Biometric information acquisition method, device and depression assessment device

Abstract

The present disclosure provides a method for obtaining biometric information for depression assessment, including: performing noise reduction processing on the acquired electroencephalogram signal of the subject to be tested to obtain the electroencephalogram signal after noise reduction processing; performing feature enhancement processing on the electroencephalogram signal after noise reduction processing to obtain the electroencephalogram signal after feature enhancement processing; converting the electroencephalogram signal after feature enhancement processing into a coarse-grained signal point time series at multiple time scales to obtain the coarse-grained signal point time series at each time scale; and respectively obtaining the disordered features of the coarse-grained signal point time series at each time scale as biometric information for depression assessment. The present disclosure also provides an acquisition device, a method for constructing a depression assessment device, a depression assessment device, an electronic device, and a storage medium.

Description

Technical Field

[0001] The present disclosure relates to the technical field of biological signal processing, and more particularly to a method for acquiring biometric information for depression assessment, an acquisition device, a method for constructing a depression assessment device, a depression assessment device, an electronic device, and a storage medium. Background Art

[0002] Major Depressive Disorder is a common medical illness, also known as depression, which is generally characterized by low mood, lack of energy, and loss of interest in life. Major depression can also lead to abnormalities in neurovegetative function (such as appetite and sleep disorders), cognition (such as feelings of worthlessness) and psychomotor activity (such as agitation or mental retardation), and even make people suicidal. Depression is caused by a combination of genetic, biological, environmental and psychological factors. And depression is not caused by any single gene, but is a disease with complex genetic characteristics. There are currently several ways to treat major depression. These methods include psychotherapy, antidepressants, electroconvulsive therapy (ECT) and other somatic therapies. Antidepressants are drugs that treat depression. They may help improve the way the brain uses certain chemicals to control emotions or stress.

[0003] Typically, the assessment of depression status is based on self-rating depression scales and the experience of psychologists. The main problems are poor convenience, lack of objectivity, and low efficiency.

[0004] Therefore, there have been many attempts in the art to obtain more convenient and objective judgment methods and quantification means of the course of disease or treatment progress. For example, please refer to the following patent documents.

[0005] Patent document 1: Publication number CN105279380B, application number CN201510746466.0, application date 2015 / 11 / 5, titled "An automatic depression assessment system based on expression analysis", this patent discloses an automatic depression assessment system based on expression analysis, including a data acquisition module, a preprocessing and feature extraction module, a related feature extraction module, a prediction model training module, a new video annotation module and a new video prediction module. The purpose of this technology is to provide an objective evaluation standard that does not rely on subjective experience and can truly achieve objective and effective evaluation; it can comprehensively analyze the data of different subjects and is not limited to isolated analysis of a single subject.

[0006] Patent document 2: Publication number CN111899894B, application number CN202010767283.8, entitled "A prognosis drug efficacy evaluation system for patients with depression and its evaluation method", application date August 3, 2020, the patent discloses a prognosis drug efficacy evaluation system for patients with depression and its evaluation method, including the following steps: collect and organize data to construct an original data set; preprocess the original data set to obtain an experimental data set; perform data mining on the experimental data set, screen differential features, and establish an input data set; divide the input data set into a training data set and a test data set according to a certain ratio; create a deep learning model for prognosis drug efficacy evaluation of patients with depression, and use the training data set to train the created deep learning model; use the test data set to evaluate the performance of the trained deep learning model, and continuously optimize the model during the evaluation process to obtain the optimal model. The purpose of this patent is to predict drug efficacy based on the patient's pre-treatment characteristics, assist in guiding medical staff to make precise treatment, and improve the treatment effect.

[0007] Patent document 3: Publication number CN104127193B, application number CN201410334898.6, entitled "A quantitative evaluation system for depression and its evaluation method", the patent discloses a quantitative evaluation system for depression, including: an integrated electrocardiogram pulse wave detection device, a data transmission device, and a data processing platform. The patent also discloses a quantitative evaluation and diagnosis method for depression, including the following steps: Step 1, obtaining human physiological information under different states through a multi-state comprehensive test platform; Step 2, obtaining HRV characteristic parameters under different states based on the principle of heart rate variability analysis; Step 3, evaluating the balance state of the sympathetic nerve and vagus nerve functions in the autonomic nervous system; Step 4, establishing a quantitative evaluation model for depression to achieve rapid and objective evaluation of the depression level of the subject. It belongs to the field of computer-aided diagnosis technology, realizes quantitative evaluation of depression, fills the gap in the field of depression examination technology, is simple and easy to operate, saves medical resources, and has good clinical practicality.

[0008] However, in the above-mentioned prior art, the information used to evaluate depression still cannot accurately assist in the diagnosis and treatment of depression. Summary of the invention

[0009] In order to solve at least one of the above technical problems, the present disclosure provides a method for acquiring biometric information for depression assessment, an acquisition device, a method for constructing a depression assessment device, a depression assessment device, an electronic device and a storage medium.

[0010] According to one aspect of the present disclosure, a method for acquiring biometric information for depression assessment is provided, comprising:

[0011] S102, performing noise reduction processing on the acquired electroencephalogram signal (signal point time series) of the measured object to obtain the electroencephalogram signal after noise reduction processing;

[0012] S104, performing feature enhancement processing on the EEG signal after the noise reduction processing to obtain the EEG signal after the feature enhancement processing;

[0013] S106, converting the feature-enhanced electroencephalogram signal into a coarse-grained signal point time series at multiple time scales to obtain a coarse-grained signal point time series at each time scale; and

[0014] S108, respectively obtaining disordered features of the coarse-grained signal point time series at each time scale to serve as the biometric feature information for depression assessment.

