Assessment method of insomnia treatment effect and related equipment thereof
By acquiring and processing cortical signals from insomnia patients using fNIRS technology and employing a target model to evaluate the treatment effect of insomnia, this approach addresses the lack of objective evaluation in existing technologies, enabling accurate efficacy assessment and scientific treatment decision-making.
Patent Information
- Application Number
- CN202510772807.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-11
- Publication Date
- 2025-11-11
AI Technical Summary
Current technologies lack objective methods to quantify the severity of insomnia and the efficacy of acupuncture treatment for insomnia, relying mainly on subjective sleep quality assessments, which cannot effectively guide treatment decisions.
Functional near-infrared spectroscopy (fNIRS) was used to acquire cortical signals of insomnia patients before and after treatment. The signals were preprocessed and converted into hemoglobin concentration data. A trained target model was used to extract a set of effective feature values, and the difference in classification labels was calculated to evaluate the treatment effect.
It enables an objective and accurate assessment of the effectiveness of insomnia treatment, reduces the shortcomings of subjective judgment, and provides scientific treatment guidance.
Smart Images
Figure CN120929869A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of treatment efficacy evaluation, and more particularly to a method and related equipment for evaluating the efficacy of insomnia treatment. Background Technology
[0002] Insomnia is a common sleep disorder. Sleep disorders and the resulting daytime fatigue can cause severe distress and significant damage to patients' social, work, and economic well-being. Severe insomnia can affect daily life and even develop into depression. Traditional Chinese medicine acupuncture treatment for insomnia has unique advantages such as significant efficacy, minimal side effects, and high cost-effectiveness, and is gradually becoming one of the best practices for treating insomnia, gaining popularity among more and more patients. However, current assessments of insomnia and the degree of improvement through treatment mainly rely on evaluations of sleep quality and its improvement, which are relatively subjective. Objective assessment methods are lacking to quantify the severity of insomnia and the effectiveness of treatment, thus hindering decision-making. Summary of the Invention
[0003] In view of the above problems, embodiments of the present invention provide a method for evaluating the treatment effect of insomnia, as well as an evaluation device, evaluation system, evaluation apparatus and electronic device, computer-readable storage medium and computer program product, for objectively evaluating the degree of insomnia in insomnia patients. The evaluation results are accurate and can effectively evaluate the efficacy of insomnia treatment and guide decision-making.
[0004] According to a first aspect of the present invention, a method for evaluating the therapeutic effect of insomnia is provided, the evaluation method comprising: Acquire a first fNIRS signal and a second fNIRS signal, wherein the first fNIRS signal is the fNIRS signal of the insomnia patient before treatment, and the second fNIRS signal is the fNIRS signal of the insomnia patient after treatment; The first fNIRS signal is preprocessed to obtain the first set of effective feature values; The second fNIRS signal is preprocessed to obtain a second set of effective feature values, wherein the first set of effective feature values and the second set of effective feature values are related to the severity of insomnia in the insomnia patient; The first effective feature value set and the second effective feature value set are respectively input into the target model to obtain the first classification label corresponding to the first effective feature value set and the second classification label corresponding to the second feature value set. The target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia. Based on the first classification label and the second classification label, the insomnia treatment effect results of the insomnia patients are obtained, wherein the classification label is used to indicate the degree of insomnia.
[0005] The evaluation method provided by the first scheme of this application extracts an effective feature value set and inputs it into a target model to obtain different classification labels for insomnia patients before and after treatment. Based on the different classification labels of insomnia patients before and after treatment, the final treatment efficacy result is obtained. Since the target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia, the classification labels of insomnia patients before and after treatment obtained by the trained target model can more objectively and accurately assess and quantify the severity of insomnia before treatment and the treatment efficacy after treatment compared with subjective evaluation, thus providing accurate guidance for subsequent treatment decisions.
[0006] In an alternative approach, the evaluation method further includes: Obtain sample datasets from multiple age groups. Each sample dataset from each age group includes a set of effective feature values corresponding to the fNIRS signals of insomnia patients with different degrees of insomnia in the stated age group, and a preset classification label corresponding to each set of effective feature values. The sample datasets from the various age groups are input into a general model for training to obtain the target model.
[0007] In this embodiment, incorporating the influence factor of different age groups into the general model for training can further improve the accuracy of the target model and enhance the accuracy of quantitative assessment of treatment efficacy.
[0008] In one alternative approach, the preprocessing of the first fNIRS signal to obtain the first set of signal feature values includes: The first fNIRS signal is converted into first hemoglobin concentration data; The first set of effective feature values is obtained based on the first hemoglobin concentration data.
[0009] In this embodiment, it is understood that hemoglobin concentration is closely related to insomnia, and the effective feature value set obtained based on hemoglobin concentration is closely related to the degree of insomnia. By inputting the effective feature value set into the target model, the accuracy and running efficiency of the target model can be greatly improved compared with directly inputting the first fNIRS signal or hemoglobin concentration data into the target model.
[0010] In one alternative approach, the preprocessing of the second fNIRS signal to obtain the second signal feature set includes: The second fNIRS signal is converted into second hemoglobin concentration data; The second set of effective feature values is obtained based on the second hemoglobin concentration data.
[0011] In one optional approach, the first hemoglobin concentration data includes first frontal lobe concentration data, first parietal lobe concentration data, first temporal lobe concentration data, and first occipital lobe concentration data, wherein obtaining the first set of effective feature values based on the first hemoglobin concentration data includes: Extract the first frontal lobe feature value, first parietal lobe feature value, first temporal lobe feature value, and first occipital lobe feature value corresponding to the first frontal lobe concentration data, the first parietal lobe concentration data, the first temporal lobe concentration data, and the first occipital lobe concentration data, respectively; Determine the weight values corresponding to the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, and the first occipital lobe feature value, respectively; The first effective feature value set is formed by the weight values corresponding to the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, the first occipital lobe feature value, and the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, and the first occipital lobe feature value.
[0012] In this embodiment, since the hemoglobin concentration varies in different areas of the brain and the degree of correlation with insomnia also varies, by extracting the hemoglobin concentration in different areas of the cerebral cortex and assigning them different weights to form a first effective feature value set, the severity of the patient's insomnia and the treatment efficacy can be evaluated more objectively and accurately.
