CN113208620A

CN113208620A - Sleep stage based Alzheimer disease screening method and system

Info

Publication number: CN113208620A
Application number: CN202110365837.6A
Authority: CN
Inventors: 沈阳; 卢树强; 王晓岸
Original assignee: Beijing Brain Up Technology Co ltd
Current assignee: Beijing Brain Up Technology Co ltd
Priority date: 2021-04-06
Filing date: 2021-04-06
Publication date: 2021-08-06

Abstract

The invention discloses a sleep stage-based Alzheimer's disease screening method and system, wherein the method comprises the following steps: BCI equipment collects an EEG signal in the sleeping process of a user and transmits the EEG signal to a sleep staging algorithm system; the sleep staging algorithm system extracts and analyzes the features of the EEG signal of the user, judges the sleep state and stages the sleep state; and the early screening system performs characteristic extraction and analysis on the sleep stage result to judge whether the user is in the early onset high risk stage of the Alzheimer's disease. The method realizes the discrimination of the early signs of the Alzheimer's disease, can early warn the high probability of the onset of the Alzheimer's disease in advance, effectively mediates early intervention, is convenient and quick, and is easy for large-scale screening.

Description

Sleep stage based Alzheimer disease screening method and system

Technical Field

The invention relates to the technical field of EEG signal identification, in particular to a sleep stage-based Alzheimer's disease screening method and system.

Background

Alzheimer's Disease (AD) is a progressive degenerative disease of the nervous system with occult onset. Clinically, the overall dementia such as dysmnesia, aphasia, disuse, agnosia, impairment of visual spatial skills, dysfunction in execution, and personality and behavior changes are characterized, and the etiology is unknown. Patients who are older than 65 years are called presenile dementia; the patient after 65 years old is called senile dementia. The clinical causes of AD mainly include family history, body disease induction, head trauma, immune function and other factors; the clinical manifestations are divided into three stages, which are mild dementia, hypomnesis, moderate dementia, severe hypomnesis, severe dementia and severe memory loss.

The current clinical examination methods for alzheimer's disease are: neuropsychological tests, mainly including the simple mental scale of memory levels (MMSE), daily living capacity Assessment (ADL), behavioral and mental state assessment (BPSD) scale, etc.; blood and cerebrospinal fluid examinations to screen organic pathogens; neuroimaging examination to screen for neurological organic lesions and trauma; electroencephalogram spectrum inspection; screening genes, and the like. The current inspection method has the problems that the neuropsychological scale test is a subjective questionnaire test, and the accuracy and the credibility are low; the gene detection cost is high, the implementation is not easy, and people carrying the genes which are easy to attack do not necessarily form the diagnosis factor of the early AD, so that unnecessary early intervention can be guided; the main common defects of the examination methods of neuropsychological scale test, blood and cerebrospinal fluid examination, neuroimaging examination and electroencephalogram spectrum examination are that the examination methods can only be applied to determining the degree of disease occurrence when AD has already suffered from diseases, namely clinical symptoms are already shown, and early screening and early treatment mediation cannot be achieved. Later examination does not reflect the screening significance of early intervention, so that the patient misses the optimal early intervention prediction.

In summary, in any of the above existing methods, it is difficult to perform reliable and easy-to-implement screening at an early stage, and the screening needs manual work, which requires a lot of labor cost, takes a long time, and is inefficient. Therefore, how to reduce labor cost and improve screening efficiency is an urgent problem to be solved.

Disclosure of Invention

The invention aims to provide a sleep stage-based Alzheimer's disease screening method and system, so that labor cost is reduced, screening efficiency is improved, early signs of Alzheimer's disease are judged, early warning on high probability of Alzheimer's disease onset can be carried out in advance, and early intervention can be effectively mediated.

In order to solve the technical problem, the invention provides a sleep stage-based Alzheimer's disease screening method, which comprises the following steps:

BCI equipment collects an EEG signal in the sleeping process of a user and transmits the EEG signal to a sleep staging algorithm system;

the sleep staging algorithm system extracts and analyzes the features of the EEG signal of the user, judges the sleep state and stages the sleep state;

and the early screening system performs characteristic extraction and analysis on the sleep stage result to judge whether the user is in the early onset high risk stage of the Alzheimer's disease.