[0015] According to at least one embodiment of the present disclosure, the biometric information acquisition method for depression assessment further includes:

[0016] S110, acquiring integrated disorder feature information of the multiple time scales based on the disorder features of the coarse-grained signal point time series at each time scale, to serve as the biometric feature information for depression assessment.

[0017] According to at least one embodiment of the present disclosure, a biometric information acquisition method for depression assessment acquires integrated disordered feature information of multiple time scales based on disordered features of a coarse-grained signal point time series at each time scale, including:

[0018] The disorder characteristics of the coarse-grained signal point time series at each time scale are given the same or different weight values ​​to obtain the comprehensive disorder characteristic information of the multiple time scales.

[0019] According to the biometric information acquisition method for depression assessment of at least one embodiment of the present disclosure, the disordered feature of the coarse-grained signal point time series at each time scale is preferably fuzzy entropy.

[0020] According to the method for acquiring biometric information for depression assessment of at least one embodiment of the present disclosure, the noise reduction processing includes: removing electrooculographic pseudo signals, electromyographic pseudo signals and / or electrocardiographic pseudo signals in the electroencephalogram signal.

[0021] According to at least one embodiment of the present disclosure, the biometric information acquisition method for depression assessment, S104, performing feature enhancement processing on the EEG signal after noise reduction processing to obtain the EEG signal after feature enhancement processing, includes:

[0022] S1041, taking the electroencephalogram signal (preferably the electroencephalogram signal of the O1 channel, with x(t) representing the electroencephalogram signal) as an initial signal to be processed, obtaining an upper envelope and a lower envelope of the initial signal to be processed, and obtaining a mean line of the upper envelope and the lower envelope as an initial mean line (m(t));

[0023] S1042, subtracting the initial mean line (m(t)) from the initial signal to be processed to obtain an intermediate signal to be processed;

[0024] S1043, obtaining an upper envelope and a lower envelope of the intermediate signal to be processed, and obtaining a mean line of the upper envelope and the lower envelope as an intermediate mean line;

[0025] S1044, repeating S1043 multiple times until the number of extreme value signal points among all signal points of the intermediate signal to be processed is the same as the number of zero-crossing signal points or differs by 1, and taking the intermediate signal to be processed at this time as the first-order signal component of the electroencephalogram signal;

[0026] Subtracting the first-order signal component from the initial signal to be processed to obtain a first-order signal residual, taking the first-order signal residual as a new signal to be processed, and performing the same processing as steps S1041 to S1044 on the new signal to be processed until the n-th order signal residual becomes a monotonic function;

[0027] Wherein, a total of n-order signal components (i.e., first-order signal components to n-th-order signal components) are obtained, and n is a natural number greater than 1;

[0028] S1045. Reconstruct the electroencephalogram signal based on the first-order signal component to the n-th order signal component and the n-th order signal residual to obtain the electroencephalogram signal after the feature enhancement processing.

[0029] According to at least one embodiment of the present disclosure, the biometric information acquisition method for depression assessment, S1045, reconstructing the electroencephalogram signal based on the first-order signal component to the n-th order signal component and the n-th order signal residual to obtain the electroencephalogram signal after the feature enhancement processing, includes: reconstructing using the following formula:

[0030]

[0031] in, is the EEG signal after feature enhancement processing, c j (t) is the j-th order signal component, r n (t) is the n-th order signal margin.

[0032] According to at least one embodiment of the present disclosure, the biometric information acquisition method for depression assessment, S106, converting the electroencephalogram signal after the feature enhancement processing into a coarse-grained signal point time series at multiple time scales, and obtaining the coarse-grained signal point time series at each time scale, includes:

[0033] Different time scale factors (τ) are used to convert the EEG signals at the original time scale into coarse-grained signal point time series at multiple time scales, and the number of coarse-grained signal points in the coarse-grained signal point time series at each time scale is limited by the ratio of the total number of signal points (N) of the EEG signal at the original time scale to the time scale factor (τ) of each time scale.

[0034] According to the biometric information acquisition method for depression assessment of at least one embodiment of the present disclosure, each coarse-grained signal point in the coarse-grained signal point time series at each time scale is preferably the average of multiple continuous electroencephalogram signal points at the original time scale corresponding to the coarse-grained signal point.

[0035] According to another aspect of the present disclosure, a biometric information acquisition device for depression assessment is provided, comprising:

[0036] A noise reduction processing module, wherein the noise reduction processing module performs noise reduction processing on the acquired electroencephalogram signal (signal point time series) of the measured object to obtain the electroencephalogram signal after noise reduction processing;

[0037] A feature enhancement processing module, wherein the feature enhancement processing module performs feature enhancement processing on the EEG signal after the noise reduction processing to obtain an EEG signal after feature enhancement processing;

[0038] A conversion module, wherein the conversion module converts the electroencephalogram signal after the feature enhancement processing into a coarse-grained signal point time series at multiple time scales to obtain a coarse-grained signal point time series at each time scale; and

[0039] The disorder feature acquisition module acquires the disorder features of the coarse-grained signal point time series at each time scale to serve as the biometric feature information for depression assessment.

