Large-scale depression screening device and method based on body surface objective symptoms and medium

Abstract

The invention discloses a depression large-scale screening device and method based on body surface objective symptoms and a medium, and the method comprises the steps: carrying out the preliminary screening of a large-scale population based on a depression self-evaluation scale, and determining a potential depression high-risk population; for potential depression high-risk crowds, body surface information is obtained, depression somatic degree evaluation is conducted on the basis of the body surface information, a depression degree evaluation result is obtained, and the body surface information comprises pulse information, lingual surface image information, voice information and exhaled gas information; aiming at the crowd with the depression degree evaluation result being positive, a standardized interview tool is adopted for interview, and the depression screening result is determined. According to the method, the subjective self-evaluation form and the objective body surface information are effectively combined, the meticulous and high accessibility of diagnosis are considered, and the requirements of large-scale screening and clinical accurate analysis are met.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear magnetic resonance imaging, and particularly to a large-scale screening device, method and medium for depression based on objective body surface symptoms. Background Art

[0002] Depression is one of the most common mental illnesses globally, with its incidence rate increasing year by year and becoming a major public health problem affecting human health. Traditional depression analysis mainly relies on patients' self-reported symptoms, doctor interviews, and psychological scale assessments, such as the Beck Depression Inventory (BDI) and the Hamilton Depression Rating Scale (HAMD). However, these methods highly depend on the subjective judgment of professionals and have high requirements for medical resources, and are not suitable for large-scale population screening.

[0003] Specifically, the following drawbacks exist in the prior art:

[0004] 1. The need for large-scale depression screening is not considered: The prior art mainly focuses on single-sample classification methods, often requiring individual testing of each subject. This method ignores the needs of large-scale screening scenarios in algorithm design and processes, and is difficult to cope with the challenges of data processing and time costs in a large range of populations.

[0005] 2. The inclusion criteria for depression samples are not fully considered: Most technologies lack clear sample inclusion criteria when constructing training data, and there are significant differences in diagnostic tools, scales, and standards used in different studies, resulting in deficiencies in the generalization ability and applicability of the model in application scenarios and being difficult to meet clinical requirements.

[0006] 3. Lack of objective and standardized diagnosis of the degree of depressive symptoms: Existing artificial intelligence technologies focus more on the "yes / no" judgment of risk screening, do not provide a grading diagnosis function for the degree of depressive symptoms, and are also unable to distinguish other mental illnesses similar to depression (such as bipolar disorder, anxiety disorder, etc.). This not only limits the refined application of screening technologies in medical clinics but also cannot meet the personalized intervention needs of patients at different stages of depression.

[0007] 4. Lack of a comprehensive assessment system that combines subjective and objective aspects for depression: The prior art usually relies on a single-modal information source (such as text, voice, or physiological signals), and fails to comprehensively consider the combination of subjective reports and objective body surface data. Single-modal methods are easily restricted by individual differences, data acquisition environments, and devices, resulting in insufficient accuracy and stability of diagnostic results. A comprehensive assessment system that can combine subjective and objective data can more comprehensively reflect the psychological and physiological health status of subjects, but the prior art has not deeply explored this field.

[0008] Therefore, there are still defects in the prior art. Summary of the Invention

[0009] The technical problem to be solved by the present invention is to provide a large-scale depression screening device, method and medium based on objective body surface symptoms in view of the above-mentioned defects of the prior art. The technical solutions adopted by the present invention are as follows:

[0010] In a first aspect, an embodiment of the present invention further provides a large-scale depression screening device based on objective body surface symptoms, wherein the device includes:

[0011] A self-assessment preliminary screening module, configured to preliminarily screen a large-scale population based on a self-rating depression scale to determine potential high-risk depression populations;

[0012] A somatization quantification detection module, configured to obtain body surface information for potential high-risk depression populations and evaluate the degree of depression somatization based on the body surface information to obtain a depression degree evaluation result, wherein the body surface information includes pulse information, tongue surface image information, voice information, and exhaled gas information;

[0013] A standardized interview module, configured to conduct an interview with a person whose depression degree evaluation result is positive using a standardized interview tool to determine the depression screening result.

