Related product and application of FT3 in depression risk assessment

Abstract

The invention discloses a related product of FT3 in depression risk assessment and application, and relates to the field of depression diagnosis. The marker provided by the invention comprises FT3 and shows a remarkable technical effect in the aspect of predicting depression, high-precision early recognition and risk prediction of depression are realized, a key window and an objective basis are provided for early active intervention and whole-course management of diseases, and the accuracy and reliability of screening and diagnosis are greatly improved. Meanwhile, the marker has excellent universality, is suitable for wide population screening, and lays a technical foundation for low-cost and high-efficiency large-scale depression screening. In conclusion, a brand new technical means is provided for effective diagnosis and risk early warning of depression, and the industrial application prospect is wide.

Description

Technical Field

[0001] This invention relates to the field of depression diagnosis, and more specifically, to FT3-related products and applications in depression risk assessment. Background Technology

[0002] Depression (clinically diagnosed as major depressive disorder, MDD) is a mental disorder characterized by persistent low mood, loss of interest, and impaired social functioning. It has become a major public health problem seriously affecting public mental health. In recent years, influenced by factors such as social pressure and changes in lifestyle, its incidence has shown a year-on-year upward trend, especially among adolescents and working adults. Depression not only causes core symptoms such as low mood, loss of interest, and decreased energy, but also severely impairs patients' social functioning, occupational abilities, and quality of life. Some severely ill patients also experience self-harming thoughts or behaviors, placing a heavy health and economic burden on individuals, families, and society.

[0003] Clinical practice shows that early identification and risk prediction of depression are key to improving its prognosis. If high-risk individuals can be identified before the onset of the disease (such as in the subclinical stage, i.e., when mild symptoms are present but do not meet the diagnostic criteria) or in the early stages of the disease, and timely interventions (such as psychological counseling and behavioral interventions) are carried out, the risk of developing depression can be reduced by more than 30%, and the course of the disease can be significantly shortened and relapses reduced. However, current risk prediction and early screening technologies for depression still have many limitations and cannot meet the clinical demand for "simple, efficient, and highly specific" prediction tools. These limitations are mainly reflected in the following aspects: (I) Assessment methods based on clinical scales have the defects of strong subjectivity and insufficient sensitivity: Currently, the commonly used clinical assessment tools for depression are mostly self-rating or other-rating scales, such as the Patient Health Questionnaire-9 (PHQ-9), the Self-Rating Depression Scale (SDS), and the Hamilton Depression Rating Scale (HAMD). Such methods rely on patients' subjective descriptions of their own emotions and behaviors, or doctors' judgments based on experience, and are easily affected by various factors. Patients may conceal their symptoms due to "stigma" or make inaccurate reports due to cognitive biases (such as a vague definition of "depressed mood"). On the other hand, for high-risk individuals in the subclinical stage, their symptoms have not yet reached the diagnostic threshold of the scale, and the scale assessment is difficult to identify effectively, causing a large number of potential patients to miss the opportunity for early intervention. (II) Imaging and neurophysiological testing technologies are difficult to popularize and apply: Some studies have attempted to observe changes in the structure and function of brain regions in patients with depression (such as reduced activity of the prefrontal cortex and hippocampal atrophy) through imaging means (such as functional magnetic resonance imaging fMRI and positron emission tomography PET), or monitor abnormal brain electrical activity through electroencephalography (EEG) to assist in risk prediction. However, such technologies have obvious shortcomings: the equipment is expensive and the operation is complicated. Professional technicians are required to interpret the results, so they cannot be used on a large scale in primary medical institutions or screening of the general population. The changes in brain structure and function of patients with early depression are usually subtle, and the sensitivity of imaging tests is insufficient, making it difficult to distinguish between "high-risk groups" and "healthy groups", thus limiting their clinical applicability. (III) The specificity and predictive efficacy of traditional biomarkers are insufficient: existing studies have found some potential depression-related biomarkers, but they generally have the problem of "poor specificity". They are unstable in the "warning window" before the onset of depression, and it is difficult to accurately predict the future risk of depression in healthy people through changes in their levels, resulting in low clinical translation value.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide FT3 related products and applications in depression risk assessment.

[0006] This invention is implemented as follows: In a first aspect, embodiments of the present invention provide the application of a reagent for detecting the content of a biomarker in a sample in the preparation of products for diagnosing or assisting in the diagnosis of depression; the biomarker includes free triiodothyronine.

[0007] Secondly, embodiments of the present invention provide a reagent or kit for the diagnosis or auxiliary diagnosis of depression, which includes a reagent for detecting the content of biomarkers in a sample; the biomarkers include free triiodothyronine.

[0008] Thirdly, embodiments of the present invention provide a method for constructing a diagnostic model for depression, which includes the following steps: The feature data and corresponding annotation results of the markers in the training samples are obtained to establish a dataset of the samples; the markers are those described in the foregoing embodiments. The model is trained using the dataset to obtain the depression diagnostic model.

[0009] Fourthly, embodiments of the present invention provide a method for assessing the risk of depression, wherein the risk assessment method is executed by a computer program and includes: Acquire feature data of biomarkers representing the subject samples; the biomarkers are those described in the foregoing embodiments. The depression risk assessment results for the subjects are obtained based on the characteristic data of the biomarkers in the subject samples. The biomarker includes free triiodothyronine.

[0010] Fifthly, embodiments of the present invention provide a device for diagnosing or assisting in the diagnosis of depression, comprising: The acquisition module is configured to acquire feature data of biomarkers representing subject samples; the biomarkers are those described in the foregoing embodiments. The diagnostic module is configured to obtain a diagnostic or auxiliary diagnostic result indicating depression in the subject based on characteristic data of markers in the subject sample.

[0011] In a sixth aspect, embodiments of the present invention provide an electronic device, the electronic device including a processor and a memory; the memory is used to store a program, which, when executed by the processor, causes the processor to implement the construction method as described in the foregoing embodiments or the depression risk assessment method as described in the foregoing embodiments.

[0012] In a seventh aspect, embodiments of the present invention provide a computer-readable medium storing a computer program that, when executed by a processor, implements the construction method as described in the foregoing embodiments or the depression risk assessment method as described in the foregoing embodiments.

[0013] Eighthly, embodiments of the present invention provide an electronic system for diagnosing or assisting in the diagnosis of depression, the electronic system comprising: The acquisition module is configured to acquire feature data of biomarkers in subject samples; The analysis module is configured to obtain an indication of a diagnosis or auxiliary diagnosis of depression for the subject based on characteristic data of biomarkers in the subject sample; The biomarker includes free triiodothyronine.

[0014] The present invention has the following beneficial effects: The novel biomarker provided in this application includes FT3, which demonstrates significant technical effectiveness in predicting depression. It achieves high-precision and high-specificity early identification and risk prediction of depression, providing a crucial window and objective evidence for early proactive intervention and comprehensive management of the disease, greatly improving the accuracy and reliability of screening and diagnosis. Simultaneously, this biomarker possesses excellent universality, applicable to screening a wide range of populations, laying the technical foundation for low-cost, high-efficiency large-scale depression screening. In summary, this application provides a novel technical means for the effective diagnosis and risk warning of depression, with broad prospects for industrial application. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic flowchart illustrating a method for constructing a depression diagnostic model provided in an embodiment of this application. Figure 2 This is a schematic flowchart of a method for diagnosing or assisting in the diagnosis of depression provided in an embodiment of this application. Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of this application; Figure 4 The ROC curves for FT3 in this embodiment of the application distinguish between the healthy control group and the depressive disorder group. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Where specific conditions are not specified in the embodiments, conventional conditions or conditions recommended by the manufacturer shall apply. Reagents or instruments whose manufacturers are not specified are all conventional products that can be purchased commercially.

[0018] Screening for high-performance predictive biomarkers for depression presents technical challenges, primarily due to the following factors: (1) High heterogeneity of the disease: Depression is not a single disease but a highly heterogeneous syndrome resulting from a combination of multiple symptoms and different etiologies. This heterogeneity leads to a diversity of biomarkers, making the search for a universal biomarker that can cover the entire population akin to finding a needle in a haystack. (2) Complex intertwined etiologies: The onset of depression is the result of the combined effects of multiple factors, including genetics, environment, psychology, and neuroendocrine factors, making it difficult to find ideal biomarkers that can comprehensively reflect multiple pathway disorders. (3) High risk of false positives and false negatives: Due to significant individual differences (such as age, gender, comorbidities, and medication use), the performance of candidate biomarkers may decline sharply when crossing different subgroups of the population, easily resulting in false positives or false negatives and predictive failures. Therefore, there has been a lack of stable, reliable, and universally applicable predictive biomarkers for depression in this field.

[0019] The biomarkers or biomarker combinations provided in the embodiments of the present invention are obtained through extensive creative screening. By including patients with depression and control groups of different ages, genders and disease stages (mild to moderate and severe depression), they not only have high predictive performance, but also exhibit excellent generalization ability. They can maintain stable predictive effects in groups of different ages, genders and disease states, which is something that many existing biomarkers cannot achieve.

[0020] Definition of noun "T3" stands for triiodothyronine, a key hormone secreted by the thyroid gland. The thyroid gland produces and releases at least two hormones: total thyroxine (TT4) and total triiodothyronine (TT3). They play crucial roles in the human endocrine system, controlling metabolism, protein synthesis, carbohydrate and fat metabolism, neural development, normal bone growth and maturation, and cardiovascular and renal function. During circulation, approximately 99.7% of TT3 binds to thyroid-binding globulin, with only 0.3% existing in a free form, referred to as "FT3" in this article—free triiodothyronine. Only these FT3 molecules, which can enter cells through specific membrane transport mechanisms, possess biological activity.

[0021] In this article, "Cortisol" refers to a glucocorticoid secreted by the adrenal pericortex and is an important biomarker of the adrenal glands. Corticotropin-releasing hormone (CRH) and adrenocorticotropic hormone (ACTH) stimulate cortisol secretion through feedback control. Cortisol can be detected in serum and urine. The main part of the cortisol circulation is bound to plasma corticosteroid-binding globulin (CBG or transcortisol) and albumin, preventing the hormone from penetrating the cell membrane of target cells. Only 3%-5% of cortisol in plasma circulates in the form of unbound free cortisol, i.e., the biologically active form. The detection methods mentioned in this application all target the free form of cortisol in peripheral blood.

[0022] The "ADPN" mentioned in this article refers to adiponectin, a major adipose-derived factor secreted by adipose tissue. It exists in circulation as a high-molecular-weight hexameric dimer, trimer, or protein complex, possessing anti-inflammatory and insulin-sensitizing properties, and playing a beneficial role in glucose metabolism. Decreased ADPN levels are associated with obesity, insulin resistance (IR), metabolic syndrome (MS), type 2 diabetes mellitus (T2DM), hypertension, and dyslipidemia. ADPN has anti-inflammatory effects on macrophages, endothelial cells, cardiomyocytes, and fibroblasts, which is one reason why ADPN shows protective effects on various organs, including the heart, blood vessels, and lungs. The detection methods mentioned in this application all target ADPN protein complexes circulating in peripheral blood. The definitions of the terms "mild depressive episode," "moderate depressive episode," and "severe depressive episode" can be based on the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) or the International Classification of Diseases (ICD-11), mainly distinguished by the number of symptoms, severity, and impact on social functioning.

[0023] "Mild depressive episode" is defined as "symptoms meeting the criteria and social functioning being slightly impaired." The patient can still maintain basic daily activities. The number of symptoms must meet at least 5 depressive symptoms, and must include one of the two core symptoms: depressed mood or loss of interest / pleasure. Daily work, study, and interpersonal communication are only slightly affected. The patient can complete most tasks independently with only a small amount of extra effort. There are no psychotic symptoms (such as hallucinations or delusions). The patient has a clear understanding of their own state and the subjective distress is relatively mild.

[0024] "Moderate depressive episodes" fall between mild and severe, characterized by "more symptoms and significantly impaired social functioning." Patients need to actively adjust to cope with daily life. Symptom count: 6-7 depressive symptoms are present, with at least one core symptom (depressed mood / loss of interest), accompanied by additional symptoms such as sleep disturbances, decreased energy, and self-blame. Social functioning: Significantly decreased work efficiency, marked difficulty in interpersonal communication (e.g., social avoidance), and needing minimal assistance from others to complete household chores and studies. Key characteristics: No psychotic symptoms, but a strong sense of subjective distress; some patients may experience brief feelings of helplessness or negative thoughts.

[0025] "Major depressive episode" is the most severe level, characterized by "comprehensive symptoms and severe loss of social functioning," sometimes accompanied by psychotic symptoms, requiring emergency intervention. Symptom count: Meeting eight or more depressive symptoms, with extreme manifestations of core symptoms (e.g., persistent low mood throughout the day, complete loss of interest), and may also include sudden weight loss / gain, severe sleep disturbances (e.g., insomnia or hypersomnia). Social functioning: Almost unable to perform any daily activities (e.g., unable to get out of bed, refuse to eat, refuse to communicate), requiring full care from others; in severe cases, self-harm may occur. Key features: May be accompanied by psychotic symptoms (e.g., depression-related hallucinations, such as hearing voices blaming oneself; or delusions, such as firmly believing oneself to be "guilty" or "worthless"); some patients may experience stupor (limb rigidity, lack of spontaneous behavior).

[0026] The term "risk assessment" refers to the process of evaluating the risk or probability of a subject currently having depression based on characteristic data of biomarkers or combinations of biomarkers. This includes, but is not limited to, assessing the risk of developing depression in subjects who have or have not yet developed related symptoms or signs; or determining whether a subject currently has depression, whether or not they have yet developed related symptoms or signs.

[0027] The term "preset threshold" refers to a parameter used to compare a marker or combination of markers in a subject's sample with a preset threshold when diagnosing disease risk, and outputs the subject's disease risk based on the comparison result.

[0028] Specifically, a sample refers to biological material obtained from the subject's body; including but not limited to peripheral blood samples, such as serum and / or plasma, or samples containing serum and / or plasma that are acceptable for this assessment method.

[0029] Specifically, the subjects included the entire population, which encompassed individuals with different health statuses (healthy, sub-healthy, and diseased), different demographic characteristics (old and young, male and female), and different behavioral habits (e.g., smoking / non-smoking, exercising / not exercising).

[0030] Specifically, the preset thresholds include, but are not limited to, positive judgment values, prediction probability thresholds, and dependent variable thresholds, which are critical values ​​that can be used to divide results and clarify judgment boundaries. The setting of these thresholds should be based on the performance requirements of the target detection scenario (such as sensitivity, specificity, accuracy, etc.) and determined through clinical data validation, statistical model analysis (such as ROC curve analysis, Youden index calculation, etc.) or industry standard calibration, so as to ensure their effectiveness and reliability in risk assessment methods or prediction models.

[0031] The term "Z-score standardization" refers to the process of subtracting the mean (μ) of each biomarker in the training set from its original concentration data, and then dividing by its standard deviation (σ). The resulting standardized data has a mean of 0 and a standard deviation of 1, making it suitable for eliminating differences in dimensions and numerical ranges between different biomarkers.

[0032] The term "Min-Max Normalization" refers to the process of subtracting the minimum value (min) of each marker from its original concentration data in the training set, and then dividing by the range (max-min) of that marker in the training set. This method linearly scales the concentration data of all markers to a fixed range, typically between [0,1].

[0033] The term "robust scaling" is a standardization method that is robust to outliers in data. Clinical sample data (such as blood parameters) may contain extreme values, and Z-score and Min-Max methods are susceptible to these extreme values. Robust scaling uses statistics less affected by outliers: the median and the interquartile range (IQR, the difference between the 75th and 25th quartiles). It is achieved by subtracting the median from the original data and then dividing by the IQR, and the result is less susceptible to interference from extreme outliers.

[0034] The term "logarithmic transformation" is a transformation method suitable for handling skewed distribution data. Biomarker concentration data (such as hormones) often exhibit an asymmetric skewed distribution (e.g., data concentrated in low-value regions with a long tail extending to high-value regions). Logarithmic transformations (e.g., taking the natural logarithm log(x), or using log(x+1) to avoid zero values) can convert this skewed distribution to data that is closer to a symmetric normal distribution, which helps improve the performance and stability of certain diagnostic models (such as logistic regression models).

[0035] On one hand, embodiments of the present invention provide the application of a reagent for detecting the content of biomarkers in a sample in the preparation of products for diagnosing or assisting in the diagnosis of depression; the biomarkers include free triiodothyronine (FT3).

[0036] In an optional implementation, the marker is selected from any combination shown in (a) to (c): (a) FT3 and Cortisol; (b) FT3 and ADPN; (c) FT3, Cortisol and ADPN.

[0037] In an optional implementation, the product for diagnosing or assisting in the diagnosis of depression can be used in the general population.

[0038] In an optional implementation, the entire population, including both men and women, is covered.

[0039] In an optional implementation, the age range of the entire population covers 12 to 65 years old.

[0040] In an optional implementation, the "whole population" refers to all people except those in the perinatal period.

[0041] In an optional implementation, the depression covers mild depressive episodes, moderate depressive episodes, and severe depressive episodes.

[0042] In an optional implementation, the major depressive episode includes: a major depressive episode without psychosis and / or a major depressive episode with psychosis.

[0043] In an optional implementation, the product includes: reagents, reagent kits, electronic systems, or devices.

[0044] In an optional implementation, an in vitro diagnostic biomarker for female depressive disorders (a biomarker with a certain concentration or proportion) or peripheral blood or serum containing the biomarker may be used alone as an auxiliary diagnostic tool for female depressive disorders or as a calibrator or quality control product for diagnostic products.

[0045] In an optional implementation, the method for diagnosing or assisting in the diagnosis of depression is the same as the depression risk assessment method described in any subsequent embodiment or implementation.

[0046] In an optional implementation, FT3 is used as an auxiliary diagnostic criterion for depressive disorders in subjects: a FT3 level ≤ (3.212~3.27) pg / ml in peripheral blood collected at the time of the subject's visit indicates a significantly increased risk of the subject being diagnosed with a depressive disorder.

[0047] On the other hand, embodiments of the present invention provide a reagent or kit for diagnosing or assisting in the diagnosis of depression, which includes: a reagent for detecting the content of biomarkers as described in any of the foregoing embodiments or implementation methods.

[0048] In an optional embodiment, the reagent or kit further includes instructions for use in diagnosing or assisting in the diagnosis of depressive disorders.

[0049] On the other hand, please refer to Figure 1 This invention illustrates a method for constructing (or training) a depression diagnostic model, which includes the following steps: S100, acquire feature data of markers representing the training samples and corresponding annotation results, and establish a dataset of samples; the markers are the markers described in any of the foregoing embodiments or implementations.

[0050] In an optional implementation, the labeling results include: a label representing the subject's risk of developing depression.

[0051] In an alternative implementation, the risk of illness includes whether or not one suffers from depression.

[0052] In an optional implementation, the label can be a character or a string. The content of the diagnostic result corresponds to the content of the labeling result.

[0053] In an optional implementation, the feature data representing the markers in the training samples is: the detection result of the marker content or the value of the detection result after standardization.

[0054] In an optional implementation, the standardization process includes at least one of Z-score normalization, Min-Max normalization, robust scaling, and logarithmic transformation.

[0055] S110, Use the dataset to train the model and obtain the depression diagnostic model.

[0056] The embodiments of the present invention do not impose any special restrictions on the diagnostic model, and can select diagnostic models commonly used in the art for predicting the risk of disease or the progression of disease.

[0057] In an optional implementation, the diagnostic model is selected from any one of the following: logistic regression model, random forest model, XGboost model, support vector machine model (SVM), decision tree model (DT), K-nearest neighbor model (KNN), Naive Bayes model (NB), LightGBM model, and CatBoost model.

[0058] In an optional implementation, the type and number of training samples are conventionally selectable by those skilled in the art, and the total number of training samples or the number of training samples of various categories (e.g., healthy population group, depression patient group) can independently be ≥10, 50, 100, 200, 300, 400 and 500 cases or take any range between any two of them.

[0059] On the other hand, please refer to Figure 2 The invention also provides a method for assessing the risk of depression (or a method for diagnosing or assisting in the diagnosis of depression), which is executed by a computer program and includes the following steps: S200, acquire feature data of biomarkers representing the subject sample; the biomarkers are any of the biomarkers described in the foregoing embodiments or implementations; S210, obtain the depression risk assessment result of the subject based on the characteristic data of the biomarkers in the subject sample.

[0060] In an optional implementation, the depression covers: mild depressive episodes, moderate depressive episodes, and severe depressive episodes; In an optional implementation, the major depressive episode includes: a major depressive episode without psychosis and / or a major depressive episode with psychosis.

[0061] In an optional implementation, the characteristic data of the marker is the detection result of the marker content or the value of the detection result after standardization.

[0062] In an optional implementation, the step of obtaining the depression risk assessment result of the subject based on the characteristic data of the biomarkers in the subject sample includes: comparing the detection result of the content of the biomarkers in the subject sample with a first preset threshold, and obtaining the depression risk assessment result of the subject based on the comparison result.

[0063] In an optional implementation, the step of obtaining the depression risk assessment result of the subject based on the characteristic data of the biomarkers in the subject sample includes: obtaining the standardized value of the detection result of the biomarker content in the subject sample and calculating the result by a preset model, comparing the calculated result with a second preset threshold, and obtaining the depression risk assessment result of the subject based on the comparison result.

[0064] In an optional implementation, the first preset threshold or the second preset threshold is obtained based on the principle of maximizing the Yoden index.

[0065] Specifically, in this paper, the first preset threshold is the positive judgment value, which refers to the critical single concentration value of the biomarker determined based on clinical sensitivity and specificity requirements when using ROC curves or models for data fitting. In one specific implementation, the detected concentration value of the biomarker is directly compared with the positive judgment value, and the diagnosis or auxiliary diagnosis result of depression for the subject is output based on the comparison result. For example, when the biomarker is free triiodothyronine, the detected concentration value of free triiodothyronine is directly compared with the positive judgment value, and the diagnosis or auxiliary diagnosis result of depression for the subject is output based on the comparison result. In another example, when the biomarker is selected from the following combinations: (a) free triiodothyronine and cortisol; (b) free triiodothyronine and ADPN; (c) free triiodothyronine, cortisol, and ADPN, a corresponding first preset threshold is set for each biomarker in the combination, and after comparison, the subject's depression risk assessment result is output based on the comparison result.

[0066] Specifically, the second preset threshold in this paper can be a prediction probability threshold, which refers to the prediction probability threshold (P-value) of the model determined based on clinical sensitivity and specificity requirements when the diagnostic model is a logistic regression model, a random forest model, or other models. In one specific implementation, the biomarker feature data is input into the model to calculate the corresponding biomarker feature data, and the P-value is compared with the model's prediction probability threshold. Based on the comparison result, the subject's depression risk assessment result is output. The second preset threshold in this article can also be a dependent variable threshold, which refers to the dependent variable threshold of the model determined based on clinical sensitivity and specificity requirements when the diagnostic model is a functional formula. In one specific implementation, the biomarker feature data is substituted into the functional formula to calculate the dependent variable, and the dependent variable is compared with the dependent variable threshold of the functional formula. Based on the comparison result, the subject's depression risk assessment result is output.

[0067] Logistic regression models can be either functional formulas or a combination of functional formulas and p-value calculation formulas.

[0068] In an optional implementation, the step of obtaining a depression risk assessment result indicative of the subject based on the characteristic data of the biomarkers in the subject sample includes: inputting the characteristic data of the biomarkers representing the subject sample into a diagnostic model constructed by the construction method described in any of the foregoing embodiments or implementations to obtain a depression risk assessment result indicative of the subject.

[0069] On the other hand, embodiments of the present invention also provide a device for diagnosing or assisting in the diagnosis of depression, comprising: The acquisition module is configured to acquire feature data of biomarkers representing subject samples; the biomarkers are any of the biomarkers described in the foregoing embodiments or implementations. The diagnostic module is configured to obtain a diagnostic or auxiliary diagnostic result indicating depression in the subject based on characteristic data of markers in the subject sample.

[0070] In an optional implementation, the characteristic data of the marker is the detection result of the marker content or the value of the detection result after standardization.

[0071] In an optional implementation, the step of obtaining the result indicating the diagnosis or auxiliary diagnosis of depression of the subject based on the characteristic data of the biomarkers in the subject sample is the same as the step of obtaining the result indicating the risk assessment of depression of the subject based on the characteristic data of the biomarkers in the subject sample described in any of the foregoing embodiments or implementations, and will not be repeated here.

[0072] The modules described in this embodiment of the invention can be stored in memory or embedded in the operating system (OS) of the electronic device provided in this application in the form of software or firmware, and can be executed by the processor in the electronic device. Meanwhile, the data, program code, etc., required to execute the above modules can be stored in memory.

[0073] On the other hand, embodiments of the present invention also provide an electronic device, the electronic device including a processor and a memory; the memory is used to store a program, which, when executed by the processor, causes the processor to implement the construction method as described in any of the foregoing embodiments or implementations, or the depression risk assessment method as described in any of the foregoing embodiments or implementations.

[0074] Please refer to Figure 3 This is a structural block diagram of an electronic device 100 provided in an embodiment of this application. The electronic device 100 may include a memory 110, a processor 120, a bus 130, and a communication interface 140. The memory 110, processor 120, and communication interface 140 are electrically connected to each other to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more buses 130 or signal lines.

[0075] The memory 110 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0076] The processor 120 can be an integrated circuit chip with signal processing capabilities. The processor 120 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0077] Understandable. Figure 3 The structure shown is for illustrative purposes only; the electronic device 100 may also include components that are more advanced than those shown. Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown. Figure 3 The components shown can be implemented using hardware, software, or a combination thereof. In practical applications, the electronic device 100 can be a server, cloud platform, mobile phone, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), handheld computer, netbook, personal digital assistant (PDA), wearable electronic device, virtual reality device, etc. Therefore, this application embodiment does not limit the type of electronic device 100.

[0078] On the other hand, embodiments of the present invention also provide a computer-readable medium storing a computer program, which, when executed by a processor, implements the construction method or the depression risk assessment method as described in any of the foregoing embodiments or implementations.

[0079] In some implementations, the computer-readable medium can be a general-purpose storage medium, such as a removable disk or hard disk.

[0080] Furthermore, embodiments of the present invention also provide an electronic system for diagnosing or assisting in the diagnosis of depression, the electronic system comprising: The acquisition module is configured to acquire feature data of biomarkers in subject samples; The analysis module is configured to obtain an indication of a diagnosis or auxiliary diagnosis of depression for the subject based on characteristic data of biomarkers in the subject sample; The biomarker includes free triiodothyronine.

[0081] In an optional implementation, the marker is any of the markers described in the foregoing embodiments or implementations.

[0082] In an optional implementation, the characteristic data of the marker is the detection result of the marker content or the value of the detection result after standardization.

[0083] In an optional implementation, the step of obtaining a diagnosis or auxiliary diagnosis of depression for the subject based on the characteristic data of the markers in the subject sample is the same as described in any of the foregoing embodiments or implementations, and will not be repeated here.

[0084] In some embodiments, this invention also provides a treatment method for depression, which includes the following steps: The subject is diagnosed or diagnosed with depression using the methods for diagnosing or assisting in the diagnosis of female depression as described in any of the foregoing embodiments or implementation methods, and the results of the diagnosis or assisting in the diagnosis of depression are obtained. Based on the diagnosis or auxiliary diagnostic results of depression, high-risk patients will receive appropriate treatment.

[0085] In optional implementations, the treatment methods include any one or more of cognitive behavioral therapy (CBT), interpersonal therapy (IPT), psychodynamic therapy, mindfulness therapy (such as mindfulness-based stress reduction (MBSR) and mindfulness-based cognitive therapy (MBCT), pharmacology, and physical therapy.

[0086] In an optional embodiment, the drug treatment includes any one or more of the following: selective serotonin reuptake inhibitors (SSRIs), serotonin and norepinephrine reuptake inhibitors (SNRIs), norepinephrine and specific serotonergic antidepressants (NaSSAs), and other classes of drugs.

[0087] In optional implementations, SSRIs include any one or more of fluoxetine (Prozac), paroxetine, sertraline (Zoloft), fluvoxamine, citalopram, and escitalopram. SNRIs include venlafaxine and duloxetine. NaSSAs include mirtazapine. Other classes of drugs include bupropion and agomelatine.

[0088] The features and performance of the present invention will be further described in detail below with reference to embodiments.

[0089] Sample type used in the examples: The sample refers to a human peripheral blood sample, including plasma or serum.

[0090] The sampling method used in this example is as follows: 5 ml of fasting venous blood was collected from patients with depressive disorders and healthy individuals. The collection method was the well-known negative pressure blood collection technique. The serum was separated by centrifugation at 3000 rpm for 10 min and stored at -80℃ for testing.

[0091] Detection method of markers: The kits used in the examples for detecting FT3 (catalog number 1302533005M), Cortisol (catalog number 130270002M), and ADPN (catalog number 130505009S) were obtained from Shenzhen New Industries Biomedical Engineering Co., Ltd., and the detection was carried out in accordance with the instructions of the kits.

[0092] Example 1: Discovery of biomarkers for the auxiliary diagnosis of depressive disorders 1.1 Research Sample Information: Sample source and population information: Peripheral blood samples from patients with depressive disorders were collected continuously from Hospital A (samples collected continuously within a period of time), including serum samples from 45 patients with depressive disorders and 32 healthy individuals undergoing physical examinations. Perinatal patients were excluded. The subjects were divided into a depression group and a healthy group. The age, gender, and disease distribution of the two groups are shown in Table 1.

[0093] Table 1 Sample Information

[0094] 1.2 Experimental Methods The concentrations of potential biomarkers in samples from the depression group and the healthy group were detected using the detection kit and method provided in the examples. The detection was performed according to the instructions for the aforementioned kit, and the differences in potential biomarker levels between the depression group and the healthy group were compared.

[0095] The results of the differential analysis of potential biomarkers between the depression group and the healthy group are shown in Table 2.

[0096] Table 2. Results of the analysis of differences in potential biomarkers between the depression group and the healthy group.

[0097] As shown in Table 2, among the 17 potential biomarkers, the levels of metabolic marker 25-OH VD, endocrine markers FT3 and Cortisol, and inflammatory markers TNFα, IL-6, and APDN showed significant differences between the healthy group and the depressed group.

[0098] Example 2: The role of FT3 in the auxiliary diagnosis of depressive disorders in a small sample population. 2.1 Research Sample Information: Sample source and population information: Peripheral blood samples from patients with depressive disorders were collected continuously from Hospital A (samples collected continuously within a period of time), including serum samples from 44 patients with depressive disorders and 36 healthy individuals undergoing physical examinations. Perinatal patients were excluded. The subjects were divided into a depression group and a healthy group. The age, gender, and disease distribution of the two groups are shown in Table 3.

[0099] Table 3 Sample Information

[0100] 2.2 Experimental Methods The concentration of FT3 in samples from a depression group and a healthy group was detected using an FT3 assay kit and method. The assay was performed according to the kit's instructions. Differences in FT3 levels between the depression group and the healthy group were compared, and ROC curve analysis was used to evaluate the performance of FT3 in distinguishing between patients with depressive disorders and healthy individuals.

[0101] 2.3 Results of ROC curve analysis of FT3 in diagnosing depressive disorders like Figure 4 As shown, the ROC curve AUC of FT3 distinguishing between the healthy group and the depressed group was 0.782, the optimal threshold was 3.212 pg / ml, the sensitivity was 0.864, and the specificity was 0.639, demonstrating that FT3 has high diagnostic performance as an auxiliary diagnostic biomarker for depressive disorders.

[0102] Example 3: The role of biomarkers and biomarker combinations in the auxiliary diagnosis of depressive disorders 3.1 Sample Information, Experimental Methods, and Data Analysis Methods 3.1.1 Research Sample Information: Information on patients with depression admitted to multiple hospitals was collected, and the proportions of patients with different disease stages were statistically analyzed, as shown in Table 4.

[0103] Table 4. Sample distribution at different disease stages

[0104] Based on the epidemiological findings regarding the gender and age distribution of the population, as well as the proportions of different disease courses, serum samples were continuously collected from patients with depressive disorders aged 12-65 years and healthy individuals from Hospital B, excluding the perinatal population. The samples included 285 patients with depressive disorders and 217 healthy individuals undergoing physical examinations. The subjects were divided into a depression group and a healthy group. The age distribution of the two groups is shown in Table 5, the gender distribution is shown in Table 6, and the disease course distribution is shown in Table 7.

[0105] Table 5. Age distribution of the sample

[0106] Table 6. Gender distribution of the sample

[0107] The healthy group and the depressed group covered people of different genders and ages. Statistically, there were no significant differences in age and gender distribution between the healthy group and the depressed group according to the chi-square test.

[0108] Table 7. Distribution of disease conditions in the sample

[0109] The depression group covered patients with different degrees of depression, including mild to moderate depressive episodes and severe depressive episodes. Among them, patients with severe depressive episodes included those without psychotic symptoms and those with psychotic symptoms. The proportion of consecutive sampling did not show significant differences from the statistical results of multiple hospitals, and the sample collection was terminated.

[0110] 3.1.2 Data Analysis Methods Statistical analysis was performed using R-4.5.1 software. Normally distributed continuous data were analyzed using... ± The comparison between the two groups was indicated by the t-test; non-normally distributed continuous data were expressed as M (interquartiles), and the comparison between the two groups was indicated by the Mann-Whitney U test; count data / categorical data were expressed by the chi-square test; p < 0.05 indicated statistical significance; the area under the receiver operating characteristic curve (ROC curve) was used to assess the discrimination of the predictive marker, and the sensitivity and specificity at the best positive judgment value were calculated.

[0111] 3.2 The role of FT3 and biomarker combination in constructing a logistic regression model for the diagnosis of depressive disorders 3.2.1 Differences in the level of biomarkers between groups The concentration of FT3 marker in serum was detected using the aforementioned detection kit and method. The detection was performed according to the kit instructions, and the differences in FT3 between the healthy group (217 cases) and the depressed group (285 cases) were statistically analyzed. The results are shown in Table 8.

[0112] Table 8 Test Results

[0113] The results showed that FT3 levels differed significantly between the healthy group and the depressed group.

[0114] 3.2.2 Construction of FT3 and Biomarker Combination Diagnostic Model A logistic regression prognostic model was constructed using various biomarkers (FT3, Cortisol, APDN). The healthy and depressed groups were randomly divided into training and test sets in a 3:1 ratio. The training set was used to build the model, and the test set was used to test the model's performance. The logistic regression model's prediction probability was calculated using the formula: P = 1 / (1 + e^(-1 / 2)). -Y (e is the natural constant, Y is the linear formula, and P is the predicted probability). Based on the model's predicted probability, the AUC is calculated using ROC curve analysis, and the optimal threshold is selected as the predicted probability standard. The model's sensitivity and specificity are then calculated to evaluate the model's ability to distinguish between the healthy group and the depressed group.

[0115] Table 9 Results

[0116] As shown in Table 9, in the sample provided in step 3.1, there is a significant difference in FT3 between depressed patients and healthy individuals, which is basically consistent with the conclusion of the sample provided in step 2.1. Furthermore, FT3 has an AUC > 0.75 for auxiliary diagnosis of depression in the general population, demonstrating good diagnostic performance. The AUC for the combined detection scheme of FT3 with any one or more of Cortisol or ADPN provided in this embodiment is > 0.75, which can be used for the diagnosis of depression in patients.

[0117] Since the training and validation sets were obtained through random sampling, both of which cover patients of different ages, genders, and disease stages, this demonstrates that the provided joint testing scheme has strong generalization ability and can provide diagnostic basis for patients with depressive disorders of different ages and disease stages.

[0118] The results from this test set show that FT3 has an AUC of 0.81 for the auxiliary diagnosis of depression in the general population, demonstrating good diagnostic performance. Based on this diagnostic model, an AUC of FT3 ≤ 3.27 pg / ml is considered an increased risk of depressive disorder. The combined FT3 and Cortisol or ADPN test both showed AUCs greater than 0.81, demonstrating superior diagnostic performance for depression in the general population compared to FT3 alone. FT3 and Cortisol are the optimal combined test, but the AUC improvement compared to single tests is not significant. This may be because the AUC is already above 0.8, making a substantial increase difficult. It may also be because FT3 and Cortisol ultimately affect the same neurotransmitter system, exhibiting a physiological connection, thus the combined effect is not significant. However, since some patients with depression may only exhibit HPT axis abnormalities (decreased FT3) while others only exhibit HPA axis abnormalities (increased Cortisol), the combined test can provide some complementarity. The combined FT3+Cortisol+ADPN assay achieved an AUC of 0.84, which is superior to FT3 alone and the combined FT3 and Cortisol or ADPN assays.

[0119] Example 4: Validation of Diagnostic Performance Based on Random Forest Based on the enrolled samples of Example 3, a random forest model was constructed for FT3, Cortisol, and ADPN single markers or marker combinations: (1) Dataset partitioning: The healthy group and the depressed group were randomly divided into training set and test set in a ratio of 3:1. The training set was used for model training, and the test set was used to evaluate the performance of the model. (2) The hyperparameters for tuning the random forest model include mtry (number of features randomly selected when splitting nodes), ntree (number of decision trees), and nodesize (minimum number of samples required for leaf node splitting). The best hyperparameters were searched using the grid search method, and AUC was used as the tuning index. The hyperparameter combination with the highest average AUC of 10-fold cross-validation was selected. (3) Model evaluation: Based on the best hyperparameter combination, the model parameters were trained using the training set data, and the prediction probability of the training set was obtained. ROC curve analysis was used to determine the threshold for prediction classification. The random forest model obtained from the training was used to predict the test set data, obtain the prediction probability and prediction classification, calculate AUC, sensitivity, and specificity, and evaluate the model's ability to distinguish between the healthy group and the depressed group.

[0120] The results are shown in Table 10.

[0121] Table 10 Results

[0122] The test set results showed that FT3 had an AUC of over 0.7 for the auxiliary diagnosis of depression in the general population, demonstrating good diagnostic performance. The diagnostic performance of the two-item combination of FT3 and Cortisol or ADPN was better than that of the FT3-only combination. The three-item combination of FT3, Cortisol and ADPN also had a good diagnostic performance with an AUC of 0.83, consistent with the conclusions of logistic regression.

[0123] Example 5: Diagnostic performance verification based on support vector machine Based on the enrolled samples of Example 3, support vector machine models were constructed for single or combined markers of VD, FT3, TNF-α, Cortisol, IL-6, and ADPN: (1) Dataset partitioning and preprocessing: The healthy group and the depressed group were randomly divided into training set and test set in a ratio of 3:1. The training set was used for model training, and the test set was used to evaluate the performance of the model. The YeoJohnson method was used to normalize the quantitative variables. The Z-score method was used to standardize the quantitative variables. (2) The kernel function of the support vector machine model was selected as the radial basis kernel. The hyperparameters were tuned, including cost and rbf_sigma (the range of influence of a single training sample in the feature space). The grid search method was used to search for the best hyperparameters. AUC was used as the tuning index, and the combination of hyperparameters with the highest average AUC of 10-fold cross-validation was selected. (3) Model evaluation: Based on the best combination of hyperparameters, the training set data was used to train the model parameters and obtain the prediction probability of the training set. ROC curve analysis was used to determine the threshold for prediction classification. The trained support vector machine model is used to predict test set data, obtain prediction probability and prediction classification, calculate AUC, sensitivity and specificity, and evaluate the model's ability to distinguish between healthy and depressed groups.

[0124] The results are shown in Table 11.

[0125] Table 11 Results

[0126] The test set results showed that FT3 had an AUC of over 0.8 for the auxiliary diagnosis of depression in the general population, demonstrating good diagnostic performance. The AUC of FT3 combined with Cortisol or ADPN, as well as the AUC of FT3+Cortisol+ADPN combined with Cortisol, reached 0.82 or 0.84, also demonstrating good diagnostic performance, consistent with the conclusions of logistic regression.

[0127] Experiments show that, among various mainstream machine learning models, the biomarkers or biomarker combinations of the present invention exhibit stable and significant diagnostic performance for depression. Their diagnostic efficacy does not depend on the selection of a specific model and has broad applicability and reliability.

[0128] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. Use of a detection reagent for a marker content in a sample in the manufacture of a product for diagnosing or aiding in the diagnosis of depression, the marker comprising free triiodothyronine.

2. Use according to claim 1, characterized in that, the marker is selected from any one of combinations (a)-(c): (a) free triiodothyronine and cortisol; (b) free triiodothyronine and ADPN; (c) free triiodothyronine, cortisol and ADPN.

3. Use according to claim 1 or 2, characterized in that, the depression covers mild depressive episode, moderate depressive episode and severe depressive episode; optionally, the severe depressive episode comprises: severe depressive episode without psychotic features and / or severe depressive episode with psychotic features; optionally, the product comprises: a reagent, a kit, an electronic system or a device.

4. A reagent or a kit for diagnosis or aid diagnosis of depression, characterized by, which comprises a detection reagent for a marker content in a sample; the marker comprising free triiodothyronine; optionally, the reagent or kit further comprises an instruction, the instruction recording an instruction indicating that the marker content corresponding to the detection reagent is used for the diagnosis or aid in the diagnosis of depressive disorder; optionally, the marker is selected from any one of combinations (a)-(c): (a) free triiodothyronine and cortisol; (b) free triiodothyronine and ADPN; (c) free triiodothyronine, cortisol and ADPN.

5. A method for constructing a diagnostic model for depression, characterized by, which comprises the following steps: obtaining feature data representing a marker in a training sample and corresponding annotation results, establishing a data set of the sample; the marker is the marker described in claim 1 or 2; training a model using the data set to obtain the depression diagnosis model; optionally, the diagnosis model is selected from any one of the following: logistic regression model, random forest model, XGboost model, support vector machine model, decision tree model, K nearest neighbor model, naive Bayes model, LightGBM model and CatBoost model.

6. The construction method of claim 5, wherein, the result of the feature data representing the marker in the training sample is: a detection result of the marker content or a result processed by standardization from the detection result; optionally, the standardization processing comprises at least one of Z-score standardization, Min-Max normalization, robust scaling and logarithmic transformation; optionally, the annotation result comprises a label representing the risk of depression of the subject.

7. A method of assessing the risk of depression, characterized by, which comprises: obtaining feature data representing a marker in a training sample and corresponding annotation results, establishing a data set of the sample; the marker is the marker described in claim 1 or 2; obtaining a risk assessment result of depression of the subject according to the feature data of the marker in the subject sample; wherein the marker comprises free triiodothyronine; optionally, the marker is selected from any one of combinations (a)-(c): (a) free triiodothyronine and cortisol; (b) free triiodothyronine and ADPN; (c) free triiodothyronine, cortisol and ADPN; optionally, the feature data of the marker is a detection result of the marker content or a value processed by standardization from the detection result; Optionally, the step of obtaining the depression risk assessment result of the subject according to the characteristic data of the marker in the sample of the subject comprises: comparing the detection result of the content of the marker in the sample of the subject with a first preset threshold, and obtaining the depression risk assessment result of the subject according to the comparison result. Optionally, the step of obtaining the depression risk assessment result of the subject according to the characteristic data of the marker in the sample of the subject comprises: obtaining the result of the calculation of the standardized value of the detection result of the content of the marker in the sample of the subject by a preset model, comparing the calculated result with a second preset threshold, and obtaining the depression risk assessment result of the subject according to the comparison result. Optionally, the step of obtaining the depression risk assessment result of the subject according to the characteristic data of the marker in the sample of the subject comprises: inputting the characteristic data representing the marker in the sample of the subject into the diagnostic model constructed by the construction method of claim 5 or 6, and obtaining the depression risk assessment result of the subject. Optionally, the depression covers mild depression, moderate depression and severe depression. Optionally, the severe depression comprises: severe depression without psychosis and / or severe depression with psychosis.

8. A depression diagnosing or aiding diagnosing apparatus characterized by comprising: It comprises: The acquisition module is configured to acquire characteristic data representing a marker in a sample of a subject; the marker is the marker in claim 1 or 2; The diagnostic module is configured to obtain a depression diagnosis or auxiliary diagnosis result of the subject according to the characteristic data of the marker in the sample of the subject; Optionally, the characteristic data of the marker is a detection result of the content of the marker or a value standardized from the detection result. Optionally, the step of obtaining the depression diagnosis or auxiliary diagnosis result of the subject according to the characteristic data of the marker in the sample of the subject comprises: comparing the detection result of the content of the marker in the sample of the subject with a first preset threshold, and obtaining the depression diagnosis or auxiliary diagnosis result of the subject according to the comparison result. Optionally, the step of obtaining the depression diagnosis or auxiliary diagnosis result of the subject according to the characteristic data of the marker in the sample of the subject comprises: obtaining the result of the calculation of the standardized value of the detection result of the content of the marker in the sample of the subject by a preset model, comparing the calculated result with a second preset threshold, and obtaining the depression diagnosis or auxiliary diagnosis result of the subject according to the comparison result. Optionally, the step of obtaining the depression diagnosis or auxiliary diagnosis result of the subject according to the characteristic data of the marker in the sample of the subject comprises: inputting the characteristic data representing the marker in the sample of the subject into the diagnostic model constructed by the construction method of claim 5 or 6, and obtaining the depression diagnosis or auxiliary diagnosis result of the subject.

9. An electronic device, comprising: The electronic device comprises a processor and a memory; the memory is configured to store a program, and when the program is executed by the processor, the processor implements the construction method of claim 5 or 6 or the depression risk assessment method of claim 7.

10. A computer readable medium characterized by The computer readable medium stores a computer program, and when the computer program is executed by the processor, the construction method of claim 5 or 6 or the depression risk assessment method of claim 7 is implemented.

11. An electronic system for the diagnosis or aided diagnosis of depression, characterized in that it comprises: The electronic system comprises: an acquisition module configured to acquire feature data of a marker in a sample of a subject; an analysis module configured to obtain a result indicative of a diagnosis or auxiliary diagnosis of depression of the subject according to the feature data of the marker in the sample of the subject; wherein the marker comprises free triiodothyronine; Optionally, the marker is selected from any one of combinations (a)-(c): (a) free triiodothyronine and cortisol; (b) free triiodothyronine and ADPN; (c) free triiodothyronine, cortisol and ADPN; Optionally, the feature data of the marker is a detection result of the content of the marker or a value standardized from the detection result; Optionally, the step of obtaining a result indicative of a diagnosis or auxiliary diagnosis of depression of the subject according to the feature data of the marker in the sample of the subject comprises: comparing the detection result of the content of the marker in the sample of the subject with a first preset threshold, and obtaining a result indicative of a diagnosis or auxiliary diagnosis of depression of the subject according to the comparison result; Optionally, the step of obtaining a result indicative of a diagnosis or auxiliary diagnosis of depression of the subject according to the feature data of the marker in the sample of the subject comprises: obtaining a result calculated by a preset model from a value standardized from the detection result of the content of the marker in the sample of the subject, comparing the calculated result with a second preset threshold, and obtaining a result indicative of a diagnosis or auxiliary diagnosis of depression of the subject according to the comparison result; Optionally, the step of obtaining a result indicative of a diagnosis or auxiliary diagnosis of depression of the subject according to the feature data of the marker in the sample of the subject comprises: inputting the feature data of the marker in the sample of the subject into the diagnostic model constructed by the construction method of claim 5 or 6, and obtaining a result indicative of a diagnosis or auxiliary diagnosis of depression of the subject.

Images