[0040] According to at least one embodiment of the present disclosure, the biometric information acquisition device for depression assessment further includes:

[0041] The disordered feature comprehensive processing module obtains the comprehensive disordered feature information of the multiple time scales based on the disordered features of the coarse-grained signal point time series at each time scale, so as to serve as the biometric feature information for depression assessment.

[0042] According to another aspect of the present disclosure, a method for constructing a depression assessment device is provided, wherein the biometric information for depression assessment of multiple subjects obtained by any of the biometric information acquisition methods described above is used to train a binary classifier to obtain the depression assessment device.

[0043] According to the method for constructing a depression assessment device according to at least one embodiment of the present disclosure, the binary classifier is preferably a SVM classifier (ie, a support vector machine classifier).

[0044] According to yet another aspect of the present disclosure, a depression assessment device is provided, which is a depression assessment device constructed by any of the above-mentioned construction methods.

[0045] According to another aspect of the present disclosure, an electronic device is provided, comprising: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, so that the processor executes any one of the above-described methods for acquiring biometric information for depression assessment and / or any one of the above-described construction methods.

[0046] According to another aspect of the present disclosure, a readable storage medium is provided, wherein the readable storage medium stores execution instructions, and when the execution instructions are executed by a processor, the execution instructions are used to implement any of the above-mentioned methods for acquiring biometric information for depression assessment and / or any of the above-mentioned construction methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings illustrate exemplary embodiments of the present disclosure and together with the description serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0048] Figure 1 It is a flowchart of a method for acquiring biometric information for depression assessment according to an embodiment of the present disclosure.

[0049] Figure 2 It is a flowchart of a method for acquiring biometric information for depression assessment according to another embodiment of the present disclosure.

[0050] Figure 3 It is a flowchart of a feature enhancement processing method in a biometric information acquisition method for depression assessment according to an embodiment of the present disclosure.

[0051] Figure 4 It is a schematic block diagram of the structure of a biometric information acquisition device for depression assessment using a hardware implementation of a processing system according to an embodiment of the present disclosure.

[0052] Figure 5 It is a structural schematic block diagram of a biometric information acquisition device for depression assessment using a hardware implementation of a processing system according to another embodiment of the present disclosure.

[0053] Figure 6 It is a structural schematic block diagram of a depression assessment device using a hardware implementation of a processing system according to another embodiment of the present disclosure.

[0054] Figure 7 This is a graph showing the change in multi-scale inherent fuzzy entropy before and after drug treatment (the scale τ is 1-10).

[0055] Figure 8 This is a graph showing the changes in multi-scale fuzzy entropy of 8 depression patients before and after medication.

[0056] Fig. 9 It is a comparison chart of the multi-scale inherent fuzzy entropy of patients and the multi-scale inherent fuzzy entropy of the healthy control group before drug treatment.

[0057] Fig.10 It is a comparison chart of the multi-scale intrinsic fuzzy entropy of patients after drug treatment and that of the healthy control group.

[0058] Description of Reference Numerals

[0059] 1000 Biometric information acquisition device

[0060] 1002 Noise Reduction Processing Module

[0061] 1004 Feature Enhancement Processing Module

[0062] 1006 Conversion Module

[0063] 1008 Disordered Feature Acquisition Module

[0064] 1010 Disordered Feature Comprehensive Processing Module

[0065] 1012 Binary Classifier Module

[0066] 1100 Bus

[0067] 1200 processor

[0068] 1300 Memory

[0069] 1400 Other circuits

[0070] 2000 Depression Assessment Device. DETAILED DESCRIPTION

[0071] The present disclosure is further described in detail below in conjunction with the accompanying drawings and implementations. It is understood that the specific implementations described herein are only used to explain the relevant content, rather than to limit the present disclosure. It should also be noted that, for ease of description, only the parts related to the present disclosure are shown in the accompanying drawings.

[0072] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure can be combined with each other. The technical solution of the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0073] Unless otherwise specified, the exemplary embodiments / embodiments shown will be understood as providing exemplary features of various details of some ways in which the technical concept of the present disclosure can be implemented in practice. Therefore, unless otherwise specified, the features of the various embodiments / embodiments can be combined, separated, interchanged and / or rearranged without departing from the technical concept of the present disclosure.

[0074] The use of cross-hatching and / or shading in the accompanying drawings is generally used to make the boundaries between adjacent components clear. As such, unless otherwise specified, the presence or absence of cross-hatching or shading does not convey or indicate any preference or requirement for the specific materials, material properties, dimensions, proportions, commonalities between the components shown, and / or any other characteristics, attributes, properties, etc. of the components. In addition, in the accompanying drawings, the sizes and relative sizes of the components may be exaggerated for clarity and / or descriptive purposes. When the exemplary embodiments can be implemented differently, the specific process sequence can be performed in a different order than described. For example, two successively described processes can be performed substantially simultaneously or in an order opposite to the described order. In addition, the same figure numbers represent the same components.

[0075] When a component is referred to as being "on," "over," "connected to," or "coupled to" another component, the component may be directly on, directly connected to, or directly coupled to the other component, or intervening components may be present. However, when a component is referred to as being "directly on," "directly connected to," or "directly coupled to" another component, there are no intervening components. For this purpose, the term "connected" may refer to a physical connection, an electrical connection, etc., with or without intervening components.

[0076] The terms used herein are for the purpose of describing specific embodiments, and are not intended to be restrictive. As used herein, unless the context clearly indicates otherwise, the singular forms "one (kind, person)" and "said (the)" are also intended to include plural forms. In addition, when the terms "comprise" and / or "include" and their variations are used in this specification, it is explained that there are stated features, integral bodies, steps, operations, parts, assemblies and / or their groups, but it is not excluded that there are or add one or more other features, integral bodies, steps, operations, parts, assemblies and / or their groups. It should also be noted that, as used herein, the terms "substantially", "approximately" and other similar terms are used as approximate terms and not as degree terms, so that they are used to explain the inherent deviations of the measured values, calculated values ​​and / or the values ​​provided that will be recognized by those of ordinary skill in the art.

[0077] Figure 1 It is a flowchart of a method for acquiring biometric information for depression assessment according to an embodiment of the present disclosure.

[0078] like Figure 1 As shown, the biometric information acquisition method S100 for depression assessment in this embodiment includes:

[0079] S102, performing noise reduction processing on the acquired electroencephalogram signal (signal point time series) of the measured object to obtain the electroencephalogram signal after noise reduction processing;

[0080] S104, performing feature enhancement processing on the EEG signal after the noise reduction processing to obtain the EEG signal after the feature enhancement processing;

[0081] S106, converting the electroencephalogram signal after feature enhancement processing into a coarse-grained signal point time series at multiple time scales to obtain a coarse-grained signal point time series at each time scale;

[0082] S108. Obtain the disordered features of the coarse-grained signal point time series at each time scale respectively to serve as biometric information for depression assessment.

[0083] The EEG signal is composed of signal points. For example, a segment of the EEG signal includes N signal points, where N is a natural number.

[0084] Among them, the electroencephalogram signal in the biometric information acquisition method S100 for depression assessment disclosed in the present invention is the electroencephalogram signal in the polysomnogram data. The polysomnogram data of the subject includes the electroencephalogram signal, and also includes one or any two or any three of the electrooculogram signal, electromyogram signal, and electrocardiogram signal.

[0085] Based on the auxiliary signals in the polysomnography data (one or any two or any three of the electrooculogram signals, electromyogram signals, and electrocardiogram signals), the electrooculogram pseudo signals, electromyogram pseudo signals, and / or electrocardiogram pseudo signals in the electroencephalogram signals are removed, so that the biometric information acquired by the biometric information acquisition method for depression assessment disclosed in the present invention is more accurate.

[0086] For the EEG signal after noise reduction processing, since its characteristic may not be very obvious, it is not conducive to the extraction of biometric information and further depression assessment. Therefore, the present invention improves the characteristic of the EEG signal through feature enhancement processing, and further improves the accuracy of biometric information extraction.

[0087] Wherein, preferably, the multiple time scales described above include a coarse-grained time scale relative to the time scale of the originally acquired electroencephalogram signal.

[0088] Among them, the EEG signal after feature enhancement processing is converted into a coarse-grained signal point time series at multiple time scales, that is, the EEG signal after feature enhancement processing is converted into a coarse-grained signal point time series at each coarse-grained time scale. Those skilled in the art should understand that the above-mentioned multiple coarse-grained time scales are different time scales.

[0089] The electroencephalogram signal obtained in the present disclosure is preferably an electroencephalogram signal of the O1 channel, and may also be an electroencephalogram signal of channels such as O2, F3, and F4.

[0090] Figure 2 It is a flowchart of a method S100 for acquiring biometric information for depression assessment according to another embodiment of the present disclosure.

[0091] like Figure 2 As shown, the biometric information acquisition method S100 for depression assessment in this embodiment includes:

[0092] S102, performing noise reduction processing on the acquired electroencephalogram signal (signal point time series) of the measured object to obtain the electroencephalogram signal after noise reduction processing;

[0093] S104, performing feature enhancement processing on the EEG signal after the noise reduction processing to obtain the EEG signal after the feature enhancement processing;

[0094] S106, converting the electroencephalogram signal after feature enhancement processing into a coarse-grained signal point time series at multiple time scales to obtain a coarse-grained signal point time series at each time scale;

[0095] S108, respectively obtaining the disorder characteristics of the coarse-grained signal point time series at each time scale;

[0096] S110, obtaining integrated disordered feature information of multiple time scales based on the disordered features of the coarse-grained signal point time series at each time scale, to serve as biometric feature information for depression assessment.

[0097] For the biometric information acquisition method S100 for depression assessment of this embodiment, preferably, the integrated disordered feature information of multiple time scales is acquired based on the disordered features of the coarse-grained signal point time series at each time scale, including:

[0098] The disorder characteristics of the time series of coarse-grained signal points at each time scale are given the same or different weight values ​​to obtain the comprehensive disorder characteristic information of multiple time scales.

[0099] More preferably, a larger weight value is given to the disordered features of the time series of coarse-grained signal points at a larger time scale.

[0100] For the biometric information acquisition method S100 for depression assessment in each of the above-mentioned embodiments, the disorder feature of the coarse-grained signal point time series at each time scale is preferably fuzzy entropy.

[0101] For the biometric information acquisition method S100 for depression assessment in each of the above-mentioned embodiments, preferably, the noise reduction process includes: removing electrooculographic pseudo signals, electromyographic pseudo signals and / or electrocardiographic pseudo signals in the electroencephalogram signal.

[0102] The noise reduction processing described above in the present disclosure includes not only the removal of the above-mentioned false signals, but also conventional noise reduction processing such as band-pass filtering.

[0103] In order to perform feature enhancement processing on the EEG signal, the biometric information acquisition method for depression assessment disclosed in the present invention preferably adopts the following feature enhancement processing method to perform feature enhancement processing on the EEG signal after noise reduction processing to obtain the EEG signal after feature enhancement processing, referring to Figure 3 ,include:

[0104] S1041, using the electroencephalogram signal (preferably the electroencephalogram signal of the O1 channel, with x(t) representing the electroencephalogram signal) as the initial signal to be processed, obtaining the upper envelope and the lower envelope of the initial signal to be processed, and obtaining the mean line of the upper envelope and the lower envelope as the initial mean line (m(t));

[0105] S1042, subtracting the initial mean line (m(t)) from the initial signal to be processed to obtain an intermediate signal to be processed;

[0106] S1043, obtaining an upper envelope and a lower envelope of the intermediate signal to be processed, and obtaining a mean line of the upper envelope and the lower envelope as an intermediate mean line;

[0107] S1044, repeating S1043 multiple times until the number of extreme value signal points among all signal points of the intermediate signal to be processed is the same as the number of zero-crossing signal points or the difference is 1, and the intermediate signal to be processed at this time is used as the first-order signal component of the electroencephalogram signal;

[0108] Subtracting the first-order signal component from the initial signal to be processed to obtain the first-order signal residual, taking the first-order signal residual as the new signal to be processed, and performing the same processing as steps S1041 to S1044 on the new signal to be processed until the n-th order signal residual becomes a monotonic function;

[0109] Wherein, a total of n-order signal components (i.e., first-order signal components to n-th-order signal components) are obtained, and n is a natural number greater than 1;

[0110] S1045 , reconstructing the electroencephalogram signal based on the first-order signal component to the n-th order signal component and the n-th order signal residual to obtain the electroencephalogram signal after feature enhancement processing.

[0111] The present disclosure preferably decomposes and reconstructs the modality of the EEG signal through the above-mentioned feature enhancement processing method, thereby enhancing the characteristic of the EEG signal.

[0112] For the biometric information acquisition method S100 for depression assessment of the above embodiment, preferably, S1045, reconstructing the electroencephalogram signal based on the first-order signal component to the n-th order signal component and the n-th order signal residual to obtain the electroencephalogram signal after feature enhancement processing, includes: reconstructing using the following formula:

[0113]

[0114] in, is the EEG signal after feature enhancement processing, c j (t) is the j-th order signal component, r n (t) is the n-th order signal margin.

[0115] For the biometric information acquisition method S100 for depression assessment in each of the above embodiments, preferably, S106, converting the electroencephalogram signal after feature enhancement processing into a coarse-grained signal point time series at multiple time scales, and obtaining the coarse-grained signal point time series at each time scale, includes:

[0116] Different time scale factors (τ) are used to convert the EEG signals at the original time scale into coarse-grained signal point time series at multiple time scales, and the number of coarse-grained signal points in the coarse-grained signal point time series at each time scale is limited by the ratio of the total number of signal points (N) of the EEG signal at the original time scale to the time scale factor (τ) of each time scale.

[0117] According to a preferred embodiment of the present disclosure, each coarse-grained signal point in the coarse-grained signal point time series at each time scale is preferably the average value of multiple continuous electroencephalogram signal points at the original time scale corresponding to the coarse-grained signal point.

[0118] Coarse-grained signal point time series Preferably, it is obtained by the following formula:

[0119] in, N is the EEG signal after feature enhancement processing The number of signal points.

[0120] in For each coarse-grained signal point in the time series of coarse-grained signal points at a time scale of τ, Represents the EEG signal after feature enhancement processing obtained by the above reconstruction method signal point.

[0121] For example, when the time scale factor τ is 3, each coarse-grained signal point in the coarse-grained signal point time series is the mean of three consecutive EEG signal points at its corresponding original time scale.

[0122] When the time scale factor τ is 1, it is the original time scale.

[0123] The multiple time scales described above in the present disclosure are preferably 10 time scales, ie, one original time scale and 9 coarse-grained time scales, ie, the value range of τ is a natural number between 1 and 10.

[0124] According to a preferred embodiment of the present disclosure, each coarse-grained signal point in the coarse-grained signal point time series at each time scale is also standardized to more accurately obtain the disordered characteristics of the coarse-grained signal point time series at each time scale.

[0125] The standardization process may adopt the standardization process method in the prior art, and the present disclosure does not specifically limit this.

[0126] According to one embodiment of the present disclosure, a biometric information acquisition device 1000 for depression assessment includes:

[0127] A noise reduction processing module 1002 performs noise reduction processing on the acquired electroencephalogram signal (signal point time series) of the measured object to obtain the electroencephalogram signal after noise reduction processing;

[0128] A feature enhancement processing module 1004, which performs feature enhancement processing on the EEG signal after the noise reduction processing to obtain an EEG signal after feature enhancement processing;

[0129] A conversion module 1006, which converts the EEG signal after feature enhancement processing into a coarse-grained signal point time series at multiple time scales to obtain a coarse-grained signal point time series at each time scale;

[0130] The disorder feature acquisition module 1008 acquires disorder features of the coarse-grained signal point time series at each time scale as biometric feature information for depression assessment.

[0131] Based on the above-mentioned biometric information acquisition device 1000 for depression assessment, it is preferred to further include:

[0132] The disordered feature comprehensive processing module 1010 obtains comprehensive disordered feature information of multiple time scales based on the disordered features of the coarse-grained signal point time series at each time scale, so as to serve as biometric feature information for depression assessment.

[0133] The biometric information acquisition device 1000 for depression assessment in each of the above-mentioned embodiments can be implemented in the form of a computer program software architecture.

[0134] Figures 4 to 5 A schematic block diagram of the structure of a biometric information acquisition device 1000 for depression assessment using a hardware implementation of a processing system is shown.

[0135] Figures 4 to 5 The biometric information acquisition device for depression assessment in the embodiment may include corresponding modules for executing each or several steps in the above flowchart. Therefore, each step or several steps in the above flowchart may be executed by the corresponding module, and the device may include one or more of these modules. The module may be one or more hardware modules specially configured to execute the corresponding steps, or implemented by a processor configured to execute the corresponding steps, or stored in a computer-readable medium for implementation by a processor, or implemented by some combination.

[0136] The hardware structure can be implemented using a bus architecture. The bus architecture can include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus 1100 connects various circuits including one or more processors 1200, memory 1300, and / or hardware modules together. The bus 1100 can also connect various other circuits 1400 such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0137] The bus 1100 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the figure only uses one connecting line, but does not mean that there is only one bus or one type of bus.

[0138] Any process or method description in the flowchart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present disclosure includes other implementations, in which the functions may not be performed in the order shown or discussed, including performing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by a person skilled in the art of the present disclosure. The processor performs the various methods and processes described above. For example, the method implementation in the present disclosure can be implemented as a software program, which is tangibly contained in a machine-readable medium, such as a memory. In some embodiments, part or all of the software program can be loaded and / or installed via a memory and / or a communication interface. When the software program is loaded into the memory and executed by the processor, one or more steps in the method described above can be performed. Alternatively, in other embodiments, the processor can be configured to perform one of the above methods in any other appropriate manner (e.g., by means of firmware).

[0139] The logic and / or steps represented in the flowchart or otherwise described herein may be embodied in any readable storage medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions on an instruction execution system, apparatus, or device), or in combination with such instruction execution systems, apparatuses, or devices.

[0140] For the purposes of this specification, a "readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use with or in conjunction with an instruction execution system, device or apparatus. More specific examples of readable storage media (a non-exhaustive list) include the following: an electrical connection with one or more wirings (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), a fiber optic device, and a portable read-only memory (CDROM). In addition, the readable storage medium may even be paper or other suitable medium on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a memory.

[0141] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0142] A person skilled in the art may understand that all or part of the steps of implementing the above-mentioned implementation method may be completed by instructing related hardware through a program, and the program may be stored in a readable storage medium, which, when executed, includes one or a combination of the steps of the implementation method.

[0143] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a readable storage medium. The storage medium may be a read-only memory, a disk or an optical disk, etc.

[0144] According to a method for constructing a depression assessment device according to an embodiment of the present disclosure, a binary classifier is trained using biometric information for depression assessment of multiple subjects acquired using the biometric information acquisition method of any of the above embodiments to obtain a depression assessment device.

[0145] Preferably, the binary classifier is preferably a SVM classifier (ie, support vector machine classifier).

[0146] The present disclosure also provides a depression assessment device, which is a depression assessment device 2000 constructed by the method for constructing a depression assessment device according to any one of the above embodiments.

[0147] It is preferred that a binary classifier module 1012 is provided on the basis of the biometric information acquisition device 1000 for depression assessment in each of the above-mentioned embodiments to constitute the depression assessment device 2000 of the present disclosure.

[0148] Figure 6 It is a schematic block diagram of the structure of a depression assessment device 2000 using a hardware implementation of a processing system according to another embodiment of the present disclosure.

[0149] An electronic device according to one embodiment of the present disclosure includes: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, so that the processor executes the biometric information acquisition method for depression assessment of any one of the above embodiments and / or the construction method of any one of the above embodiments.

[0150] According to a readable storage medium of one embodiment of the present disclosure, execution instructions are stored in the readable storage medium, and when the execution instructions are executed by a processor, they are used to implement the biometric information acquisition method for depression assessment of any of the above-mentioned embodiments and / or the construction method of any of the above-mentioned embodiments.

[0151] The following is a detailed description of the accuracy of depression assessment of the depression assessment device described above in the present disclosure with reference to specific examples.

[0152] The data of 7 depression patients before taking medication (e.g., escitalopram) and the data of 11 healthy controls were used as training data for the depression assessment device disclosed herein, and the data of the remaining 1 depression patient before taking medication were used as test data to verify the reliability of the depression assessment device disclosed herein. The eigenvalues ​​of the binary classification model were calculated using fuzzy entropy on different time scales. The reliability of the final test model was 88.2%.

[0153] The acquisition process of a polysomnogram is described by way of example:

[0154] All patients with major depressive disorder (8 patients as described above) underwent two polysomnograms, the first before escitalopram treatment and the second on day 57 after escitalopram treatment.

[0155] Among them, the polysomnography records include electroencephalogram (EEG; leads: C3, C4, O1, O2, with the contralateral mastoid as the reference electrode), electrooculography (EOG), electromyography (EMG) and electrocardiography (ECG). Scalp electrodes can be placed according to the 10 / 20 standard system, the electrode impedance is less than 5000 ohms, and the sampling frequency can be 256Hz. Polysomnography is performed on normal control members (ie, healthy people) under the same environment, and it is ensured that there is no interference from other elements during the collection process. The above collection process is only for illustrating the collection process of polysomnography, and does not constitute a limitation on the scope of protection of the technical solution disclosed in the present invention.

[0156] The biometric information acquisition device for depression assessment and the depression assessment device disclosed in the present invention obtain the disordered characteristics (multi-scale inherent fuzzy entropy) of the EEG signals collected by the electrode O1 after measuring the EEG signals of the depression patient during sleep and denoising the EEG signals, especially by analyzing the EEG signals collected by the occipital region electrode O1. The doctor can refer to the disordered characteristics of the EEG signals of the depression patient or the output results of the binary classification module of the depression assessment device to assist in judging the patient's condition and recovery status.

[0157] Figure 7 is the change of multi-scale intrinsic fuzzy entropy (preferably the average value of 8 patients) before and after drug treatment (scale τ is 1-10), Figure 7 It can be seen that after drug treatment, the multi-scale inherent fuzzy entropy has decreased and the patient's condition has recovered.

[0158] Figure 8 The multi-scale fuzzy entropy of 8 patients with depression before and after medication changes, such as Figure 8 As shown, when the time scale factor is 10, the fuzzy entropy of 8 depression patients before drug treatment ( Figure 8 The 8 data points on the left in the middle) change to the fuzzy entropy after drug treatment ( Figure 8 Among the 8 data points on the right side of the figure, only one patient’s fuzzy entropy increased, one patient’s fuzzy entropy changed little, and the other six patients’ fuzzy entropies decreased to varying degrees.

[0159] Fig. 9 It is a comparison chart of the multi-scale intrinsic fuzzy entropy of the patient (preferably the average value of 8 patients) and the multi-scale intrinsic fuzzy entropy of the healthy control group before drug treatment.

[0160] Fig.10It is a comparison chart of the multi-scale intrinsic fuzzy entropy of patients after drug treatment (preferably the average value of 8 patients) and the multi-scale intrinsic fuzzy entropy of the healthy control group.

[0161] Depend on Figures 7 to 10 It can be seen that the biometric information (inherent fuzzy entropy, i.e., the disordered characteristics of the coarse-grained signal point time series at each time scale) acquired by the biometric information acquisition method / device for depression assessment disclosed in the present invention can reflect the patient's condition and recovery status.

[0162] In the description of this specification, the description with reference to the terms "one embodiment / method", "some embodiments / methods", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present application. In this specification, the schematic representations of the above terms are not necessarily the same embodiment / method or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments / methods or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments / methods or examples described in this specification and the features of the different embodiments / methods or examples, unless they are contradictory.

[0163] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0164] Those skilled in the art should understand that the above embodiments are only for the purpose of clearly illustrating the present disclosure, and are not intended to limit the scope of the present disclosure. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present disclosure.

Claims

1. A method for obtaining biometric information for depression assessment, characterized in that: include: S102, performing noise reduction processing on the acquired electroencephalogram signal of the measured object to obtain the electroencephalogram signal after noise reduction processing; S104, performing feature enhancement processing on the EEG signal after the noise reduction processing to obtain the EEG signal after the feature enhancement processing; S106, converting the electroencephalogram signal after the feature enhancement processing into a coarse-grained signal point time series at multiple time scales to obtain a coarse-grained signal point time series at each time scale; S108, respectively obtaining disordered features of the coarse-grained signal point time series at each time scale as the biometric information for depression assessment; and S110, acquiring the integrated disorder feature information of the multiple time scales based on the disorder feature of the coarse-grained signal point time series at each time scale, to serve as the biometric feature information for depression assessment; Among them, based on the disorder characteristics of the coarse-grained signal point time series at each time scale, the comprehensive disorder characteristic information of multiple time scales is obtained, including: Different weight values ​​are given to the disordered features of the time series of coarse-grained signal points at different time scales to obtain the comprehensive disordered feature information of multiple time scales, and a larger weight value is given to the disordered features of the time series of coarse-grained signal points at a larger time scale; Among them, S104, performing feature enhancement processing on the EEG signal after the noise reduction processing to obtain the EEG signal after the feature enhancement processing, includes: S1041, taking the electroencephalogram signal as an initial signal to be processed, obtaining an upper envelope and a lower envelope of the initial signal to be processed, and obtaining a mean line of the upper envelope and the lower envelope as an initial mean line; S1042, subtracting the initial mean line from the initial signal to be processed to obtain an intermediate signal to be processed; S1043, obtaining an upper envelope and a lower envelope of the intermediate signal to be processed, and obtaining a mean line of the upper envelope and the lower envelope as an intermediate mean line; S1044, repeating S1043 multiple times until the number of extreme value signal points among all signal points of the intermediate signal to be processed is the same as the number of zero-crossing signal points or differs by 1, and taking the intermediate signal to be processed at this time as the first-order signal component of the electroencephalogram signal; Subtracting the first-order signal component from the initial signal to be processed to obtain a first-order signal residual, taking the first-order signal residual as a new signal to be processed, and performing the same processing as steps S1041 to S1044 on the new signal to be processed until the n-th order signal residual becomes a monotonic function; Among them, a total of n-order signal components are obtained, and n is a natural number greater than 1; S1045, reconstructing the electroencephalogram signal based on the first-order signal component to the n-th order signal component and the n-th order signal residual to obtain the electroencephalogram signal after the feature enhancement processing; Among them, the following formula is used for reconstruction: in, is the EEG signal after feature enhancement processing, c j (t) is the j-th order signal component, r n (t) is the n-th order signal margin.