[0013] In an alternative approach, converting the first fNIRS signal into first hemoglobin concentration data includes: Motion artifacts are removed during the acquisition of the first fNIRS signal, and the first fNIRS signal after removing the motion artifacts is converted into a first optical density signal. The first optical density signal is converted into first hemoglobin concentration data.
[0014] In this embodiment, by removing interference signals from the first fNIRS signal, the input data required by the target model can be obtained more directly, thereby making the subsequent results more accurate.
[0015] In one alternative approach, obtaining the insomnia treatment effect result for the insomnia patient based on the first classification label and the second classification label includes: Determine the difference between the value corresponding to the second category label and the value corresponding to the first category label; If the difference is greater than or equal to a first preset value, the insomnia treatment is determined to be significantly effective. If the difference is less than a first preset value and greater than or equal to a second preset value, the insomnia treatment effect is determined to be generally effective. If the difference is less than the second preset value, the insomnia treatment is determined to be ineffective.
[0016] In this embodiment, the treatment results of insomnia patients are obtained by calculating the difference between classification labels, thus achieving an objective evaluation of the treatment efficacy of insomnia patients. This makes up for the shortcomings and defects of subjective judgment in the prior art and is more scientific and efficient.
[0017] According to a second aspect of the present invention, an evaluation device for the treatment effect of insomnia is provided, comprising a processor, a connection interface, and a display device. The processor is connected to both the connection interface and the display device. The processor is configured to acquire a first fNIRS signal and a second fNIRS signal through the connection interface, and to preprocess the first fNIRS signal and the second fNIRS signal to obtain a first set of effective feature values and a second set of effective feature values, wherein the first fNIRS signal is the fNIRS signal of the insomnia patient before insomnia treatment, and the second fNIRS signal is the fNIRS signal of the insomnia patient after insomnia treatment. The processor is further configured to input the first effective feature value set and the second effective feature value set into the target model respectively, to obtain the first classification label corresponding to the first effective feature value set and the second classification label corresponding to the second feature value set respectively, and to obtain the insomnia treatment effect of the insomnia patient based on the first classification label and the second classification label; wherein, the target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia; The display device is used to display the results of the insomnia treatment.
[0018] The assessment equipment provided in this solution enables the above assessment methods to operate smoothly and stably on the assessment equipment, and the operator can intuitively obtain the final treatment effect of the patient's insomnia through the display device.
[0019] In one alternative approach, the processor runs a data acquisition module, a data processing module, and a result judgment module; The processor executes the data acquisition module to acquire the first fNIRS signal and the second fNIRS signal; The processor runs the data processing module to obtain the first set of effective feature values and the second set of effective feature values based on the first fNIRS signal and the second fNIRS signal, respectively. The processor runs the result judgment module to obtain the first classification label and the second classification label based on the first effective feature value set, the second effective feature value set and the target model, and then obtains the insomnia treatment effect result.
[0020] In one alternative embodiment, the display device includes a display interface, which includes a basic information display area and a result display area. The basic information display area includes a basic information sub-area for the insomnia patient, a sub-area for the acquisition status of the first fNIRS signal and the second fNIRS signal, and a first operation button. The result display area includes a result display sub-area and a second operation button. The processor is configured to acquire the first fNIRS signal and the second fNIRS signal when receiving the trigger signal of the first operation button, and display the insomnia treatment effect rating result obtained based on the first fNIRS signal and the second fNIRS signal through the result display sub-area; The processor is used to export a treatment effect result report upon receiving a trigger signal from the second operation button.
[0021] In this embodiment, the different partitions and button settings of the display interface not only allow operators to obtain detailed patient information and treatment results, but also enable them to operate the assessment equipment more directly and conveniently through the buttons, further improving assessment efficiency and saving time and labor costs.
[0022] According to a third aspect of the present invention, an insomnia treatment effect evaluation system is provided, comprising a signal acquisition device and the aforementioned evaluation device, wherein the signal acquisition device is connected to the evaluation device via a connection interface, and the signal acquisition device is used to acquire fNIRS signals from the cerebral cortex of insomnia patients.
[0023] The assessment system provided in this solution includes hardware such as a headgear, electrodes, a light source emitter, and a detector, which can accurately obtain the fNIRS signal of the patient's cerebral cortex, facilitating subsequent signal extraction and conversion.
[0024] According to a fourth aspect of the present invention, an evaluation device for the treatment effect of insomnia is provided, characterized in that it comprises: The acquisition module is used to acquire a first fNIRS signal and a second fNIRS signal, wherein the first fNIRS signal is the fNIRS signal of the insomnia patient before treatment, and the second fNIRS signal is the fNIRS signal of the insomnia patient after treatment; The processing module is configured to preprocess the first fNIRS signal to obtain a first set of effective feature values; and to preprocess the second fNIRS signal to obtain a second set of effective feature values, wherein the first set of effective feature values and the second set of effective feature values are related to the severity of insomnia in the insomnia patient; The determination module is used to input the first effective feature value set and the second effective feature value set into the target model respectively, and obtain the first classification label corresponding to the first effective feature value set and the second classification label corresponding to the second feature value set respectively. The target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia. The judgment module is used to obtain the insomnia treatment effect result of the insomnia patient based on the first classification label and the second classification label, wherein the classification label is used to indicate the degree of insomnia.
[0025] According to a fifth aspect of the present invention, an electronic device is provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor executing the computer program to implement the insomnia treatment effect evaluation method as described above.
[0026] According to a sixth aspect of the present invention, a computer-readable storage medium is provided, including a stored computer program, which, when executed, performs an evaluation method for the insomnia treatment effect of any of the above embodiments.
[0027] According to a seventh aspect of the present invention, a computer program product is provided that, when the computer program product is run on an electronic device, causes the electronic device to perform the method for evaluating the effect of insomnia treatment in any of the above embodiments.