Preferably, the features extracted for the EEG signal of the user comprise time domain features and frequency domain features of the EEG signal.

Preferably, the sleep state is judged and staged by using a convolutional neural network model.

Preferably, the sleep staging result includes time series data marked by a time axis and a data point during the sleep process.

Preferably, the features extracted from the sleep staging results include overall duration features, proportional relationships, starting positions, durations and degrees of dispersion of the stages, the number and duration of repetitions of the sleep cycle, whether the sleep cycle is typical and healthy, and whether the transitions of the stages of sleep are normal.

Preferably, a deep learning algorithm is adopted to judge whether the user is in an early stage of high risk of developing alzheimer disease, and the method specifically comprises the following steps:

(1) carrying out grading labeling on early signs of the Alzheimer disease, and respectively representing the incidence probability of the Alzheimer disease; (2) judging to obtain a morbidity probability result model by using a convolutional neural network and taking the extracted features of the sleep stage result as input; (3) and applying a generation model, and generating a disease incidence prediction result by taking the disease incidence rate grade obtained by the disease incidence probability result model evaluation and the characteristics of the sleep stage result as input.

The invention also provides a sleep stage-based Alzheimer's disease screening system, which is used for realizing the method and comprises the following steps:

the BCI equipment is used for collecting an EEG signal in the sleeping process of a user and transmitting the EEG signal to the sleep staging algorithm system;

the sleep staging algorithm system is used for carrying out feature extraction and analysis on an EEG signal of a user, judging a sleep state and staging the sleep state;

and the early screening system is used for extracting and analyzing the features of the sleep stage results and judging whether the user is in the early stage high risk stage of the Alzheimer disease.

According to the sleep stage-based Alzheimer's disease screening method and system, the sleep state is judged and the stage is divided by extracting and analyzing the features of the EEG signals of the user, and the sleep stage result is extracted and analyzed to judge whether the early-stage onset of Alzheimer's disease is in a high-risk stage, so that the early-stage symptoms of Alzheimer's disease are judged, early warning on the high-probability onset of Alzheimer's disease can be realized in advance, early intervention is effectively mediated, namely the early-stage symptoms of Alzheimer's disease are judged by utilizing the EEG signals, manual screening is not needed, the labor cost is reduced, and the screening efficiency is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a flowchart of an implementation of a sleep stage-based Alzheimer's disease screening method provided by the present invention;

FIG. 2 is a schematic diagram of a sleep staging algorithm;

FIG. 3 is a schematic diagram of the prediction of disease onset;

fig. 4 is a schematic structural diagram of a sleep stage-based alzheimer's disease screening system provided by the present invention.

Detailed Description

The core of the invention is to provide a sleep stage-based Alzheimer's disease screening method and system, so that labor cost is reduced, screening efficiency is improved, early signs of Alzheimer's disease are judged, early warning on high probability of Alzheimer's disease onset can be carried out in advance, and early intervention can be effectively mediated.

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The invention provides a sleep stage-based Alzheimer's disease screening method, which comprises the following steps:

s11: BCI equipment collects an EEG signal in the sleeping process of a user and transmits the EEG signal to a sleep staging algorithm system;

s12: the sleep staging algorithm system extracts and analyzes the features of the EEG signal of the user, judges the sleep state and stages the sleep state;

wherein the features extracted for the EEG signal of the user comprise time domain features and frequency domain features of the EEG signal. And judging the sleep state by using a convolutional neural network model and staging.

S13: and the early screening system performs characteristic extraction and analysis on the sleep stage result to judge whether the user is in the early onset high risk stage of the Alzheimer's disease.

The sleep staging result comprises time sequence data which takes a time axis as a mark and takes the staging result as a data point in the sleep process. The features extracted from the sleep stage result include the overall duration feature, the proportional relation, the initial position, the duration and the dispersion degree of each stage, the repetition number and the duration of the sleep cycle, whether the sleep cycle is typical and healthy, and whether the conversion of each stage of sleep is normal.