2. The method for obtaining biometric information for depression assessment according to claim 1, characterized in that: The integrated disorder feature information of the multiple time scales is obtained based on the disorder feature of the coarse-grained signal point time series at each time scale, including: The disorder characteristics of the coarse-grained signal point time series at each time scale are given the same or different weight values ​​to obtain the comprehensive disorder characteristic information of the multiple time scales.

3. The method for obtaining biometric information for depression assessment according to claim 1 or 2, characterized in that: The disordered characteristic of the coarse-grained signal point time series at each time scale is fuzzy entropy.

4. The method for obtaining biometric information for depression assessment according to claim 1 or 2, characterized in that: The noise reduction process includes: removing electrooculographic false signals, electromyographic false signals and / or electrocardiographic false signals in the electroencephalogram signal.

5. A biometric information acquisition device for depression assessment, characterized in that: include: A noise reduction processing module, wherein the noise reduction processing module performs noise reduction processing on the acquired electroencephalogram signal of the measured object to obtain the electroencephalogram signal after the noise reduction processing; A feature enhancement processing module, wherein the feature enhancement processing module performs feature enhancement processing on the EEG signal after the noise reduction processing to obtain an EEG signal after feature enhancement processing; A conversion module, wherein the conversion module converts the electroencephalogram signal after the feature enhancement processing into a coarse-grained signal point time series at multiple time scales to obtain a coarse-grained signal point time series at each time scale; A disordered feature acquisition module, wherein the disordered feature acquisition module acquires disordered features of the coarse-grained signal point time series at each time scale, respectively, to serve as the biometric feature information for depression assessment; and A disordered feature comprehensive processing module, wherein the disordered feature comprehensive processing module obtains comprehensive disordered feature information of multiple time scales based on the disordered features of the coarse-grained signal point time series at each time scale, so as to serve as biometric feature information for depression assessment; Among them, based on the disorder characteristics of the coarse-grained signal point time series at each time scale, the comprehensive disorder characteristic information of multiple time scales is obtained, including: Different weight values ​​are given to the disordered features of the time series of coarse-grained signal points at different time scales to obtain the comprehensive disordered feature information of multiple time scales, and a larger weight value is given to the disordered features of the time series of coarse-grained signal points at a larger time scale; The step of performing feature enhancement processing on the EEG signal after the noise reduction processing to obtain the EEG signal after the feature enhancement processing comprises the following steps: S1041, taking the electroencephalogram signal as an initial signal to be processed, obtaining an upper envelope and a lower envelope of the initial signal to be processed, and obtaining a mean line of the upper envelope and the lower envelope as an initial mean line; S1042, subtracting the initial mean line from the initial signal to be processed to obtain an intermediate signal to be processed; S1043, obtaining an upper envelope and a lower envelope of the intermediate signal to be processed, and obtaining a mean line of the upper envelope and the lower envelope as an intermediate mean line; S1044, repeating S1043 multiple times until the number of extreme value signal points among all signal points of the intermediate signal to be processed is the same as the number of zero-crossing signal points or differs by 1, and taking the intermediate signal to be processed at this time as the first-order signal component of the electroencephalogram signal; Subtracting the first-order signal component from the initial signal to be processed to obtain a first-order signal residual, taking the first-order signal residual as a new signal to be processed, and performing the same processing as steps S1041 to S1044 on the new signal to be processed until the n-th order signal residual becomes a monotonic function; Among them, a total of n-order signal components are obtained, and n is a natural number greater than 1; S1045, reconstructing the electroencephalogram signal based on the first-order signal component to the n-th order signal component and the n-th order signal residual to obtain the electroencephalogram signal after the feature enhancement processing; Among them, the following formula is used for reconstruction: in, is the EEG signal after feature enhancement processing, c j (t) is the j-th order signal component, r n (t) is the n-th order signal margin.

6. A method for constructing a depression assessment device, using the biometric information for depression assessment of multiple subjects obtained by the biometric information acquisition method described in any one of claims 1 to 4 to train a binary classifier to obtain a depression assessment device.

7. An electronic device, characterized in that: include: A memory storing execution instructions; as well as A processor, wherein the processor executes the execution instructions stored in the memory, so that the processor executes the biometric information acquisition method for depression assessment described in any one of claims 1 to 4 and / or the construction method described in claim 6.

8. A readable storage medium, characterized in that: The readable storage medium stores execution instructions, which, when executed by a processor, are used to implement the biometric information acquisition method for depression assessment described in any one of claims 1 to 4 and / or the construction method described in claim 6.

Images