Neurodegenerative disease assessment method, device, equipment and storage medium

Abstract

The embodiment of the invention provides a neurodegenerative disease assessment method, device and equipment and a storage medium, and is applied to the technical field of medical diagnosis. The method comprises the steps that electroencephalogram signals and electrocardiosignals of a testee in the sleep period are collected, and electroencephalogram signal data and electrocardiosignal data are obtained; performing feature extraction on the electroencephalogram signal data and the electrocardiosignal data to obtain electroencephalogram signal features and electrocardiosignal features; and inputting the electroencephalogram signal features and the electrocardiosignal features into a pre-trained neurodegenerative disease evaluation model, processing the electroencephalogram signal features and the electrocardiosignal features by the neurodegenerative disease evaluation model, and predicting whether the subject attacks the neurodegenerative disease in the future. In this way, whether the subject attacks the neurodegenerative disease or not in the future can be quickly and accurately predicted based on the electroencephalogram signals and the electrocardiosignals of the subject in the sleep period, and then a doctor is assisted in making more objective judgment on the subject.

Description

Technical Field

[0001] The present invention relates to the field of medical diagnosis technology, and in particular to a neurodegenerative disease assessment method, device, equipment and storage medium. Background Art

[0002] With the improvement of science and technology and living standards, the problem of population aging is becoming more and more serious. Neurodegenerative diseases are common diseases among the elderly. Depending on the symptoms and severity, patients show certain cognitive function decline or motor function decline until they cannot take care of themselves, which causes serious psychological, physiological and economic burdens to patients and their families.

[0003] The earlier most neurodegenerative diseases are discovered and intervened, the faster the progression of the disease can be prevented or slowed, the later life of the potential population can be improved, and the burden on families can be reduced.

[0004] Studies have shown that some patients with neurodegenerative diseases will experience changes in their vital signs in the first few years of onset. Most existing neurodegenerative disease assessment programs focus on single features, trying to understand the mechanism behind the disease, develop drugs or conduct targeted examinations to identify potential neurodegenerative disease patients. However, assessment programs targeting a single feature generally ignore the mutual influence of multiple features and have poor accuracy. Summary of the invention

[0005] Embodiments of the present invention provide a neurodegenerative disease assessment method, apparatus, device and storage medium.

[0006] In a first aspect, an embodiment of the present invention provides a method for evaluating a neurodegenerative disease, the method comprising:

[0007] Collecting the EEG signals and ECG signals of the subjects during sleep to obtain EEG signal data and ECG signal data;

[0008] Extract features from the EEG signal data and the ECG signal data to obtain EEG signal features and ECG signal features;

[0009] The EEG signal features and ECG signal features are input into a pre-trained neurodegenerative disease assessment model, which processes the EEG signal features and ECG signal features to predict whether the subject will develop a neurodegenerative disease in the future.

[0010] In some possible implementations of the first aspect, collecting EEG signals and ECG signals of a subject during sleep to obtain EEG signal data and ECG signal data includes:

[0011] The EEG signals and ECG signals of the subjects during sleep are collected by an EEG diagnostic instrument and an electrocardiograph to obtain EEG signal data and ECG signal data.

[0012] In some possible implementations of the first aspect, feature extraction is performed on the EEG signal data and the ECG signal data to obtain EEG signal features and ECG signal features, including:

[0013] The EEG signal data and the ECG signal data are screened, and features are extracted from the screened EEG signal data and the ECG signal data to obtain EEG signal features and ECG signal features.

[0014] In some implementations of the first aspect, the neurodegenerative disease assessment model is trained by the following steps:

[0015] Obtain a pre-training data set, which includes multiple neurodegenerative disease assessment samples and their corresponding labels; the neurodegenerative disease assessment samples include EEG signal data and ECG signal data of the subject during sleep in a specified time period; the label includes the onset of the neurodegenerative disease of the subject after the specified time period;

[0016] Feature extraction is performed on samples in the pre-training data set, and the EEG signal features, ECG signal features and corresponding labels of the samples in the pre-training data set after feature extraction are used to train the initial neurodegenerative disease assessment model to obtain a neurodegenerative disease assessment model.

[0017] In some implementations of the first aspect, obtaining a pre-training dataset includes:

[0018] Obtain public data sets of EEG and ECG signals, and offline data sets of EEG and ECG signals;

[0019] A pre-training dataset is generated based on the public datasets of EEG signals and ECG signals and the offline datasets of EEG signals and ECG signals.

