KR20230110386A - Eeg-based parkinson's subtype classification device - Google Patents

Abstract

The present invention relates to a brain wave-based parkinson's subtype classification method, which includes the steps of: an EEG signal reception step of acquiring EEG signals which appear according to changes in time of a user; an EEG feature generation step of generating EEG features by frequency analyzing the EEG signal; and a subtype determination step of determining the user's Parkinson's disease subtype by inputting the brain wave features into a Parkinson's subtype classification model.

Description

EEG-BASED PARKINSON'S SUBTYPE CLASSIFICATION DEVICE}

The present invention relates to an EEG-based Parkinson's subtype classification method, and more particularly, may include an EEG signal receiving step of acquiring an EEG signal appearing according to a change in time of a user, an EEG feature generating step of generating an EEG feature by frequency analysis of the EEG signal, and a subtype determining step of inputting the EEG feature into a Parkinson's subtype classification model to determine the user's Parkinson's disease subtype.

Parkinson's disease is a slowly progressive neurodegenerative disease without a clear cause. Pathologically, loss of nerve cells and proliferation of glial cells (cells that help nerve cells perform their functions without performing nerve transmission) are observed in the substantia nigra or blue plaque.

Parkinson's disease, along with dementia, is one of the two major neurodegenerative diseases of the elderly, and its incidence is increasing worldwide with the aging of the population. In addition, Parkinson's disease does not only occur in the elderly, but about 20% of patients are young people under the age of 50, so the seriousness is being highlighted.

In Parkinson's disease, tremor is said to be the first symptom, but many patients complain of vague symptoms that are difficult to explain (such as abnormal sensations, muscle pain, and muscle spasms).

As Parkinson's disease progresses, it is difficult to perform independent daily life, social activities are restricted, and accompanied by non-motor symptoms such as cognitive dysfunction, autonomic nervous disorder, and pain, which easily reduce the patient's quality of life.

In fact, the quality of life of patients with Parkinson's disease was confirmed to be 14% lower on average than that of stroke patients, the same geriatric disease, and it was reported that it was lower in all areas compared to diabetic patients.

In addition, Parkinson's disease not only causes physical motor function decline, but also suffers from mental symptoms such as anxiety, apathy, depression and dementia. Therefore, it is reported that patients with Parkinson's disease are up to six times more likely to develop dementia than normal people, and their mortality rate is three times higher.

In addition, the economically active population ratio of Parkinson's disease patients is 9 times higher than that of dementia, indicating that the patient's productivity decline has a significant impact on the household burden and the quality of life of the entire family. As a result of comparing and analyzing the 2016 disease statistics data of the Health Insurance Review and Assessment Service, in the case of dementia, the proportion of people in their 40s-50s out of a total of 359,705 patients was 1.3% (4,828), while in the case of Parkinson's disease, the proportion of people in their 40s-50s out of 96,499 patients was found to be 9.1% (8,816).

In addition, according to the survey, Parkinson's disease patients and their caregivers appeared to need 'active introduction and support of the latest treatment technology (62%)' the most, followed by 'reduction of the patient's burden of treatment costs (3 8%)' and 'Parkinson's disease patient family support service' (31%). In particular, the 'Patient Family Support Service' and 'Revitalization of Domestic Parkinson's Disease Research' had a relatively high percentage of requests from patients' guardians, and there was an opinion that the development of new treatment methods and new drugs was necessary.

However, despite the increasing incidence, it is a reality that is not receiving social attention. In particular, according to the investigation by the Parkinson's Disease Center at Ulasan Hospital, in Korea, Parkinson's disease was diagnosed only after an average of 18 months after the onset of symptoms. There is a problem that the suffering of patients and medical expenses are wasted.

A problem in the treatment of Parkinson's disease is that it is difficult to distinguish specific subtypes of patients.