Wherein, adopt the deep learning algorithm to judge whether the user is in the early high risk stage of onset of Alzheimer's disease, specific process includes:

Therefore, in the method, the sleep state is judged and staged through characteristic extraction and analysis of the EEG signals of the user, and the sleep stage result is subjected to characteristic extraction and analysis to judge whether the early-stage onset of the Alzheimer disease is in a high-risk stage, so that the early-stage symptoms of the Alzheimer disease are judged, early warning can be performed on the high-probability onset of the Alzheimer disease in advance, early intervention is effectively mediated, namely the early-stage symptoms of the Alzheimer disease are judged by utilizing the EEG signals, manual screening is not needed, the labor cost is reduced, and the screening efficiency is improved. The specific implementation process of the method is referred to fig. 1.

Referring to fig. 1, in the present embodiment, the portable BCI device in fig. 1 is preferably a dry electrode high-precision EEG acquisition device, electrodes of the device are symmetrically distributed in the frontal lobe or frontal lobe, electrode points are symmetrically distributed left and right, and the electrodes have a higher sampling rate, so that accurate depiction, denoising, filtering, amplifying, encoding and transmitting of electroencephalogram signals can be satisfied; the device mainly comprises a biosensor, a front-end circuit device and the like.

The portable BCI equipment is used for collecting EEG data in the sleep process of a tested evening, and the method specifically comprises the following steps: 1. the portable BCI equipment is worn, positioned and impedance is adjusted, so that the forehead and the stable spontaneous scalp electroencephalogram of the forehead can be acquired; 2. and (4) amplifying, coding and transmitting the electroencephalogram signals.

Analyzing the night sleep state of the testee and extracting the characteristics through a sleep staging algorithm system, and the method comprises the following specific steps:

1. receiving 6-channel signal data transmitted by the portable BCI equipment through a Bluetooth system;

2. denoising and filtering, namely filtering the original data by adopting a filtering algorithm, and filtering high-frequency and low-frequency artifacts, power frequency interference, eye electrical noise and other noises in the original data to obtain a pure electroencephalogram signal;

3. and extracting the characteristics of the electroencephalogram signals. The code extraction algorithm can be deployed at the cloud, data is uploaded to the cloud through terminal equipment for analysis, and the code extraction algorithm can also be directly deployed at the terminal or the front end. Preferably, in order to increase the operation speed and reduce the operation cost, the embodiment adopts a cloud deployment algorithm for calculation; the features extracted in this step include time domain and frequency domain features, preferably, the time domain features are: complete waveform images and rasterized data within 30 seconds; the frequency domain characteristics are: FFT result of 30 seconds sliding window average, including power spectrum function, power spectrum slope; specific frequency band power spectrum ratio and the like;

4. and judging the sleep state and staging the sleep. Preferably, an SVM support vector machine model may be adopted to judge whether the subject is in a sleep state through EEG data, and then a deep learning algorithm and a convolutional neural network model are adopted to classify the EEG data in the sleep state, specifically, the classification result is:

REM rapid eye movement sleep state, accounting for about 20% of data volume;

NREM1 phase (light sleep phase), accounting for approximately 15% of sleep;

NREM2 phase (mid sleep phase), accounting for approximately 40% of sleep;

stage NREM3-4 (deep sleep period), accounting for approximately 25% of sleep.

5. The sleep staging results are transmitted to an AD screening algorithm system, and the transmission mode is not limited to network protocol transmission, Bluetooth transmission, WIFI transmission and the like; depending on where the two systems are arranged separately; in the scheme, the AD screening system and the sleep staging system are both arranged at the cloud end, so that data is directly transmitted through a network protocol or does not need to be transmitted; the transmitted sleep staging content comprises time series data which is marked by a time axis and takes staging results as data points for sleeping all night. Please refer to fig. 2 for a schematic diagram of a sleep staging algorithm.