[0020] In some implementations of the first aspect, feature extraction is performed on samples in a pre-training data set, and the pre-training data set after feature extraction is used to train an initial neurodegenerative disease assessment model to obtain a neurodegenerative disease assessment model, including:

[0021] Divide the pre-training data set into training set and test set;

[0022] Extract features from samples in the training set and test set;

[0023] Using the EEG signal features, ECG signal features and their corresponding labels of the samples in the training set after feature extraction to train the initial neurodegenerative disease assessment model, and generate a neurodegenerative disease assessment model in training;

[0024] The EEG signal features, ECG signal features and their corresponding labels of the samples in the test set after feature extraction are used to perform a performance test on the neurodegenerative disease assessment model in training. If the performance test is passed, the final neurodegenerative disease assessment model is obtained.

[0025] In some implementations of the first aspect, the neurodegenerative disease assessment model is composed of a combination of a CTRA decision tree and an adaptive boosting tree.

[0026] In a second aspect, an embodiment of the present invention provides a neurodegenerative disease assessment device, the device comprising:

[0027] The acquisition module is used to collect the EEG signal and the ECG signal of the subject during sleep to obtain the EEG signal data and the ECG signal data;

[0028] An extraction module is used to extract features from EEG signal data and ECG signal data to obtain EEG signal features and ECG signal features;

[0029] The prediction module is used to input the EEG signal features and the ECG signal features into a pre-trained neurodegenerative disease assessment model. The neurodegenerative disease assessment model processes the EEG signal features and the ECG signal features to predict whether the subject will develop a neurodegenerative disease in the future.

[0030] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described above.

[0031] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to enable a computer to execute the method described above.

[0032] In an embodiment of the present invention, it is possible to quickly and accurately predict whether the subject will develop a neurodegenerative disease in the future based on the EEG signals and ECG signals of the subject during sleep, thereby assisting doctors in making more objective judgments on the subject, so as to detect potential patients earlier and intervene early, thereby preventing or delaying the occurrence of neurodegenerative diseases. This has great potential value in improving the quality of life of potential patients and their families, reducing the diagnosis costs of medical staff, and reducing the burden on the medical system.

[0033] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for a better understanding of the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0035] Figure 1 A flowchart of a neurodegenerative disease assessment method provided by an embodiment of the present invention is shown;

[0036] Figure 2 A structural diagram of a neurodegenerative disease assessment device provided by an embodiment of the present invention is shown;

[0037] Figure 3 A structural diagram of an exemplary electronic device capable of implementing an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0040] In order to solve the technical problems arising from the background technology, the embodiments of the present invention provide a method, device, equipment and storage medium for evaluating neurodegenerative diseases. Specifically, the EEG signals and ECG signals of the subjects during sleep are collected to obtain EEG signal data and ECG signal data; feature extraction is performed on the EEG signal data and ECG signal data to obtain EEG signal features and ECG signal features; the EEG signal features and ECG signal features are input into a pre-trained neurodegenerative disease evaluation model, and the neurodegenerative disease evaluation model processes the EEG signal features and ECG signal features to predict whether the subject will develop a neurodegenerative disease in the future.

[0041] In this way, based on the EEG and ECG signals of the subjects during sleep, it is possible to quickly and accurately predict whether the subjects will develop neurodegenerative diseases in the future, thereby assisting doctors in making more objective judgments about the subjects, so as to detect potential patients earlier and intervene early, thereby preventing or delaying the occurrence of neurodegenerative diseases. This has great potential value in improving the quality of life of potential patients and their families, reducing the diagnostic costs of medical staff, and reducing the burden on the medical system.

[0042] In conjunction with the accompanying drawings, a neurodegenerative disease assessment method, device, equipment and storage medium provided by the embodiments of the present invention are described in detail through specific embodiments.

[0043] Figure 1 A flowchart of a neurodegenerative disease assessment method provided by an embodiment of the present invention is shown. Figure 1 As shown, the neurodegenerative disease assessment method 100 may include the following steps:

[0044] S110, collecting EEG signals and ECG signals of the subject during sleep to obtain EEG signal data and ECG signal data.

[0045] In some embodiments, the EEG signals and ECG signals of the subject during sleep can be collected by an EEG diagnostic instrument and an electrocardiograph to obtain EEG signal data and ECG signal data.

[0046] S120, extracting features from the EEG signal data and the ECG signal data to obtain EEG signal features and ECG signal features.

