining screening weights for each screening feature based on correlation coefficients for each screening feature comprises: and carrying out equal ratio weight assignment on each screening feature according to the correlation coefficient of each screening feature.
6. The apparatus of claim 1, wherein the processor is further configured to:
and carrying out correlation analysis on the first characteristic value and the second characteristic value of the salient features and the reference value of the reference standard to obtain the correlation coefficient of the salient features, taking the salient features as screening features under the condition that the correlation coefficient of the salient features does not meet the preset condition, and carrying out equal weight assignment on each screening feature.
7. The apparatus of claim 1 or 6, wherein the processor is further configured to:
when the screening weight is determined for each screening feature, the standardization processing is performed on each screening feature in advance so that the individual difference of each screening feature is smaller than the preset difference.
8. The device of claim 1, wherein the screening feature comprises one or more of an average oxyhemoglobin concentration of a lower left leaflet, an average oxyhemoglobin concentration of a lower right leaflet, an average oxyhemoglobin concentration of a left occipital leaflet, and an average oxyhemoglobin concentration of a right occipital leaflet.
9. A system for screening analysis of mild cognitive impairment, comprising a near infrared brain function imaging device and apparatus for screening analysis of mild cognitive impairment according to any one of claims 1-8;
the system is configured to:
receiving first near infrared data of a preset brain region of a first examinee in a preset quantity acquired by the near infrared brain function imaging equipment during the process of performing the VFT task by using the device, and determining the screening characteristics according to the first near infrared data;
acquiring screening characteristics of a second subject based on second near infrared data of a preset brain region of the second subject during the execution of the VFT task, wherein the second near infrared data is acquired by the near infrared brain function imaging device;
based on the screening characteristics, screening analysis results are obtained for the second subject having a predisposition for mild cognitive impairment.
10. A computer readable storage medium, characterized in that it stores a computer program which, when executed by a processor, causes the processor to perform the steps performed by the processor in the apparatus for screening analysis of mild cognitive impairment according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310382323.0A CN116110599A (en) | 2023-04-12 | 2023-04-12 | Apparatus, system and storage medium for screening analysis of mild cognitive impairment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310382323.0A CN116110599A (en) | 2023-04-12 | 2023-04-12 | Apparatus, system and storage medium for screening analysis of mild cognitive impairment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116110599A true CN116110599A (en) | 2023-05-12 |
Family
ID=86262014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310382323.0A Pending CN116110599A (en) | 2023-04-12 | 2023-04-12 | Apparatus, system and storage medium for screening analysis of mild cognitive impairment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116110599A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190167179A1 (en) * | 2016-08-07 | 2019-06-06 | Hadasit Medical Research Services And Development Ltd. | Methods and system for assessing a cognitive function |
| TW201938109A (en) * | 2018-03-19 | 2019-10-01 | 財團法人祺華教育基金會 | Biological marker and method for evaluating mild cognitive impairment based on changes of the blood oxygen concentration of the frontal lobe |
| CN112022136A (en) * | 2020-09-11 | 2020-12-04 | 国家康复辅具研究中心 | Near-infrared brain function and gait parameter based assessment method and system |
| CN112561935A (en) * | 2020-12-26 | 2021-03-26 | 广东工业大学 | Method, device and equipment for identifying Alzheimer's disease |
| CN114974566A (en) * | 2022-05-23 | 2022-08-30 | 国家康复辅具研究中心 | Cognitive function assessment method and system |
| CN115590465A (en) * | 2021-07-08 | 2023-01-13 | 丹阳慧创医疗设备有限公司（Cn） | Diagnosis device, diagnosis equipment and diagnosis system for cognitive disorder |
-
2023
- 2023-04-12 CN CN202310382323.0A patent/CN116110599A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190167179A1 (en) * | 2016-08-07 | 2019-06-06 | Hadasit Medical Research Services And Development Ltd. | Methods and system for assessing a cognitive function |
| TW201938109A (en) * | 2018-03-19 | 2019-10-01 | 財團法人祺華教育基金會 | Biological marker and method for evaluating mild cognitive impairment based on changes of the blood oxygen concentration of the frontal lobe |
| CN112022136A (en) * | 2020-09-11 | 2020-12-04 | 国家康复辅具研究中心 | Near-infrared brain function and gait parameter based assessment method and system |
| CN112561935A (en) * | 2020-12-26 | 2021-03-26 | 广东工业大学 | Method, device and equipment for identifying Alzheimer's disease |
| CN115590465A (en) * | 2021-07-08 | 2023-01-13 | 丹阳慧创医疗设备有限公司（Cn） | Diagnosis device, diagnosis equipment and diagnosis system for cognitive disorder |
| CN114974566A (en) * | 2022-05-23 | 2022-08-30 | 国家康复辅具研究中心 | Cognitive function assessment method and system |
Non-Patent Citations (1)
| Title |
|---|
| YIZHU TIAN等: "Decreased Hemodynamic Responses in Left Parietal Lobule and Left Inferior Parietal Lobule in Older Adults with Mild Cognitive Impairment: A Near-Infrared Spectroscopy Study", JOURNAL OF ALZHEIMER’S DISEASE, vol. 90, no. 3, pages 1163 - 1175 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022256063A1 (en) | Predictive prognosis based on multimodal analysis | |
| Noirhomme et al. | “Look at my classifier's result”: Disentangling unresponsive from (minimally) conscious patients | |
| US20210022670A1 (en) | Systems and methods for diagnosing sleep | |
| Buettner et al. | High-performance diagnosis of sleep disorders: a novel, accurate and fast machine learning approach using electroencephalographic data | |
| CN111466876B (en) | Alzheimer's disease auxiliary diagnosis system based on fNIRS and graph neural network | |
| CN109770921B (en) | Method and device for screening early stage language and cognitive ability of autistic children | |
| Campbell et al. | Pharmacologically informed machine learning approach for identifying pathological states of unconsciousness via resting-state fMRI | |
| CN111568446A (en) | Portable electroencephalogram depression detection system combined with demographic attention mechanism | |
| EP3493736B1 (en) | System for detecting acute brain function impairment | |
| Baumgartl et al. | Detecting Antisocial Personality Disorder Using a Novel Machine Learning Algorithm Based on Electroencephalographic Data. | |
| Rafiei et al. | Automated detection of major depressive disorder with EEG signals: a time series classification using deep learning | |
| CN106974660B (en) | Method for realizing gender judgment based on blood oxygen characteristics in brain function activity detection | |
| EP4139933A1 (en) | Method and system for estimating early progression of dementia from human head images | |
| Ma et al. | Distinguishing bipolar depression from major depressive disorder using fnirs and deep neural network | |
| Laskaris et al. | Improved detection of amnestic MCI by means of discriminative vector quantization of single-trial cognitive ERP responses | |
| Eken | Assessment of flourishing levels of individuals by using resting-state fNIRS with different functional connectivity measures | |
| Park et al. | Effects of daily stress in mental state classification | |
| Li et al. | A face image classification method of autistic children based on the two-phase transfer learning | |
| Zuo et al. | Deep Learning-based Eye-Tracking Analysis for Diagnosis of Alzheimer's Disease Using 3D Comprehensive Visual Stimuli | |
| Posada-Quintero et al. | Autism spectrum disorder detection using variable frequency complex demodulation of the electroretinogram | |
| JP6404162B2 (en) | Brain function index calculation device and brain function index calculation method | |
| Yoo et al. | Hemodynamics analysis of patients with mild cognitive impairment during working memory tasks | |
| Lombardi et al. | Detecting sepsis from photoplethysmography: strategies for dataset preparation | |
| Boppana et al. | Deep Learning Approach for an early stage detection of Neurodevelopmental Disorders | |
| CN116110599A (en) | Apparatus, system and storage medium for screening analysis of mild cognitive impairment |
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 |