[0014] In a second aspect, the present invention provides a large-scale depression screening method based on objective body surface symptoms, wherein the method is applied to a large-scale depression screening device based on objective body surface symptoms, and the method includes:

[0015] Preliminarily screen a large-scale population based on a self-rating depression scale to determine potential high-risk depression populations;

[0016] For potential high-risk depression populations, obtain body surface information and evaluate the degree of depression somatization based on the body surface information to obtain a depression degree evaluation result, wherein the body surface information includes pulse information, tongue surface image information, voice information, and exhaled gas information;

[0017] For a person whose depression degree evaluation result is positive, conduct an interview using a standardized interview tool to determine the depression screening result.

[0018] In one implementation, preliminarily screening a large-scale population based on a self-rating depression scale to determine potential high-risk depression populations includes:

[0019] Controlling a large-scale population to complete the self-assessment questions in the self-rating depression scale within a preset time period to obtain a self-assessment score;

[0020] Based on the self-assessment score, determine potential high-risk depression populations.

[0021] In one implementation, for the population at high risk of potential depression, body surface information is obtained, including:

[0022] The pulse signal of the population at high risk of potential depression is collected by a non-invasive pulse wave sensor to obtain pulse information;

[0023] Based on a high-definition camera device, the tongue surface image of the population at high risk of potential depression is collected to obtain tongue surface image information;

[0024] By detecting the tone, speech rate, and voice intensity of the population at high risk of potential depression, voice information is obtained;

[0025] Based on a gas analyzer, the exhaled gas of the population at high risk of potential depression is detected to obtain exhaled gas information.

[0026] In one implementation, based on the body surface information, the degree of depression somatization is evaluated to obtain a depression degree evaluation result, including:

[0027] Perform multimodal fusion analysis on the body surface information, and calculate the distances of the body surface information to the clustering center of positive samples of depression and the clustering center of negative samples of depression;

[0028] Mark the body surface information closer to the clustering center of positive samples of depression as positive to obtain the depression degree evaluation result.

[0029] In one implementation, for the population with a positive depression degree evaluation result, a standardized interview tool is used for an interview to determine the depression screening result, including:

[0030] For the population with a positive depression degree evaluation result, a standardized interview tool is used for item-by-item interviews to obtain the evaluation result corresponding to each interview item;

[0031] Based on the evaluation result corresponding to each interview item, the depression screening result is determined.

[0032] In one implementation, based on the evaluation result corresponding to each interview item, the depression screening result is determined, including:

[0033] Based on the evaluation result corresponding to each interview item, individuals with positive depression are determined;

[0034] Perform a grading evaluation on individuals with positive depression to obtain the depression screening result, and archive the depression screening result.

[0035] In one implementation, the self-rating depression scale includes the CES-D self-rating form, the PHQ-9 self-rating form, or the BDI self-rating form; the interview tool includes the CIDI-C interview tool, the MINI interview tool, or the SCID interview tool.

[0036] Thirdly, an embodiment of the present invention further provides a terminal. The terminal includes a memory, a processor, and a large-scale screening program for depression based on objective body surface symptoms stored in the memory and executable on the processor. When the processor executes the large-scale screening program for depression based on objective body surface symptoms, the steps of the large-scale screening method for depression based on objective body surface symptoms in any one of the above solutions are implemented.

[0037] Fourthly, an embodiment of the present invention further provides a computer-readable storage medium. A large-scale screening program for depression based on objective body surface symptoms is stored on the computer-readable storage medium. When the large-scale screening program for depression based on objective body surface symptoms is executed by a processor, the steps of the large-scale screening method for depression based on objective body surface symptoms in any one of the above solutions are implemented.

[0038] Beneficial effects: Compared with the prior art, the present invention provides a large-scale screening method for depression based on objective body surface symptoms. First, the present invention preliminarily screens a large-scale population based on a self-rating depression scale to determine potential high-risk depression populations. Then, for the potential high-risk depression populations, body surface information is obtained, and the degree of depression somatization is evaluated based on the body surface information to obtain a depression degree evaluation result, where the body surface information includes pulse information, tongue surface image information, voice information, and exhaled gas information. Finally, for the populations with a positive depression degree evaluation result, a standardized interview tool is used for an interview to determine the depression screening result.