[0047] In some embodiments, the EEG signal data and the ECG signal data can be screened, and feature extraction can be performed on the screened EEG signal data and ECG signal data to obtain EEG signal features and ECG signal features. In other words, the data is first screened to ensure that the test instrument does not fall off during the subject's sleep. If it does fall off, the corresponding data needs to be removed before feature extraction is performed to obtain the corresponding features.

[0048] For example, the EEG signal features and ECG signal features extracted here include but are not limited to:

[0049] (1) Total sleep time;

[0050] (2) Sleep efficiency;

[0051] (3) slow-wave sleep time;

[0052] (4) rapid eye movement sleep duration;

[0053] (5) N1 sleep time;

[0054] (6) N2 sleep time;

[0055] (7) N3 sleep time;

[0056] (8) sleep latency time;

[0057] (9) Number of awakenings;

[0058] (10) wake-up time after falling asleep;

[0059] (11) REM latency duration;

[0060] (12) Number of instant awakenings;

[0061] (13) the number and duration of sleep spindles;

[0062] (14) Number of occurrences of K complex waves;

[0063] (15) Average heart rate;

[0064] (16) Maximum heart rate;

[0065] (17) minimum heart rate;

[0066] (18) Resting heart rate;

[0067] (18) heart rate variability related (including standard deviation of adjacent heart beat intervals (NN), root mean square of the difference between adjacent heart beat intervals (RR), low frequency power, high frequency power, and low frequency / high frequency ratio);

[0068] (20) heart rate fragmentation correlation coefficient (including the number of times the difference between adjacent heartbeat intervals exceeds 50 ms (NN50), the percentage of time when the difference between adjacent heartbeat intervals exceeds 50 ms in the total RR intervals (pNN50);

[0069] (21) Heart rate variability coefficient (ratio of heart rate standard deviation to mean heart rate).

[0070] It is worth noting that the algorithms used for feature extraction here are all standard algorithms, such as the AASM (American Academy of Sleep Medicine) sleep staging guidelines, ISO / IEEE 11073 Personal Health Data (PHD) Standards, etc., which will not be elaborated here.

[0071] S130, inputting the EEG signal features and the ECG signal features into a pre-trained neurodegenerative disease assessment model, and the neurodegenerative disease assessment model processes the EEG signal features and the ECG signal features to predict whether the subject will develop a neurodegenerative disease in the future.

[0072] In some embodiments, the neurodegenerative disease assessment model can be trained by the following steps:

[0073] Obtain a pre-training data set. The pre-training data set may include multiple neurodegenerative disease assessment samples and their corresponding labels (approximately 5,000); the neurodegenerative disease assessment samples include EEG signal data and ECG signal data of the subjects during sleep within a specified time period (e.g., within 5 years); the labels include the onset of neurodegenerative diseases in the subjects after the specified time period (e.g., after 5 years).

[0074] Exemplarily, public data sets of EEG signals and ECG signals, and offline data sets of EEG signals and ECG signals (i.e., data sets generated based on signal data collected by offline EEG diagnostic instruments and electrocardiographs) can be obtained to generate a pre-training data set.

[0075] Feature extraction is performed on samples in the pre-training data set, and the EEG signal features, ECG signal features and corresponding labels of the samples in the pre-training data set after feature extraction are used to train the initial neurodegenerative disease assessment model to obtain a neurodegenerative disease assessment model.

[0076] Exemplarily, the above neurodegenerative disease assessment model can be composed of a combination of a CTRA decision tree and an adaptive boosting tree, as shown below:

[0077] The CTRA decision tree consists of many common nodes and leaf nodes. Each common node is a judgment condition. Its mathematical form can be expressed as:

[0078]

[0079] in, Represents the j-th dimension feature value of the n-th sample to be divided; τ j Represents the division threshold of this dimension; this function is an indicative function. When it is 1, it means the sample Satisfy the judgment condition, then the sample Will be divided into the left node, otherwise, when When it is not 1, the sample will be partitioned to the right node.

[0080] The basic principle of adaptive boosting tree is to learn a series of weak classifiers or basic classifiers from a given data set, and then assign different weights to these classifiers to form a strong classifier. Its mathematical form can be expressed as:

[0081]

[0082] Among them, F(x) is the final boosting tree composed of M decision trees; F m―1 (x) represents the boosted tree after m-1 rounds of iterations; α m represents the weight corresponding to the mth basic decision tree; f m (x) represents the mth decision tree.

[0083] Here we can use the adaptive boosting tree to optimize the classification effect of the CTRA decision tree, and its loss function is:

[0084] L(y,F(x))=exp(―yF(x))=exp(―yF m―1 (x)+α m f m (3)

[0085] The above is the loss function of the adaptive boosting tree, where the coefficient α m With the base tree f m (x) is the unknown coefficient. Assume F m―1 (x) can continue to improve, which means that the loss function can be further reduced. That is, if all samples are brought into the loss function, there must be an optimal α m and f m (x) minimizes the loss function, thus we can get:

[0086]

[0087] It can be seen that the loss function is similar to exp(―y i (F m―1 (x i )) is irrelevant, you can further write:

[0088]

[0089] Among them, p mi =exp(-y i (F m―1 (x i )).

[0090] For the above formula, it can be seen that for a fixed α m In order to obtain the minimum value of the loss function, we need to find the best f m (x), the solution can be expressed as:

[0091]

[0092] Among them, f represents all available basic decision tree spaces, f m (x) *The m-th round basic decision tree found from the f space can minimize the classification error points of the weighted training sample points.

[0093] When f m (x) * After obtaining it, we can solve α by entering it into the formula m :

[0094]

[0095] Among them, α m * is the weight of the basic decision tree, e m is the error rate of the basic decision tree m, which can be expressed as:

[0096]

[0097] Therefore, the CTRA decision tree and adaptive boosting tree can be combined to form a neurodegenerative disease assessment model.

[0098] It is worth noting that the pre-training data set can be divided into a training set and a test set in a ratio of 4:1, and feature extraction is performed on the samples in the training set and the test set. The EEG signal features, ECG signal features and corresponding labels of the samples in the training set after feature extraction are used to train the initial neurodegenerative disease assessment model to generate a neurodegenerative disease assessment model in training. Specifically, the weights of the sample points are continuously changed during this period, and the basic decision trees of each round are linearly combined by weights to continuously optimize the classification confidence of the model. The performance of the optimized neurodegenerative disease assessment model is tested using the EEG signal features, ECG signal features and corresponding labels of the samples in the test set after feature extraction. If the performance test is passed, the final neurodegenerative disease assessment model is obtained. It can be understood that the final neurodegenerative disease assessment model can be encapsulated, and no training is required for subsequent use. Only the data required by the model needs to be input into the model to output the neurodegenerative disease assessment result. Among them, if the neurodegenerative disease assessment result is YES, it indicates that according to the current data, the subject is likely to suffer from neurodegenerative disease in the future. If the result is NO, it means that based on current data, the subject is unlikely to develop a neurodegenerative disease in the future.

[0099] In summary, according to the embodiments of the present invention, at least the following technical effects are achieved:

[0100] A neurodegenerative disease assessment model with good generalization ability and prediction accuracy can be trained based on the pre-training data set, and then based on the model, it can be quickly and accurately predicted whether the subject will develop a neurodegenerative disease in the future, thereby assisting doctors to make more objective judgments on the subjects, so as to detect potential patients earlier and intervene early, thereby preventing or delaying the occurrence of neurodegenerative diseases. This has great potential value in improving the quality of life of potential patients and their families, reducing the diagnosis costs of medical staff, and reducing the burden on the medical system.

[0101] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0102] The above is an introduction to a method embodiment. The following is a further explanation of the solution of the present invention through an apparatus embodiment.

[0103] Figure 2 FIG. 4 shows a structural diagram of a neurodegenerative disease assessment device provided by an embodiment of the present invention, such as Figure 2 As shown, the neurodegenerative disease assessment device 200 may include:

[0104] The acquisition module 210 is used to acquire the EEG signal and the ECG signal of the subject during sleep to obtain EEG signal data and ECG signal data.

[0105] The extraction module 220 is used to extract features from the EEG signal data and the ECG signal data to obtain EEG signal features and ECG signal features.

[0106] The prediction module 230 is used to input the EEG signal features and the ECG signal features into a pre-trained neurodegenerative disease assessment model, and the neurodegenerative disease assessment model processes the EEG signal features and the ECG signal features to predict whether the subject will develop a neurodegenerative disease in the future.

[0107] Understandably, Figure 2 Each module / unit in the neurodegenerative disease assessment device 200 has the following functions: Figure 1 The functions of the various steps in the neurodegenerative disease assessment method 100 shown in the figure can achieve their corresponding technical effects, and for the sake of brevity, they will not be repeated here.