Korean Patent Publication No. 10-2014-0049583 (2015.11.04)

An embodiment of the present invention relates to an EEG-based Parkinson's subtype classification method for distinguishing a Parkinson's subtype of a patient through EEG measurement of the patient based on a model capable of discriminating the subtype of Parkinson's disease.

An EEG-based Parkinson's subtype classification method according to an embodiment of the present invention includes an EEG signal reception step of acquiring an EEG signal that appears according to a user's time change, an EEG feature generation step of generating an EEG feature by frequency-analyzing the EEG signal; and determining a Parkinson's disease subtype of the user by inputting the EEG feature into a Parkinson's subtype classification model.

The EEG feature may include a reference feature determined as a feature for classifying a Parkinson's subtype in the Parkinson's subtype classification model.

An EEG noise removal step of removing noise included in the EEG signal may be further included.

The Parkinson's subtype is defined based on the treatment agent, and may include a first Parkinson's type, a second Parkinson's type, ... and an nth Parkinson's type.

The disclosed technology may have the following effects. However, it does not mean that a specific embodiment must include all of the following effects or only the following effects, so it should not be understood that the scope of rights of the disclosed technology is limited thereby.

The EEG-based Parkinson's subtype classification method according to an embodiment of the present invention can discriminate the Parkinson's subtype of a patient by measuring the EEG of the patient based on a model capable of discriminating the subtype of Parkinson's disease.

1 is a diagram illustrating an EEG-based Parkinsonian subtype classification system according to an embodiment of the present invention.
2 is a diagram illustrating a physical configuration of an EEG-based Parkinsonian subtype classification method according to an embodiment.
3 is a diagram illustrating a functional configuration of an EEG-based Parkinsonian subtype classification method according to an embodiment.

Since the description of the present invention is only an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiment can be changed in various ways and can have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, the scope of the present invention should not be construed as being limited thereto.

Meanwhile, the meaning of terms described in this application should be understood as follows.

Terms such as "first" and "second" are used to distinguish one component from another, and the scope of rights should not be limited by these terms. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected to the other element, but other elements may exist in the middle. On the other hand, when an element is referred to as being "directly connected" to another element, it should be understood that no intervening elements exist. Meanwhile, other expressions describing the relationship between components, such as “between” and “immediately between” or “adjacent to” and “directly adjacent to” should be interpreted similarly.

Singular expressions should be understood to include plural expressions unless the context clearly dictates otherwise, and terms such as "comprise" or "having" are intended to designate that an embodied feature, number, step, operation, component, part, or combination thereof exists, and it should be understood that the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof is not precluded.

In each step, the identification code (eg, a, b, c, etc.) is used for convenience of explanation, and the identification code does not describe the order of each step, and each step is context-specific. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be implemented as computer readable code on a computer readable recording medium, and the computer readable recording medium includes all types of recording devices storing data that can be read by a computer system. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like, and also include those implemented in the form of carrier waves (for example, transmission through the Internet). In addition, the computer-readable recording medium may be distributed to computer systems connected through a network, so that computer-readable codes may be stored and executed in a distributed manner.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless defined otherwise. Terms defined in commonly used dictionaries should be interpreted as consistent with meanings in the context of the related art, and cannot be interpreted as having ideal or excessively formal meanings unless explicitly defined in the present application.

1 is a diagram illustrating an EEG-based Parkinsonian subtype classification system 100 according to an embodiment of the present invention.

Referring to FIG. 1 , an EEG-based Parkinson's subtype classification system 100 may include a user terminal 110, an EEG-based Parkinson's subtype classification apparatus 130, and a database 150.

The user terminal 110 may be implemented as a smart phone or a wearable device capable of checking EEG data collected through the EEG-based Parkinsonian subtype classification device 130 and metadata analyzed therefrom, but is not limited thereto, and may also be implemented in various devices such as a tablet PC. The user terminal 110 may be connected to the brain wave-based Parkinson's subtype classification device 130 through a network, and a plurality of user terminals 110 may be simultaneously connected to the brain wave-based Parkinson's subtype classification device 130.