[0039] The technical effects of the present invention are mainly reflected in the following aspects:

[0040] 1. Improve the efficiency of large-scale preliminary screening: By using a self-rating scale for rapid evaluation in the initial stage, the number of subjects who need to further receive more complex diagnoses is significantly reduced. In the case of limited resources, potential high-risk depression populations can be preferentially identified, and more energy and medical resources can be concentrated on the populations that require more in-depth diagnosis and intervention, thereby overall improving the efficiency of large-scale preliminary screening.

[0041] 2. Solve the problem of the lack of objectivity in the existing methods for diagnosing depression: By using objective body surface information such as the facial expressions, speech intonations, and pulses of the subjects for multi-modal fusion analysis, and effectively combining subjective self-rating scales, objective body surface information, and structured interviews, it makes up for the excessive dependence of traditional diagnostic methods on the experience and subjective judgment of professional physicians. Through the collection of body surface information and algorithm analysis, more standardized and quantitative objective detection of the degree of depressive symptoms is carried out, which can reduce the errors caused by individual differences and subjective biases to a certain extent.

[0042] 3. Enhance the standardization of depression screening: Compared with the existing technologies that only rely on subjective scales or single physiological indicators, the present invention adopts quantifiable and repeatable screening means in both the objective evaluation stage and the standardized interview stage of the degree of somaticization of depression, achieving a multi-level unified specification from preliminary screening to refined diagnosis. While ensuring the scientific nature of the diagnosis, it also provides a standardized data basis for further clinical research, database construction, and the formulation of subsequent intervention plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flowchart of a preferred embodiment of the large-scale depression screening method based on objective body surface symptoms provided by an embodiment of the present invention.

[0044] Figure 2 It is an actual application example diagram of the large-scale depression screening method based on objective body surface symptoms provided by an embodiment of the present invention.

[0045] Figure 3 It is a schematic architecture diagram of the large-scale depression screening device based on objective body surface symptoms provided by an embodiment of the present invention.

[0046] Figure 4 It is a schematic block diagram of the principle of the terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To make the objectives, technical solutions, and effects of the present invention clearer and more definite, the following further elaborates on the present invention with reference to the accompanying drawings and by way of examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] The flowchart shown in the accompanying drawings is only an example illustration and does not necessarily include all the contents, operations, or steps, nor does it necessarily need to be executed in the described order. For example, some operations or steps can also be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0049] It should be understood that the terms used in the specification of the present invention are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0050] It should be understood that, for the convenience of clearly describing the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and effects. For example, the first control information and the second control information are only used to distinguish different control information, and do not limit their order.

[0051] Those skilled in the art can understand that the terms such as "first" and "second" do not limit the quantity and execution order, and the terms such as "first" and "second" do not necessarily mean different.

[0052] It should also be understood that the term " / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0053] Although the prior art has made certain progress in the field of depression screening, there are still many problems and limitations. There is an urgent need for a new technical method that can meet the needs of large-scale screening scenarios with higher efficiency, lower cost and higher accuracy, clarify the sample inclusion criteria, achieve hierarchical diagnosis of depression symptoms, and improve the comprehensiveness and scientificity of screening through a subjective and objective combined evaluation system.

[0054] This embodiment proposes a large-scale depression screening method based on objective symptoms on the body surface to solve the deficiencies of the prior art in aspects such as large-scale screening requirements, sample inclusion criteria, and objective diagnosis of the degree of depressive symptoms. The method aims to use an efficient self-rating scale for preliminary screening, and then perform fine objective diagnosis and analysis of depression on people with depressive tendencies, so as to quickly, effectively and low-cost complete large-scale depression screening.