[0028] The beneficial effects that the evaluation device provided in the fourth aspect, the electronic device provided in the fifth aspect, the computer-readable storage medium provided in the sixth aspect, and the computer program product provided in the seventh aspect can achieve can be referred to the beneficial effects that can be achieved in the first aspect and any of its embodiments, the second aspect and any of its embodiments, and the third aspect and any of its embodiments, and will not be repeated here. Attached Figure Description
[0029] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic diagram of the structure of an insomnia treatment efficacy evaluation system according to this application is shown; Figure 2 A schematic diagram illustrating the working principle of the signal acquisition device is shown. Figure 3 A schematic diagram of a specific structure of a display device is shown; Figure 4 A schematic diagram of the structure of another insomnia treatment efficacy evaluation system of this application is shown; Figure 5A flowchart of a method for evaluating the therapeutic effect of insomnia according to this application is shown; Figure 6 The flowchart of fNIRS signal data conversion is shown; Figure 7 A schematic diagram of the cerebral cortex divisions is shown; Figure 8 A table comparing the HbO concentration ranges in different regions of the cerebral cortex of insomnia patients and healthy individuals in a resting state is shown. Detailed Implementation
[0030] To enable those skilled in the art to better understand the technical solutions of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. Although the accompanying drawings and specific embodiments describe exemplary embodiments of the present invention, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.
[0031] The terms "first," "second," and similar words used in this application do not indicate any order, quantity, or importance, but are merely used for distinction. The terms "including" or "comprising," etc., used in this application mean that the element preceding the word encompasses the elements listed after the word, and do not exclude the possibility of encompassing other elements. In this application, the arrows shown in the figures for each step are merely examples of the execution order, not limitations. The technical solution of this application is not limited to the execution order described in the embodiments. The steps in the execution order can be combined, broken down, or rearranged, as long as the logical relationship of the executed content is not affected.
[0032] All terms used in this application (including technical or scientific terms) have the same meaning as understood by one of ordinary skill in the art to which this application pertains, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries should be interpreted as having meanings consistent with their meanings in the context of the relevant art, and not as idealized or highly formalized, unless expressly defined herein. Technologies and equipment known to one of ordinary skill in the art may not be discussed in detail, but where appropriate, such technologies and equipment should be considered part of the specification.
[0033] The term "functional near-infrared spectroscopy (fNIRS)" used in the following embodiments of this application refers to a non-invasive, high spatial resolution, and high-precision medical imaging technique that supports multiple channels, multiple brain regions, multiple modalities, and multiple time points. Compared with traditional neuroimaging techniques, it excels at detecting hemodynamic responses in the cerebral cortex (such as the distribution and changes in hemoglobin concentration in various brain regions), making the detection and analysis of blood oxygenation activity in the brain more effective. It can also reflect potential cortical neural activity by combining neurovascular coupling effects.
[0034] fNIRS signals are biological signals from the cerebral cortex acquired using fNIRS technology.
[0035] Insomnia is a common sleep disorder. Sleep disorders and the resulting daytime fatigue can cause severe distress and significant impairment in social, work, and economic aspects. The global prevalence among adults is approximately 4%–22%. Severe insomnia can affect daily life and even develop into depression. Currently, Western medicine often uses long-term medication for severe insomnia, but the efficacy is unsatisfactory, and long-term medication can cause serious adverse reactions, leading to a growing search for alternative therapies. Traditional Chinese medicine acupuncture treatment for insomnia has unique advantages such as significant efficacy, minimal side effects, and high cost-effectiveness, and is gradually becoming one of the best practices for treating insomnia, gaining popularity among more and more patients. In general, acupuncture treatment for insomnia can improve sleep through several aspects, including the nervous system, neurotransmitters, inflammatory factors, and circadian rhythm genes.
[0036] Current assessments of insomnia and the degree of improvement through treatment rely on evaluations of sleep quality and its improvement, using questionnaire scoring (Pittsburgh Sleep Quality Index (PSQI) scores), which is relatively subjective. The lack of objective assessment methods to quantify the severity of insomnia makes it difficult to effectively evaluate the efficacy of acupuncture treatment for insomnia and guide decision-making. Furthermore, research using various modern medical imaging techniques (fNIRS, fMRI, EEG, etc.) indicates that insomnia at the microscopic level is specifically related to dysfunction of the cerebral cortex.
[0037] To address the aforementioned issues, this application provides an evaluation system, equipment, and method for assessing the effectiveness of insomnia treatment. These methods objectively evaluate the degree of insomnia in patients, providing accurate results that effectively assess the therapeutic efficacy of insomnia treatment and guide decision-making.
[0038] First, the insomnia treatment efficacy evaluation system provided in the embodiments of this application is introduced.
[0039] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of an insomnia treatment effect evaluation system provided in an embodiment of this application.
[0040] like Figure 1 As shown, the insomnia treatment efficacy assessment system 100 may include a signal acquisition device 10 and an assessment device 20. The signal acquisition device 10 is connected to the assessment device 20 via a connection interface 21. The signal acquisition device 10 is used to acquire fNIRS signals from the cerebral cortex of insomnia patients. The assessment device 20 is used to process the fNIRS signals acquired by the signal acquisition device 10 to obtain an assessment of the degree of insomnia in the insomnia patients.
[0041] In some embodiments, the signal acquisition device 10 may be a medical instrument (such as a commercially available medical instrument) that includes hardware such as a headgear 11, electrodes, a light source emitter, and a detector, and can accurately obtain the fNIRS signal of the patient's cerebral cortex.
[0042] When evaluating the treatment efficacy of insomnia patients, the signal acquisition device 10 can be worn on the patient's head to collect fNIRS signals, which will facilitate the subsequent processing of the fNIRS signals by the evaluation device 20.
[0043] In some implementations, such as Figure 2 As shown, Figure 2 This is a schematic diagram of the working principle of the signal acquisition device 10. The distance between each transmitter and detector in the signal acquisition device 10 is about 3cm. The optical signal is emitted through the transmitter, passes through the scalp and skull, and is captured by the detector again through the skull and scalp after reflection and refraction in the cerebral cortex. The evaluation device 20 obtains the light signal captured by the detector through the connection interface 21 and performs subsequent steps.
[0044] It should be noted that the distance between the transmitter and the detector is not limited to this embodiment and can also be other distances, such as 4cm, 5cm, etc.
[0045] like Figure 1 In the illustrated embodiment, the evaluation device 20 may include a processor (not shown), a connection interface 21, and a display device 22, with the processor connected to both the connection interface 21 and the display device 22. For example, the evaluation device 20 may be a computer, or it may be a device capable of acquiring and processing data signals.
[0046] A processor can be a central processing unit (CPU), microcontroller unit (MCU), microprocessor unit (MPU), system on chip (SOC), digital signal processor (DSP), graphics processing unit (GPU), or other integrated circuits used to execute program instructions, process data, and control system operation.
[0047] In this embodiment, the processor is used to acquire the first fNIRS signal and the second fNIRS signal through the connection interface 21, and preprocess the first fNIRS signal and the second fNIRS signal to obtain the first effective feature value set and the second effective feature value set, respectively. The first fNIRS signal is the fNIRS signal of the insomnia patient before insomnia treatment, and the second fNIRS signal is the fNIRS signal of the insomnia patient after insomnia treatment.
[0048] The processor is also used to input the first effective feature value set and the second effective feature value set into the target model, respectively, to obtain the first classification label corresponding to the first effective feature value set and the second classification label corresponding to the second feature value set, and based on the first classification label and the second classification label, to obtain the insomnia treatment effect for insomnia patients. The target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia.
[0049] Display device 22 is used to display the results of the insomnia treatment.
[0050] The assessment device 20 provided in this solution processes the fNIRS signals of insomnia patients before and after treatment using a processor to obtain the insomnia treatment effect, and displays the insomnia treatment effect result through a display device 22. The assessment operation is simple, and the operator can intuitively obtain the patient's final insomnia treatment effect result through the display device 22.
[0051] In some embodiments, the processor runs a data acquisition module, a data processing module, and a result judgment module. The processor runs the data acquisition module to acquire a first fNIRS signal and a second fNIRS signal. The processor runs the data processing module to obtain a first set of effective feature values and a second set of effective feature values based on the first and second fNIRS signals, respectively. The processor runs the result judgment module to obtain a first classification label and a second classification label based on the first set of effective feature values, the second set of effective feature values, and the target model, thereby obtaining the insomnia treatment effect result.
[0052] The data acquisition module, data processing module, and result judgment module running on the processor work together to enable the processor to obtain accurate results on the treatment effect of insomnia.
[0053] In some embodiments, the data processing module may include a data preprocessing module and a feature extraction module. The processor runs the data preprocessing module to convert the first fNIRS signal into first hemoglobin concentration data and the second fNIRS signal into second hemoglobin concentration data. The processor runs the feature extraction module to obtain a first set of valid feature values based on the first hemoglobin concentration data and a second set of valid feature values based on the second hemoglobin concentration data.
[0054] In this embodiment, it is understood that hemoglobin concentration is closely related to insomnia, and the effective feature value set obtained based on hemoglobin concentration is closely related to the degree of insomnia. By inputting the effective feature value set into the target model, the accuracy and running efficiency of the target model calculation can be greatly improved compared with directly inputting the first fNIRS signal or hemoglobin concentration data into the target model.
[0055] In some implementations, the data preprocessing module converts the first fNIRS signal into first hemoglobin concentration data. Specifically, this may include removing motion artifacts during the acquisition of the first fNIRS signal, converting the motion artifact-removed first fNIRS signal into a first optical density signal, and then converting the first optical density signal into first hemoglobin concentration data.
[0056] In this embodiment, by removing interference signals from the first fNIRS signal, the input data required by the target model can be obtained more directly, thereby making the subsequent results more accurate.
[0057] It is understandable that the data preprocessing module converts the second fNIRS signal into second hemoglobin concentration data in the same way that the data preprocessing module converts the first fNIRS signal into first hemoglobin concentration data, and will not be described again.
[0058] In some embodiments, the first hemoglobin concentration data includes first frontal lobe concentration data, first parietal lobe concentration data, first temporal lobe concentration data, and first occipital lobe concentration data. The feature extraction module obtains a first set of effective feature values based on the first hemoglobin concentration data, which may specifically include: Extract the first frontal lobe feature value, first parietal lobe feature value, first temporal lobe feature value, and first occipital lobe feature value corresponding to the first frontal lobe concentration data, first parietal lobe concentration data, first temporal lobe concentration data, and first occipital lobe concentration data, respectively; Determine the weight values corresponding to the feature values of the first frontal lobe, the first parietal lobe, the first temporal lobe, and the first occipital lobe, respectively; The first effective feature value set is formed by the weight values corresponding to the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, the first occipital lobe feature value, and the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, and the first occipital lobe feature value.
[0059] In this embodiment, since the hemoglobin concentration varies in different areas of the brain and the degree of correlation with insomnia also varies, by extracting the hemoglobin concentration in different areas of the cerebral cortex and assigning them different weights to form a first effective feature value set, the severity of the patient's insomnia and the treatment efficacy can be evaluated more objectively and accurately.
[0060] It is understandable that the feature extraction module obtains the second set of effective feature values based on the second hemoglobin concentration data in the same way as it obtains the first set of effective feature values based on the first hemoglobin concentration data, and will not be described in detail here.
[0061] In some embodiments, both the first hemoglobin concentration data and the second hemoglobin concentration data include oxyhemoglobin HbO concentration data and deoxyhemoglobin HbR concentration data. The optical density signal of the first fNIRS signal is converted into oxyhemoglobin HbO concentration data and deoxyhemoglobin HbR concentration data, which is achieved by modifying the Beer-Lambert Law.
[0062] Hemoglobin concentration is closely related to insomnia. The effective feature set obtained based on hemoglobin concentration is closely related to the degree of insomnia. By inputting the effective feature set into the target model, the accuracy and efficiency of the target model calculation can be greatly improved compared to directly inputting the first fNIRS signal or hemoglobin concentration data into the target model. Of course, in some other embodiments, the data after simple preprocessing of the first fNIRS signal can also be directly input into the target model as the feature set, reducing the preprocessing steps.