The brain wave-based Parkinsonian subtype classification apparatus 130 receives external data, performs omnidirectional learning and reinforcement learning on the external data, and sequentially performs steps to advance the model through this. It can be implemented as a server corresponding to a computer or program. The brain wave-based Parkinsonian subtype classification device 130 may be wirelessly connected to the user terminal 110 through Bluetooth, WiFi, or a communication network, and may exchange data with the user terminal 110 through the network.

The database 150 receives external data, performs forward learning and reinforcement learning on the external data, sequentially performs steps to advance the model through this, and stores various information generated through the above process. It may correspond to a storage device. In addition, the database 150 may store information collected or processed in various forms in the process of sequentially performing steps in which the brain wave-based Parkinson's subtype classification apparatus 130 receives external data, receives the external data, performs omnidirectional learning and reinforcement learning on the corresponding external data, and thereby advances the model.

2 is a diagram illustrating a physical configuration of an apparatus 130 for classifying Parkinson's subtypes based on brain waves according to an embodiment.

Referring to FIG. 2 , an apparatus 130 for classifying Parkinson's subtypes based on brain waves may be implemented by including a processor 210, a memory 230, a user input/output unit 250, and a network input/output unit 270.

The processor 210 may execute a procedure that converts the received EEG, extracts EEG features through conversion of the EEG composed of time-series data, analyzes the EEG features, and classifies the Parkinsonian subtype of the patient, manages the memory 230 that is read or written throughout the process, and schedules a synchronization time between volatile memory and non-volatile memory in the memory 230. The processor 210 may control the overall operation of the apparatus 130 for classifying Parkinson's subtype based on brain waves, and is electrically connected to the memory 230, the user input/output unit 250, and the network input/output unit 270 to control data flow between them. The processor 210 may be implemented as a central processing unit (CPU) of the apparatus 130 for classifying Parkinson's subtypes based on brain waves.

The memory 230 may include an auxiliary memory implemented as a non-volatile memory such as a solid state drive (SSD) or a hard disk drive (HDD) and used to store all data necessary for the brain wave-based Parkinson's subtype classification device 130, and may include a main memory implemented as a volatile memory such as random access memory (RAM).

The user input/output unit 250 may include an environment for receiving user input and an environment for outputting specific information to the user. For example, the user input/output unit 250 may include an input device including an adapter such as a touch pad, a touch screen, an on-screen keyboard, or a pointing device, and an output device including an adapter such as a monitor or touch screen. In one embodiment, the user input/output unit 250 may correspond to a computing device connected through a remote connection, and in such a case, the brain wave-based Parkinson's subtype classification device 130 may be implemented as a server.

The network input/output unit 270 includes an environment for connecting to an external device or system through a network, and may include, for example, adapters for communication such as a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a value added network (VAN).

3 is a diagram illustrating a functional configuration of an apparatus 130 for classifying Parkinson's subtypes based on brain waves according to an embodiment. Referring to FIG. 3 , the apparatus for classifying Parkinson's subtypes based on EEG may include an EEG signal receiver 310, an EEG feature generator 320, a subtype determiner 330, and an EEG noise removal unit 340.

The EEG signal receiving unit 310 may obtain an EEG signal that appears according to the user's time change. Here, the EEG signal receiving unit 310 may include a plurality of channels (2, 4, 8, 16, 19, 24, 68, 128, or 256 caps or individual electrodes attached) attached to different positions of the head of the first user, and may be a device for measuring independent EEG signals through each channel according to the EEG measurement 10-20 system, and may collect a plurality of EEG signals through each of the plurality of channels. . For example, the EEG signal receiver 310 may include 19 channels (eg, Fp1, Fp2, F3, F4, C3, C4, P3, P4, O1, O2, F7, F8, T3, T4, T5, T6, Fz, Cz, Pz) (where Fz, Cz, and Pz are common channels), and measure 19 independent EEG signals through the 19 channels. You can.

In various embodiments, the computing device may collect a plurality of EEG signals measured in a normal state in which the first user is not performing a separate operation through the EEG signal receiver 310, but is not limited thereto, and may collect a plurality of EEG signals measured in the process of taking various actions or performing various tests.

The EEG feature generation unit 320 may generate EEG features by frequency-analyzing the EEG signal. Here, frequency analysis may mean representing time series data as frequency data through Fourier analysis. The EEG feature generating unit 320 determines the location of the scalp electrodes according to the 10-20 electrode method (10-20 System) as the EEG generation location, and classifies and determines the EEG frequency bands into delta, theta, alpha, beta, and gamma according to the frequency components of the EEG signal. The 10-20 electrode method (10-20 System) may correspond to a representative method for defining locations of scalp electrodes for measuring brain waves. '10' and '20' may correspond to the fact that the actual distance between adjacent electrodes is 10% or 20% of the total anteroposterior or lateral distance of the skull. The location of each electrode can be expressed as frontal lobe (Fp), frontal lobe (F), temporal lobe (T), parietal lobe (P), occipital lobe (O), and center (C). In addition, the EEG frequency band may be defined as delta 0 ~ 4 Hz, theta 4 ~ 8 Hz, alpha 8 ~ 13 Hz, beta 13 ~ 30 Hz, and gamma 30 ~ 50 Hz. For example, the feature set definition unit 310 may define a specific feature as 'Fp1d', and in this case, the corresponding feature may correspond to a signal value of a delta wave measured at the position of the Fp1 electrode.

The Parkinson's subtype classification model may include a reference feature determined as a feature for classifying the Parkinson's subtype. A feature may correspond to information about characteristics that specify data.

The subtype determiner 330 may determine the subtype of Parkinson's disease of the user by inputting the EEG features to a Parkinson's subtype classification model. The subtype determiner 330 may generate a dimensionally specific feature combination using various features defined as a feature set. In this case, the dimension may correspond to the number of features constituting the feature combination. For example, a one-dimensional feature combination may consist of one feature, and a two-dimensional feature combination may consist of two features.

The EEG noise removal unit 340 may remove noise included in the EEG signal. The EEG noise removal unit 340 may filter EEG signals of a specific frequency band by pre-processing a plurality of EEG signals. For example, the EEG noise remover 340 may extract only EEG signals corresponding to frequency bands in the range of 1 to 45 Hz by filtering unnecessary frequency bands or frequency bands that may be susceptible to noise among a plurality of EEG signals (e.g., EEG signals corresponding to frequency bands below 4 Hz and EEG signals corresponding to frequency bands above 45 Hz).

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention without departing from the spirit and scope of the present invention described in the claims below. It will be understood that it can be changed.

100: EEG-based Parkinson's subtype classification system
110: user terminal
130: EEG-based Parkinsonian subtype classification device
150: database
210: processor 230: memory
250: user input/output unit 270: network input/output unit
310: EEG signal receiver 320: EEG feature generator
330: subtype determination unit 340: EEG noise removal unit

Claims (3)

an EEG signal receiving unit for obtaining an EEG signal that appears according to a user's time change;
an EEG feature generation unit generating EEG features by frequency-analyzing the EEG signal; and
and an EEG-based Parkinson's subtype classification apparatus comprising a subtype determiner configured to input the brain wave features into a Parkinson's subtype classification model to determine the Parkinson's disease subtype of the user.
According to claim 1,
The brain wave feature,
Including a reference feature determined as a feature for classifying a Parkinson's subtype in the Parkinson's subtype classification model;
EEG-based Parkinsonian subtype classification apparatus further comprising an EEG noise removal unit for removing noise included in the EEG signal.
According to claim 2,
The Parkinson's subtype,
An apparatus for classifying Parkinson's subtypes based on EEG, characterized in that it is defined based on a therapeutic drug and includes a first Parkinson type, a second Parkinson type, ... and an n-th Parkinson type.