[0108] Figure 3A block diagram of an exemplary electronic device capable of implementing an embodiment of the present invention is shown. Electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 300 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown in the present invention, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required in the present invention.

[0109] like Figure 3 As shown, the electronic device 300 may include a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 may also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0110] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0111] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer program product, including a computer program, which is tangibly contained in a computer-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0112] The various embodiments described above in the present invention can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs, which may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general programmable processor, which may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0114] In the context of the present invention, a computer-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a computer-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] It should be noted that the present invention also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute method 100 and achieve the corresponding technical effect achieved by executing the method in an embodiment of the present invention. For the sake of concise description, they will not be repeated here.

[0116] In addition, the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method 100 is implemented.

[0117] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and the present invention is not limited here.

[0118] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating neurodegenerative diseases, characterized in that: The method comprises: Collecting the EEG signals and ECG signals of the subjects during sleep to obtain EEG signal data and ECG signal data; Extracting features from the EEG signal data and the ECG signal data to obtain EEG signal features and ECG signal features; The EEG signal features and the ECG signal features are input into a pre-trained neurodegenerative disease assessment model, and the neurodegenerative disease assessment model processes the EEG signal features and the ECG signal features to predict whether the subject will develop a neurodegenerative disease in the future.

2. The method according to claim 1, characterized in that: The step of collecting the EEG signal and the ECG signal of the subject during sleep to obtain the EEG signal data and the ECG signal data includes: The EEG signals and ECG signals of the subjects during sleep are collected by an EEG diagnostic instrument and an electrocardiograph to obtain EEG signal data and ECG signal data.

3. The method according to claim 1, characterized in that The feature extraction of the EEG signal data and the ECG signal data to obtain EEG signal features and ECG signal features includes: The EEG signal data and the ECG signal data are screened, and feature extraction is performed on the screened EEG signal data and ECG signal data to obtain EEG signal features and ECG signal features.

4. The method according to claim 1, characterized in that: The neurodegenerative disease assessment model is trained by the following steps: Acquire a pre-training data set, wherein the pre-training data set includes a plurality of neurodegenerative disease assessment samples and their corresponding labels; the neurodegenerative disease assessment samples include EEG signal data and ECG signal data of the subject during sleep in a specified time period; the label includes the onset of the neurodegenerative disease of the subject after the specified time period; Feature extraction is performed on the samples in the pre-training data set, and the EEG signal features, ECG signal features and corresponding labels of the samples in the pre-training data set after feature extraction are used to train the initial neurodegenerative disease assessment model to obtain the neurodegenerative disease assessment model.

5. The method according to claim 4, characterized in that The obtaining of the pre-training data set comprises: Obtain public data sets of EEG and ECG signals, and offline data sets of EEG and ECG signals; A pre-training data set is generated according to the public data set of EEG signals and ECG signals and the offline data set of EEG signals and ECG signals.

6. The method according to claim 4, characterized in that The extracting features of the samples in the pre-training data set and using the pre-training data set after feature extraction to train the initial neurodegenerative disease assessment model to obtain the neurodegenerative disease assessment model includes: Dividing the pre-training data set into a training set and a test set; Performing feature extraction on samples in the training set and the test set; Using the EEG signal features, ECG signal features and their corresponding labels of the samples in the training set after feature extraction to train the initial neurodegenerative disease assessment model, and generate a neurodegenerative disease assessment model in training; The EEG signal features, ECG signal features and their corresponding labels of the samples in the test set after feature extraction are used to perform a performance test on the neurodegenerative disease assessment model in training. If the performance test is passed, the final neurodegenerative disease assessment model is obtained.

7. The method according to claim 4, characterized in that The neurodegenerative disease assessment model is composed of a combination of a CTRA decision tree and an adaptive boosting tree.

8. A neurodegenerative disease assessment device, characterized in that: The device comprises: The acquisition module is used to collect the EEG signal and the ECG signal of the subject during sleep to obtain the EEG signal data and the ECG signal data; An extraction module, used for extracting features from the EEG signal data and the ECG signal data to obtain EEG signal features and ECG signal features; The prediction module is used to input the EEG signal features and the ECG signal features into a pre-trained neurodegenerative disease assessment model, and the neurodegenerative disease assessment model processes the EEG signal features and the ECG signal features to predict whether the subject will develop a neurodegenerative disease in the future.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to make a computer execute the method according to any one of claims 1 to 7.

Images