[0063] In some embodiments, the result judgment module may also be called a rating module. Specifically, the result judgment module is used to determine the difference between the value corresponding to the second classification label and the value corresponding to the first classification label. If the difference is greater than or equal to a first preset value, the insomnia treatment effect is determined to be significantly effective. If the difference is less than the first preset value but greater than or equal to a second preset value, the insomnia treatment effect is determined to be generally effective. If the difference is less than the second preset value, the insomnia treatment effect is determined to be ineffective.
[0064] In this embodiment, the treatment results for insomnia patients are obtained by calculating the difference between classification labels, achieving an objective evaluation of the treatment efficacy and overcoming the shortcomings and defects of subjective judgment in existing technologies, making it more scientific and efficient. Of course, through module combination and merging, the processor can also have fewer modules.
[0065] like Figure 1 and Figure 3 As shown, Figure 3 This is a schematic diagram of the specific structure of a display device 22 provided in an embodiment of this application.
[0066] For example, the display device 22 may be an electronic screen such as a display screen, and the display interface 221 may be a human-computer interaction interface such as a visual interactive front-end interface.
[0067] In this embodiment, the display device 22 may include a display interface 221, which includes a basic information display area 2211 and a result display area 2212. The basic information display area 2211 includes a basic information sub-area 2213 for insomnia patients, a sub-area 2214 for the acquisition status of the first fNIRS signal and the second fNIRS signal, and a first operation button 2215. The result display area 2212 includes a result display sub-area 2216 and a second operation button 2217. The processor, upon receiving a trigger signal from the first operation button 2215, acquires the first fNIRS signal and the second fNIRS signal and displays them in the acquisition status sub-area 2214, and displays the insomnia treatment effect rating result obtained based on the first fNIRS signal and the second fNIRS signal in the result display sub-area 2216. Upon receiving a trigger signal from the second operation button 2217, the processor exports a treatment effect result report.
[0068] By dividing the display interface 221 into different functional display zones and providing user-friendly operation buttons, operators can not only obtain detailed patient information and treatment results, but also operate the assessment device 20 more directly and conveniently through the buttons, further improving assessment efficiency and saving time and labor costs.
[0069] It should be noted that the first operation button 2215 and the second operation button 2217 mentioned in this embodiment can be virtual buttons on the display interface 221 or mechanical buttons set independently outside the display interface 221. This embodiment does not make specific limitations here.
[0070] Please see Figure 4 , Figure 4 This is a schematic diagram of another insomnia treatment effect evaluation system provided in the embodiments of this application.
[0071] Figure 4 The evaluation system shown is Figure 1 The evaluation systems shown are largely the same, and the similarities will not be repeated. The difference lies in the display interface of display device 22. Figure 4The display interface shown includes: a basic information display area 2211, a result display area 2212, and a target model operation area 2218. The basic information display area 2211 includes a basic information sub-area for insomnia patients (not shown in the figure), a sub-area for the acquisition status of the first fNIRS signal and the second fNIRS signal (not shown in the figure), and a first operation button (not shown in the figure). The result display area 2212 includes a result display sub-area 2216 and a second operation button 2217. The target model operation area 2218 includes a feature extraction result display area 2218a and a third operation button (not shown in the figure), a rating result display area 2218b, and a fourth operation button (not shown in the figure). The processor, upon receiving a trigger signal from the first operation button, acquires a first fNIRS signal and a second fNIRS signal and displays them in the acquisition status sub-area. Upon receiving a trigger signal from the third operation button, the processor extracts effective feature values from the acquired first and second fNIRS signals. Upon receiving a trigger signal from the fourth operation button, the processor inputs the extracted effective feature values into the target model and performs a rating assessment on the insomnia patient, obtaining an insomnia treatment effect rating result, which is displayed in the result display sub-area 2216. Upon receiving a trigger signal from the second operation button 2217, the processor exports a treatment effect result report.
[0072] By adding a feature extraction result display area 2218a and a third operation button, and a rating result display area 2218b and a fourth operation button to the target model operation area 2218, operators can distribute the operation and evaluation steps, improving operability. Simultaneously, the effective feature values and rating results of insomnia patients can be obtained in real time through the feature extraction result display area 2218a and the rating result display area 2218b, facilitating operators to check and verify the effective feature values and rating results, thus improving work efficiency.
[0073] It should be noted that the first operation button, the second operation button 2217, the third operation button and the fourth operation button mentioned in this embodiment can be virtual buttons on the display interface 221 or mechanical buttons set independently outside the display interface 221. This embodiment does not make specific limitations here.
[0074] It should be understood that the evaluation device 20 may have more or fewer components than shown in the figure, may combine two or more components, or may have different component configurations. The various components shown in the figure may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and / or application-specific integrated circuits.
[0075] This application embodiment also provides a method for evaluating the treatment effect of insomnia, which is operated in the aforementioned evaluation device 20. Figure 5This is a flowchart illustrating a method for evaluating the effectiveness of insomnia treatment provided in the application embodiments. Figure 5 As shown, the evaluation method includes the following S110~S150.
[0076] S110: Acquire the first fNIRS signal and the second fNIRS signal.
[0077] The first fNIRS signal is the fNIRS signal of the insomnia patient before treatment, and the second fNIRS signal is the fNIRS signal of the insomnia patient after treatment.
[0078] It is understandable that the first fNIRS signal of the cerebral cortex of the insomnia patient can be collected by the signal acquisition device 10 before the insomnia patient is treated, and the second fNIRS signal of the cerebral cortex of the insomnia patient can be collected by the signal acquisition device 10 after the insomnia patient is treated.
[0079] In this embodiment, the treatment received by the insomnia patient can be traditional Chinese medicine acupuncture. Of course, in other embodiments, the treatment received by the insomnia patient can be other treatment methods.
[0080] S120: Preprocess the first fNIRS signal to obtain the first set of effective eigenvalues.
[0081] S130: Preprocess the second fNIRS signal to obtain the second set of effective eigenvalues.
[0082] Among them, the first set of effective eigenvalues and the second set of effective eigenvalues are related to the severity of insomnia in insomnia patients.
[0083] Understandably, since both the first and second fNIRS signals are biological signals from the cerebral cortex, including signals strongly correlated with the degree of insomnia (such as oxyhemoglobin HbO and deoxyhemoglobin HbR signals) and signals weakly correlated with the degree of insomnia (such as cerebral hemodynamic signals, noise from heartbeat and respiration), preprocessing the first and second fNIRS signals removes signals weakly correlated with the degree of insomnia and retains signals strongly correlated with the degree of insomnia. The resulting set of effective feature values consists of numerical features strongly correlated with the degree of insomnia, which can improve the accuracy of insomnia-related signals and facilitate more accurate determination of the treatment effect of insomnia.
[0084] It should be noted that S120 and S130 do not indicate a sequential relationship and can be interchanged arbitrarily. This method does not impose specific restrictions on them.
[0085] S140: Input the first effective feature value set and the second effective feature value set into the target model respectively, and obtain the first classification label corresponding to the first effective feature value set and the second classification label corresponding to the second feature value set respectively.
[0086] The first category label can be a numerical value indicating the severity of insomnia before treatment, while the second category label can be another numerical value indicating the severity of insomnia after treatment. Quantifying the degree of insomnia in patients can reduce the interference of subjective factors, improve accuracy, and facilitate scientific decision-making for subsequent treatment.
[0087] The target model is trained based on a set of signal feature values corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia. These multiple degrees of insomnia may include multiple patients with severe insomnia, multiple patients with moderate insomnia, and multiple patients with mild insomnia. For example, the effective sleep duration for patients with severe insomnia may be less than 3 hours, for patients with moderate insomnia may be greater than 3 hours but less than 6 hours, and for patients with mild insomnia may be greater than 6 hours but less than 8 hours. Of course, in other embodiments, the determination of whether a patient is severely, moderately, or mildly insomniac may be based on criteria other than effective sleep duration. Alternatively, in other embodiments, the effective sleep duration for patients with severe, moderate, or mild insomnia may differ from the examples described above.
[0088] S150: Based on the first and second category labels, the results of insomnia treatment for insomnia patients are obtained. The category labels are used to indicate the degree of insomnia.
[0089] Understandably, by calculating the difference between the value corresponding to the second category label and the value corresponding to the first category label, the corresponding treatment effect for insomnia patients can be obtained. For example, if the difference is greater than or equal to a first preset value, the insomnia treatment effect is determined to be significantly effective; if the difference is less than the first preset value but greater than or equal to a second preset value, the insomnia treatment effect is determined to be generally effective; and if the difference is less than the second preset value, the insomnia treatment effect is determined to be ineffective. By calculating the difference between the category labels to obtain the treatment results for insomnia patients, an objective evaluation of the treatment efficacy is achieved, overcoming the shortcomings and defects of subjective judgment in existing technologies, making it more scientific and efficient.
[0090] The insomnia treatment efficacy evaluation method provided in this application extracts an effective feature value set and inputs it into a target model to obtain different classification labels for insomnia patients before and after treatment. Based on these different classification labels, the final treatment efficacy result is obtained. Since the target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia, the classification labels of insomnia patients before and after treatment obtained by this method through the trained target model can more objectively and accurately assess and quantify the severity of insomnia before treatment and the treatment efficacy after treatment compared to subjective evaluation, thus providing accurate guidance for subsequent treatment decisions.
[0091] In some implementations, the evaluation method further includes: acquiring multiple sample datasets of different age groups, each sample dataset including a set of effective feature values corresponding to the fNIRS signals of insomnia patients with different degrees of insomnia in multiple age groups and a preset classification label corresponding to each set of effective feature values; inputting the multiple sample datasets of different age groups into a general model for training to obtain the target model.
[0092] Because the effective feature values extracted from patients of different age groups vary significantly for the same degree of insomnia—for example, the effective feature values for older age groups may be higher than those for younger age groups for the same degree of insomnia—incorporating age group as a factor into the training of a general model can further improve the accuracy of the target model and enhance the accuracy of quantitative assessments of treatment efficacy.
[0093] In some embodiments, preprocessing the first fNIRS signal to obtain a first signal feature set includes: converting the first fNIRS signal into a first hemoglobin concentration; and obtaining a first effective feature set based on the first hemoglobin concentration data.
[0094] Hemoglobin concentration is closely related to insomnia. The effective feature set obtained based on hemoglobin concentration is closely related to the degree of insomnia. By inputting the effective feature set into the target model, the accuracy and efficiency of the target model calculation can be greatly improved compared to directly inputting the first fNIRS signal or hemoglobin concentration data into the target model. Of course, in some other embodiments, the data after simple preprocessing of the first fNIRS signal can also be directly input into the target model as the feature set, reducing the preprocessing steps.
[0095] It should be noted that the first hemoglobin concentration data in this embodiment includes both oxyhemoglobin (HbO) and deoxyhemoglobin (HbR) concentration data. By obtaining concentration data of two different hemoglobins, the data results can be cross-validated, improving data accuracy.
[0096] For example, the optical density signal of the first fNIRS signal is converted into oxyhemoglobin (HbO) concentration data and deoxyhemoglobin (HbR) concentration data using a modified Beer-Lambert Law.
[0097] Preprocessing the second fNIRS signal has the same effect as preprocessing the first fNIRS signal, and will not be described in detail here.
[0098] like Figure 6 As shown, Figure 6 This is a flowchart of the fNIRS signal data conversion process. Figure 6 In the illustrated embodiment, converting the first fNIRS signal into first hemoglobin concentration data includes: removing motion artifacts during the acquisition of the first fNIRS signal; converting the motion artifact-removed first fNIRS signal into a first optical density signal; removing interference signals (including low-frequency data drift and high-frequency noise such as heartbeat and respiration) from the first optical density signal; and converting the first optical density signal into first hemoglobin concentration data based on a modified Beer-Lambert law. This allows the target model to obtain the required input data more directly, resulting in more accurate subsequent results.
[0099] The same conversion is performed on the second fNIRS signal, which will not be repeated here.
[0100] Please see Figure 7 , Figure 7 This is a schematic diagram of the divisions of the cerebral cortex. (For example...) Figure 7 As shown, the human brain comprises four main regions: the frontal lobe, parietal lobe, temporal lobe, and occipital lobe. In some embodiments, the first hemoglobin concentration data includes first frontal lobe concentration data, first parietal lobe concentration data, first temporal lobe concentration data, and first occipital lobe concentration data. Obtaining a first effective feature value set based on the first hemoglobin concentration data includes: extracting the first frontal lobe feature value, first parietal lobe feature value, first temporal lobe feature value, and first occipital lobe feature value corresponding to the first frontal lobe concentration data, first parietal lobe concentration data, first temporal lobe concentration data, and first occipital lobe concentration data, respectively.
[0101] Determine the weight values corresponding to the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, and the first occipital lobe feature value, respectively; and construct the first effective feature value set by combining the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, the first occipital lobe feature value, and the weight values corresponding to the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, and the first occipital lobe feature value, respectively.
[0102] Please see Figure 8 , Figure 8This is a table comparing the HbO concentration ranges in different regions of the cerebral cortex of insomnia patients and healthy individuals in a resting state.
[0103] like Figure 8 As shown, the HbO concentration ranges in different regions of the cerebral cortex of insomnia patients at rest were: 6 μmol / L - 11 μmol / L in the frontal lobe, 5 μmol / L - 9 μmol / L in the temporal lobe, 5 μmol / L - 9 μmol / L in the parietal lobe, and 5 μmol / L - 7 μmol / L in the occipital lobe. In contrast, the HbO concentration ranges in different regions of the cerebral cortex of normal individuals at rest were: 5 μmol / L - 8 μmol / L in the frontal lobe, 4 μmol / L - 7 μmol / L in the temporal lobe, 4 μmol / L - 7 μmol / L in the parietal lobe, and 4 μmol / L - 6 μmol / L in the occipital lobe. It is evident that the HbO concentrations in different regions of the cerebral cortex of insomnia patients at rest were significantly higher than those of normal individuals. Therefore, different weightings were assigned to different regions of hemoglobin concentration, such as assigning higher weights to HbO in the frontal, temporal, and parietal lobes.
[0104] Because hemoglobin concentrations vary across different brain regions, and their correlation with insomnia also differs, I set up a corresponding number of signal acquisition channels for different regions of the cerebral cortex, assigning different weights to each region. This constitutes the first set of effective feature values, which can more objectively and accurately evaluate the severity of a patient's insomnia and the effectiveness of treatment.
[0105] For example, the number of signal acquisition channels configured for different regions of the cerebral cortex could be: 20 signal acquisition channels for the frontal lobe, 10 signal acquisition channels for the parietal lobe, 28 signal acquisition channels for the temporal lobe, and 12 signal acquisition channels for the occipital lobe. The weights assigned to different regions of the cerebral cortex could be: 0.40 for the frontal lobe, 0.20 for the parietal lobe, 0.28 for the temporal lobe, and 0.12 for the occipital lobe. The frontal and temporal lobes are given relatively more signal acquisition channels and weights because they are more closely associated with insomnia.
[0106] Understandably, there are significant differences in hemoglobin concentration changes across different brain regions in insomnia patients compared to healthy individuals. These biosignals also change significantly after acupuncture treatment. Based on this biosignal data, feature engineering is used to extract effective features, which are then combined with a target model to obtain corresponding classification labels. This allows for the assessment of insomnia in patients, also known as the grading of treatment effectiveness. The severity of insomnia before acupuncture treatment and the treatment effect after treatment can be termed the treatment effectiveness level. The treatment effectiveness results can serve as a micro-quantitative reference for doctors to diagnose patients' conditions, assisting in decision-making regarding insomnia treatment strategies and providing an objective quantitative evaluation of treatment efficacy.
[0107] In some embodiments, obtaining the insomnia treatment effect result for insomnia patients based on the first classification label and the second classification label includes: determining the difference between the value corresponding to the second classification label and the value corresponding to the first classification label; if the difference is greater than or equal to a first preset value, determining that the insomnia treatment effect is significantly effective; if the difference is less than the first preset value but greater than or equal to the second preset value, determining that the insomnia treatment effect is generally effective; and if the difference is less than the second preset value, determining that the insomnia treatment effect is ineffective.
[0108] For example, a first preset value of 20 and a second preset value of 10 can be set. When the difference between the value corresponding to the second category label of the insomnia patient and the value corresponding to the first category label is less than 10, the insomnia treatment effect is determined to be ineffective; when the difference between the value corresponding to the second category label of the insomnia patient and the value corresponding to the first category label is greater than 10 but less than 20, the insomnia treatment effect is determined to be generally effective; when the difference between the value corresponding to the second category label of the insomnia patient and the value corresponding to the first category label is greater than 20, the insomnia treatment effect is determined to be significantly effective.
[0109] In this embodiment, the treatment results of insomnia patients are obtained by calculating the difference between classification labels, thus achieving an objective evaluation of the treatment efficacy of insomnia patients. This makes up for the shortcomings and defects of subjective judgment in the prior art and is more scientific and efficient.
[0110] This application also provides an evaluation device for the treatment effect of insomnia, comprising: The acquisition module is used to acquire a first fNIRS signal and a second fNIRS signal, wherein the first fNIRS signal is the fNIRS signal of the insomnia patient before treatment, and the second fNIRS signal is the fNIRS signal of the insomnia patient after treatment.
[0111] The processing module is used to preprocess the first fNIRS signal to obtain a first set of effective feature values; and to preprocess the second fNIRS signal to obtain a second set of effective feature values, wherein the first set of effective feature values and the second set of effective feature values are related to the severity of insomnia in insomnia patients.
[0112] The determination module is used to input the first effective feature value set and the second effective feature value set into the target model respectively, and obtain the first classification label corresponding to the first effective feature value set and the second classification label corresponding to the second feature value set respectively. The target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia.
[0113] The judgment module is used to obtain the insomnia treatment effect results of insomnia patients based on the first classification label and the second classification label, wherein the classification label is used to indicate the degree of insomnia.
[0114] This application also provides an electronic device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor executing the computer program to implement the insomnia treatment effect evaluation method as described above.
[0115] This application also provides a computer-readable storage medium including a stored computer program, which, when executed, performs a method for evaluating the effectiveness of insomnia treatment according to any of the above embodiments.
[0116] This application also provides a computer program product that, when run on an electronic device, causes the electronic device to perform the insomnia treatment effect evaluation method in any of the above embodiments.
[0117] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Furthermore, the embodiments of this invention are not directed to any particular programming language.
[0118] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.
[0119] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.
[0120] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware.
Claims
1. A method for evaluating the efficacy of insomnia treatment, characterized in that, The evaluation method includes: Acquire a first fNIRS signal and a second fNIRS signal, wherein the first fNIRS signal is the fNIRS signal of the insomnia patient before treatment, and the second fNIRS signal is the fNIRS signal of the insomnia patient after treatment; The first fNIRS signal is preprocessed to obtain the first set of effective feature values; The second fNIRS signal is preprocessed to obtain a second set of effective feature values, wherein the first set of effective feature values and the second set of effective feature values are related to the severity of insomnia in the insomnia patient; The first effective feature value set and the second effective feature value set are respectively input into the target model to obtain the first classification label corresponding to the first effective feature value set and the second classification label corresponding to the second feature value set. The target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia. Based on the first classification label and the second classification label, the insomnia treatment effect results of the insomnia patients are obtained, wherein the classification label is used to indicate the degree of insomnia.
2. The evaluation method according to claim 1, characterized in that, The evaluation method also includes: Obtain sample datasets from multiple age groups. Each sample dataset from each age group includes a set of effective feature values corresponding to the fNIRS signals of insomnia patients with different degrees of insomnia in the stated age group, and a preset classification label corresponding to each set of effective feature values. The sample datasets from the various age groups are input into a general model for training to obtain the target model.
3. The evaluation method according to claim 1 or 2, characterized in that, The preprocessing of the first fNIRS signal to obtain the first signal feature value set includes: The first fNIRS signal is converted into first hemoglobin concentration data; The first set of effective feature values is obtained based on the first hemoglobin concentration data.
4. The evaluation method according to claim 3, characterized in that, The first hemoglobin concentration data includes first frontal lobe concentration data, first parietal lobe concentration data, first temporal lobe concentration data, and first occipital lobe concentration data. The step of obtaining the first effective feature value set based on the first hemoglobin concentration data includes: Extract the first frontal lobe feature value, first parietal lobe feature value, first temporal lobe feature value, and first occipital lobe feature value corresponding to the first frontal lobe concentration data, the first parietal lobe concentration data, the first temporal lobe concentration data, and the first occipital lobe concentration data, respectively; Determine the weight values corresponding to the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, and the first occipital lobe feature value, respectively; The first effective feature value set is formed by the weight values corresponding to the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, the first occipital lobe feature value, and the first frontal lobe feature value, the first parietal lobe feature value, the first temporal lobe feature value, and the first occipital lobe feature value.
5. The evaluation method according to claim 3, characterized in that, The step of converting the first fNIRS signal into first hemoglobin concentration data includes: Motion artifacts are removed during the acquisition of the first fNIRS signal, and the first fNIRS signal after removing the motion artifacts is converted into a first optical density signal. The first optical density signal is converted into first hemoglobin concentration data.
6. The evaluation method according to claim 1, characterized in that, The results of the insomnia treatment effect obtained based on the first classification label and the second classification label include: Determine the difference between the value corresponding to the second category label and the value corresponding to the first category label; If the difference is greater than or equal to a first preset value, the insomnia treatment is determined to be significantly effective. If the difference is less than a first preset value and greater than or equal to a second preset value, the insomnia treatment effect is determined to be generally effective. If the difference is less than the second preset value, the insomnia treatment is determined to be ineffective.
7. A device for evaluating the effectiveness of insomnia treatment, characterized in that, The device includes a processor, a connection interface, and a display device. The processor is connected to both the connection interface and the display device. The processor is used to acquire a first fNIRS signal and a second fNIRS signal through the connection interface, and to preprocess the first fNIRS signal and the second fNIRS signal to obtain a first set of effective feature values and a second set of effective feature values, respectively. The first fNIRS signal is the fNIRS signal of the insomnia patient before insomnia treatment, and the second fNIRS signal is the fNIRS signal of the insomnia patient after insomnia treatment. The processor is further configured to input the first effective feature value set and the second effective feature value set into the target model respectively, to obtain the first classification label corresponding to the first effective feature value set and the second classification label corresponding to the second feature value set respectively, and to obtain the insomnia treatment effect of the insomnia patient based on the first classification label and the second classification label; wherein, the target model is trained based on the signal feature value set corresponding to the fNIRS signals of multiple insomnia patients with different degrees of insomnia; The display device is used to display the results of the insomnia treatment.
8. The evaluation device according to claim 7, characterized in that, The processor is equipped with a data acquisition module, a data processing module, and a result judgment module. The processor executes the data acquisition module to acquire the first fNIRS signal and the second fNIRS signal; The processor runs the data processing module to obtain the first set of effective feature values and the second set of effective feature values based on the first fNIRS signal and the second fNIRS signal, respectively. The processor runs the result judgment module to obtain the first classification label and the second classification label based on the first effective feature value set, the second effective feature value set and the target model, and then obtains the insomnia treatment effect result.
9. The evaluation device according to claim 7, characterized in that, The display device includes a display interface, which includes a basic information display area and a result display area. The basic information display area includes a basic information sub-area for the insomnia patient, a sub-area for the acquisition status of the first fNIRS signal and the second fNIRS signal, and a first operation button. The result display area includes a result display sub-area and a second operation button. The processor is configured to acquire the first fNIRS signal and the second fNIRS signal when receiving the trigger signal of the first operation button, and display the insomnia treatment effect rating result obtained based on the first fNIRS signal and the second fNIRS signal through the result display sub-area; The processor is used to export a treatment effect result report upon receiving a trigger signal from the second operation button.
10. A system for evaluating the effectiveness of insomnia treatment, characterized in that, The device includes a signal acquisition device and the assessment equipment as described in claims 7-9, wherein the signal acquisition device is connected to the assessment equipment via a connection interface, and the signal acquisition device is used to acquire fNIRS signals from the cerebral cortex of insomnia patients.