[0055] When conducting large-scale screening, first, based on the Self-Rating Depression Scale, a large population is preliminarily screened to identify potential high-risk depression populations, so as to reduce the screening cost and shorten the screening time. Subsequently, for the potential high-risk depression populations, body surface information is obtained, and based on the body surface information, the degree of somaticization of depression is evaluated to obtain the depression degree evaluation result, where the body surface information includes pulse information, tongue surface image information, voice information, and exhaled gas information. Then, for the populations with a positive depression degree evaluation result, a standardized interview tool is used for an interview to determine the depression screening result. Compared with the prior art, the present invention significantly improves the applicability and accuracy of large-scale screening, reduces the consumption of screening resources, and provides important technical support for the early identification and grading diagnosis of depression.

[0056] The large-scale depression screening method based on objective body surface symptoms in this embodiment is applied to a terminal, and the terminal can be an intelligent terminal product such as a computer, a smart TV, or a mobile phone. As Figure 1 shown, the large-scale depression screening method based on objective body surface symptoms in this embodiment includes the following steps:

[0057] Step S100: Based on the Self-Rating Depression Scale, a large population is preliminarily screened to identify potential high-risk depression populations.

[0058] Specifically, the Self-Rating Depression Scale in this embodiment is the CES-D self-rating form, and the CES-D self-rating form is one of the internationally recognized depression screening tools. The CES-D self-rating form has the following advantages:

[0059] (1) High efficiency: The scale contains 20 concise and clear self-rating questions, and the completion time is usually 5 to 7 minutes, which is suitable for large-scale screening.

[0060] (2) Sensitivity and specificity: Multiple studies have shown that CES-D has high sensitivity and specificity in predicting depression and can effectively distinguish individuals without depression, mild depression, and moderate to severe depression.

[0061] (3) Wide applicability: CES-D has been widely applied in different cultural backgrounds and language environments and has good reliability and validity.

[0062] The CES-D self-rating form includes 20 self-test depression symptom questions, which can generally be completed in 5 to 7 minutes, and the main statistical indicator is the total score. Among the total score of 60 points, if the total score ≤ 15 points, there are no depression symptoms; if the total score is 16 - 19 points, there may be depression symptoms; if the total score ≥ 20 points, it is determined that there are depression symptoms.

[0063] Based on this, in this embodiment, it is possible to control a large number of people (i.e., subjects to be screened) to complete the self-assessment questions in the self-rating depression scale within a preset time period, and obtain a self-assessment score. Then, based on the self-assessment score, potential high-risk groups of depression are determined. Specifically, in combination with Figure 2 As shown, in this embodiment, people with a self-assessment score less than or equal to 15 points are marked as CES-D negative samples, and people with a self-assessment score greater than 15 points are marked as CES-D positive samples, that is, potential high-risk groups of depression are determined. CES-D positive samples need to enter the next step of the assessment of the degree of depression somatization. To meet the needs of large-scale screening, the CES-D self-rating form can be filled out online and automatically scored by the system, achieving high efficiency and low cost in the initial screening stage.

[0064] In this embodiment, the present invention uses a professional and highly versatile CES-D self-rating scale to conduct a preliminary screening of a large number of people, and preferentially screens out potential high-risk groups of depression (i.e., CES-D positive samples), thereby avoiding investing too much medical resources and time in unnecessary people. This initial screening process is characterized by simple operation, low cost, and less time consumption, and is suitable for wide application in communities, schools, enterprises, or other large-scale population scenarios.

[0065] Step S200: For potential high-risk groups of depression, obtain body surface information, and based on the body surface information, conduct an assessment of the degree of depression somatization to obtain an assessment result of the degree of depression, where the body surface information includes pulse information, tongue surface image information, voice information, and exhaled gas information.

[0066] In this embodiment, the detection of body surface information is realized based on the method of combining the four diagnostic methods of traditional Chinese medicine. As an important method of traditional Chinese medicine diagnosis, the combination of the four diagnostic methods of traditional Chinese medicine combines four diagnostic means: observation, auscultation and olfaction, interrogation, and palpation. By comprehensively observing and analyzing the body surface information of the subject, the somatization characteristics related to depression are evaluated. The body surface information in this embodiment includes pulse information, tongue surface image information, voice information, and exhaled gas information. Specifically, the following techniques are adopted in this embodiment to complete the quantitative assessment of the combination of the four diagnostic methods of traditional Chinese medicine:

[0067] (1) Pulse information collection: Collect the pulse signal of the subject through a non-invasive pulse wave sensor, analyze the pulse frequency, amplitude, and waveform characteristics, and judge whether there is an abnormal physiological state. Each time, it is necessary to collect the pulse wave changes of the subject within a period of time, which takes about 2 minutes.

[0068] (2) Tongue surface image information collection: Use a high-definition camera device to collect tongue surface images, and analyze the color, shape, and distribution of the tongue coating through algorithms to reveal abnormal digestive system or microcirculation disorders that may be caused by depression. Each collection requires taking a tongue image of the subject, which takes about 1 minute.

[0069] (3) Voice information analysis: Collect and perform spectral analysis on the voice signals of the subjects to identify changes in tone, speech rate, and voice intensity, and evaluate their emotional state and mental activity level. Each collection requires the subject to speak a passage according to the instructions, which takes about 2 minutes.

[0070] (4) Exhaled gas detection: Detect volatile organic compounds in exhaled breath through a dedicated gas analyzer to reveal metabolic characteristic changes that may be caused by stress or mood disorders. Each collection requires the subject to breathe through the instrument for a period of time, which takes about 1 minute.

[0071] In this embodiment, all subjects with CES-D positive samples (i.e., potential high-risk depression populations) and the same number of CES-D negative samples selected will be arranged in batches to a dedicated research site for testing. Each test includes a group of no more than 20 people to ensure the reasonable allocation of equipment resources and the efficiency of data collection. The subject needs to maintain a fasting state before the test (not eat for at least 2 hours) and avoid strenuous exercise. There is no specific order requirement for the collection of the above body surface information, and each subject only needs about 6 - 8 minutes of sampling time.

[0072] For the collected body surface information, algorithms such as data preprocessing, multimodal fusion, and machine learning are used to obtain the clustering centers of positive depression samples and negative depression samples respectively during the training stage. Then, for the collected test samples, calculate the distances of the sample to the clustering center of positive depression samples and the clustering center of negative depression samples, and select the sample label with a closer distance as the label of the test sample. Mark the test sample corresponding to the body surface information closer to the clustering center of positive depression samples as positive to obtain the depression degree evaluation result, and further precise depression screening in the next step is required.

[0073] In this embodiment, among the subjects with CES-D positive samples preliminarily screened, the depressive somatization characteristics of the subjects are evaluated by collecting and performing multimodal analysis on body surface information such as facial expressions, speech intonation, pulse frequency and amplitude. This step can combine the concept of the four diagnostic methods in traditional Chinese medicine (observation, auscultation and olfaction, interrogation, and palpation), calculate the distances between the subject and the positive and negative clustering centers of depression respectively, so as to quantitatively evaluate the objectification degree of depressive symptoms. This method can achieve a rapid and objective preliminary judgment of the severity of depression under non-invasive conditions by using big data and artificial intelligence algorithms.

[0074] In other implementation manners, based on pulse waves, tongue surface images, voice signals, and exhaled gases, other physiological or objective parameters can be added in this embodiment, such as facial expression recognition or galvanic skin response; or only some detection items can be selected as the means for somatization assessment according to site conditions or equipment accessibility. Moreover, during the multi-modal data fusion process, deep neural networks, random forests, or other machine learning algorithms can be selected; different degrees of trade-offs and optimizations can be made for the data acquisition frequency and algorithm real-time performance according to different research requirements or hardware performance.

[0075] Step S300: For the population with a positive depression degree assessment result, conduct an interview using a standardized interview tool to determine the depression screening result.

[0076] Based on the population with a positive depression degree assessment result determined in the above step S200, in this embodiment, a standardized interview tool is used to conduct item-by-item interviews to obtain the assessment result corresponding to each interview item. Then, based on the assessment result corresponding to each interview item, the depression screening result is determined. Specifically, the interview tool in this embodiment is CIDI-C (Composite International Diagnostic Interview Core Version), and CIDI-C is a structured diagnostic tool developed by the World Health Organization for diagnostic analysis of mental diseases including depression. CIDI-C has the following characteristics:

[0077] (1) Standardization: CIDI-C has a highly structured interview process, reducing subjective interference and ensuring the reliability and consistency of the results. All interviewers who execute CIDI-C need to receive professional training to ensure familiarity with the interview process and techniques and the ability to handle the emotional fluctuations of the subjects.

[0078] (2) Multi-dimensional assessment: CIDI-C not only assesses the symptoms of the subjects but also collects detailed information such as the onset course, severity, onset frequency, and age, comprehensively considering the symptoms from multiple dimensions to accurately diagnose the disease type and degree and distinguish diseases similar to depression such as anxiety disorder and bipolar disorder.

[0079] (3) Wide applicability: CIDI-C has been verified to be applicable to subjects of different ages, cultural backgrounds, and language environments. CIDI does not require an interview to be conducted by a doctor with clinical qualifications and can be conducted by ordinary people after training, reducing the medical pressure.

[0080] Based on this, in this embodiment, for the population with a positive depression degree evaluation result determined in the above step S200, the evaluation results corresponding to each interview item in the CIDI-C form for these people can be determined, so as to determine individuals with positive depression. The CIDI-C form in this embodiment has a scoring rule for further grading depression into mild, moderate, severe, etc. Therefore, individuals with positive depression can be graded and evaluated to obtain the depression screening result, and the depression screening result can be archived to assist in formulating subsequent clinical intervention or treatment strategies.

[0081] The IDI-C in this embodiment has high reliability and validity and can be implemented in clinical settings or institutions with professional mental health practitioners to distinguish different types of depressive disorders (such as unipolar depression, bipolar disorder) and other mental illnesses that may present similar symptoms, improving the accuracy and specialty value of diagnosis.

[0082] In practical applications, in this embodiment, the CES-D self-rating scale can be replaced with other self-rating scales such as the PHQ-9 self-rating scale or the BDI self-rating scale; the CIDI-C interview tool can be replaced with structured interview tools such as the MINI or SCID; and different scales and interview tools can be flexibly combined according to the local medical environment, project scale, and characteristics of the subjects.

[0083] In summary, in the large-scale depression screening method based on objective body surface symptoms proposed by the present invention, a three-level tree-like decision-making strategy of "self-rating preliminary screening - somatic quantification detection - standardized interview" is adopted, which not only meets the requirements for efficiency and cost in large-scale screening but also takes into account the refined needs of clinical diagnosis. In other implementation manners, in this embodiment, in addition to the three-level tree-like decision-making framework of "self-rating preliminary screening - somatic quantification detection - standardized interview", the number of levels can be increased or decreased, and flexible process adjustments can be made for different populations and different scenarios. Moreover, an objective data collection and analysis link based on the combination of the four traditional Chinese medicine diagnostic methods is inserted between the self-rating questionnaire (CES-D) and the structured interview (CIDI-C) in the present invention, so that the diagnostic basis includes not only the self-reported psychological status of the subjects but also objective data such as physiological signals, tongue and facial images, and exhalation characteristics and machine learning analysis. For the evaluation indexes of this embodiment, the algorithm or threshold can also be adjusted according to the research goal focusing on specificity or sensitivity, including the scoring threshold for distinguishing positive and negative in the CES-D preliminary screening, the criteria for judging positive or negative based on the combination of the four diagnostic methods, etc.

[0084] Based on the above embodiments, the present invention also provides a large-scale depression screening device based on objective body surface symptoms. The device is used to implement the steps of the large-scale depression screening method based on objective body surface symptoms in the above method embodiments, such as Figure 3As shown in the figure, the device of this embodiment includes: a self-evaluation preliminary screening module 10, a somatization quantitative detection module 20, and a standardized interview module 30. Specifically, the self-evaluation preliminary screening module 10 is used to preliminarily screen a large-scale population based on the Self-Rating Depression Scale to determine potential high-risk depression populations. The somatization quantitative detection module 20 is used to obtain body surface information for potential high-risk depression populations and evaluate the degree of depression somatization based on the body surface information to obtain a depression degree evaluation result, where the body surface information includes pulse information, tongue surface image information, voice information, and exhaled gas information. The standardized interview module 30 is used to conduct an interview with the population with a positive depression degree evaluation result using a standardized interview tool to determine the depression screening result.

[0085] In one implementation, the self-evaluation preliminary screening module 10 includes:

[0086] A self-evaluation score determination unit, configured to control a large-scale population to complete the self-evaluation questions in the Self-Rating Depression Scale within a preset time period to obtain a self-evaluation score;

[0087] A high-risk population determination unit, configured to determine potential high-risk depression populations based on the self-evaluation score.

[0088] In one implementation, the somatization quantitative detection module 20 includes:

[0089] A pulse information detection unit, configured to collect the pulse signals of potential high-risk depression populations through a non-invasive pulse wave sensor to obtain pulse information;

[0090] A tongue surface image information detection unit, configured to collect the tongue surface images of potential high-risk depression populations based on a high-definition camera device to obtain tongue surface image information;

[0091] A voice information detection unit, configured to detect the tone, speech rate, and sound intensity of potential high-risk depression populations to obtain voice information;

[0092] An exhaled gas detection unit, configured to detect the exhaled gas of potential high-risk depression populations based on a gas analyzer to obtain exhaled gas information.

[0093] In one implementation, the somatization quantitative detection module 20 further includes:

[0094] A distance calculation unit, configured to perform multimodal fusion analysis on the body surface information and calculate the distances of the body surface information to the clustering center of positive depression samples and the clustering center of negative depression samples;

[0095] An evaluation result determination unit, configured to label the body surface information closer to the clustering center of positive samples of depression as positive, so as to obtain the depression degree evaluation result.

[0096] In one implementation, the standardized interview module 30 includes:

[0097] An interview evaluation unit, configured to conduct item-by-item interviews on the population with a positive depression degree evaluation result by using a standardized interview tool, so as to obtain the evaluation result corresponding to each interview item;

[0098] A screening result determination unit, configured to determine the depression screening result based on the evaluation result corresponding to each interview item.

[0099] In one implementation, the screening result determination unit includes:

[0100] A positive individual determination unit, configured to determine the individuals with positive depression based on the evaluation result corresponding to each interview item;

[0101] A grading evaluation unit, configured to conduct a grading evaluation on the individuals with positive depression to obtain the depression screening result, and archive the depression screening result.

[0102] The working principles of the various modules in the large-scale depression screening device based on objective body surface symptoms in this embodiment are the same as those of the various steps in the above method embodiment, and will not be elaborated here.

[0103] The various modules in the above large-scale depression screening device based on objective body surface symptoms can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the terminal in the form of hardware or be independent of the processor, or can be stored in the memory in the terminal in the form of software, so that the processor can call and execute the operations corresponding to the above various modules.

[0104] Based on the above embodiments, the present invention further provides a terminal, and the principle block diagram of the terminal can be as Figure 4 shown. The terminal may include one or more processors 100 ( Figure 4 only one is shown in the figure), a memory 101, and a computer program 102 stored in the memory 101 and executable on one or more processors 100. For example, a large-scale depression screening program based on objective body surface symptoms. When one or more processors 100 execute the computer program 102, the various steps in the method embodiment of the large-scale depression screening method based on objective body surface symptoms can be implemented. Or, when one or more processors 100 execute the computer program 102, the functions of the various modules / units in the large-scale depression screening device embodiment based on objective body surface symptoms can be implemented, and no limitation is made here.

[0105] In one embodiment, the so-called processor 100 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0106] In one embodiment, the memory 101 may be an internal storage unit of the electronic device, such as the hard disk or memory of the electronic device. The memory 101 may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 101 may also include both an internal storage unit and an external storage device of the electronic device. The memory 101 is used to store computer programs and other programs and data required by the terminal. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0107] Those skilled in the art can understand that Figure 4 the principle block diagram shown in

[0108] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, operational database, or other medium used in the embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A large-scale screening device for depression based on objective symptoms on the surface of the body, characterized in that: The device comprises: The self-assessment initial screening module is used to conduct preliminary screening of a large population based on the depression self-assessment scale to identify potential high-risk groups for depression; A somatization quantitative detection module is used to obtain body surface information for people with a high risk of depression, and to evaluate the degree of depression somatization based on the body surface information to obtain a depression degree evaluation result, wherein the body surface information includes pulse information, tongue image information, voice information, and exhaled gas information; The standardized interview module is used to conduct interviews with people whose depression level assessment results are positive using standardized interview tools to determine depression screening results.

2. A large-scale screening method for depression based on objective symptoms on the surface of the body, characterized in that: The method is applied to the large-scale depression screening device based on objective symptoms on the body surface as claimed in claim 1, and the method comprises: Conduct preliminary screening of a large population based on the Self-Rating Depression Scale to identify potential high-risk groups for depression; For a potential high-risk population for depression, obtaining body surface information, and evaluating the degree of depression somatization based on the body surface information to obtain a depression degree evaluation result, wherein the body surface information includes pulse information, tongue image information, voice information, and exhaled gas information; For those with positive depression assessment results, a standardized interview tool is used to conduct an interview to determine the depression screening results.

3. The method for large-scale depression screening based on objective symptoms of body surface according to claim 2, characterized in that: A large-scale population screening was conducted based on the self-rating depression scale to identify potential high-risk groups for depression, including: Controlling a large group of people to complete the self-assessment questions in the depression self-assessment scale within a preset time period to obtain self-assessment scores; Based on the self-assessment scores, people with potential high risk of depression are identified.

4. The method for large-scale depression screening based on objective symptoms of body surface according to claim 2, characterized in that: For people at high risk of depression, obtain body surface information, including: The pulse information is obtained by collecting the pulse signals of people with a high risk of depression through non-invasive pulse wave sensors; Using high-definition camera equipment to collect tongue images of people at high risk of depression, and obtain tongue image information; By testing the tone, speech speed and intensity of people at high risk of depression, voice information can be obtained; The exhaled gas of people at high risk of potential depression is detected based on a gas analyzer to obtain exhaled gas information.

5. The method for large-scale depression screening based on objective symptoms of body surface according to claim 2, characterized in that: The somatization degree of depression is assessed based on the body surface information to obtain a depression degree assessment result, including: Performing multimodal fusion analysis on the body surface information, and calculating the distance of the body surface information to the cluster center of depression-positive samples and the distance to the cluster center of depression-negative samples; The body surface information closer to the cluster center of the depression-positive samples is marked as positive, and the depression degree assessment result is obtained.

6. The method for large-scale screening of depression based on objective symptoms on body surface according to claim 2, characterized in that: For those with positive depression assessment results, a standardized interview tool was used to conduct an interview to determine the depression screening results, including: For the people whose depression level is positive, a standardized interview tool is used to conduct interviews one by one to obtain the assessment results corresponding to each interview item; The depression screening results were determined based on the assessment results corresponding to each interview item.

7. The method for large-scale depression screening based on objective symptoms on body surface according to claim 6, characterized in that: Determine the depression screening results based on the assessment results corresponding to each interview item, including: Based on the assessment results corresponding to each interview item, individuals who were positive for depression were identified; Individuals who are positive for depression are graded and evaluated to obtain the depression screening results, which are then archived.

8. The method for large-scale depression screening based on objective symptoms of body surface according to claim 2, characterized in that: The depression self-rating scale includes the CES-D self-rating scale, the PHQ-9 self-rating scale or the BDI self-rating scale; the interview tool includes the CIDI-C interview tool, the MINI interview tool or the SCID interview tool.

9. A terminal, characterized in that: The terminal includes a memory, a processor, and a large-scale screening program for depression based on objective surface symptoms stored in the memory and executable on the processor. When the processor executes the large-scale screening program for depression based on objective surface symptoms, the steps of the large-scale screening method for depression based on objective surface symptoms as described in any one of claims 2-8 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a large-scale screening program for depression based on objective surface symptoms. When the large-scale screening program for depression based on objective surface symptoms is executed by the processor, the steps of the large-scale screening method for depression based on objective surface symptoms as described in any one of claims 2-8 are implemented.

Images