Through the early screening system of Alzheimer's disease, carry out analysis, feature extraction to whole night sleep stage result, judge whether be in AD early stage high risk stage of onset, concrete step includes:

1. and performing feature extraction on the sleep staging result data. The main extracted features include: (1) overall duration characteristics, proportional relation, initial position, duration and scattering degree of each stage; (2) the number and duration of sleep cycle repetitions, whether the sleep cycle is typical and healthy; (3) whether the conversion of each stage of sleep is normal or not;

2. and (4) applying a deep learning algorithm to judge the risk probability of the AD early-stage features. The method specifically comprises the following steps:

(1) grading and labeling early signs of AD, wherein the labeling method adopts gene sequencing evaluation, is divided into 0-5 grades and respectively represents the place values of 0%, 20%, 40%, 60%, 80% and 100% of the AD morbidity probability;

(2) the model applies a convolutional neural network, the extracted sleep stage characteristics are used as input, and a generated result model is obtained through discrimination;

(3) and applying a generation model, and taking the incidence probability grade obtained by the evaluation of the model and the basic characteristics of sleep stages as input to obtain continuous incidence probability, incidence time and incidence severity estimation values. And (4) the model input is labeled by adopting a case analysis method.

And transmitting the result including the incidence probability and the incidence time estimated value to the user terminal to form a detection report. Please refer to fig. 3 for a schematic diagram of the disease condition prediction.

Referring to fig. 4, fig. 4 is a schematic structural diagram of a sleep stage-based alzheimer's disease screening system for implementing the method of the present invention, including:

the BCI equipment 101 is used for collecting an EEG signal in the sleeping process of a user and transmitting the EEG signal to the sleep staging algorithm system;

the sleep staging algorithm system 102 is used for extracting and analyzing features of an EEG signal of a user, judging a sleep state and staging the sleep state;

and the early screening system 103 is used for performing feature extraction and analysis on the sleep staging result and judging whether the user is in the early stage high risk stage of the Alzheimer disease.

Therefore, in the system, the sleep state is judged and staged through characteristic extraction and analysis of the EEG signals of the user, and the sleep staging result is subjected to characteristic extraction and analysis to judge whether the early-stage onset of the Alzheimer's disease is in a high-risk stage, so that the early-stage signs of the Alzheimer's disease are judged, early warning can be performed on the high-probability onset of the Alzheimer's disease in advance, early intervention is effectively mediated, namely the early-stage signs of the Alzheimer's disease are judged by utilizing the EEG signals, manual screening is not needed, the labor cost is reduced, and the screening efficiency is improved.

For the introduction of the sleep stage-based alzheimer's disease screening system provided by the present invention, please refer to the foregoing embodiment of the sleep stage-based alzheimer's disease screening method, and the embodiment of the present invention is not described herein again. The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The method and the system for screening the Alzheimer's disease based on the sleep stage provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.

Claims

1. A sleep stage-based Alzheimer's disease screening method is characterized by comprising the following steps:

2. The sleep stage based screening method for alzheimer's disease as set forth in claim 1 wherein the features extracted for the EEG signal of the user comprise time domain features and frequency domain features of the EEG signal.

3. The sleep stage-based alzheimer's disease screening method according to claim 1 wherein the sleep state is discriminated and staged using a convolutional neural network model.

4. The sleep stage-based alzheimer's disease screening method of claim 1, wherein said sleep stage results comprise time series data labeled on a time axis and data points of the stage results during sleep.

5. The sleep stage-based alzheimer's disease screening method of claim 1, wherein the extracted features of the sleep stage results comprise overall duration features, proportionality, starting position, duration and degree of dispersion of each stage, number and duration of sleep cycle repetitions, whether sleep cycle is typical and healthy, and whether sleep stage transitions are normal.

6. The sleep stage-based Alzheimer's disease screening method of claim 1, wherein a deep learning algorithm is used to determine whether the user is in the early stage of Alzheimer's disease with high risk of developing, and the method comprises:

7. A sleep stage based Alzheimer's disease screening system for implementing the method of any one of claims 1 to 6, comprising: