Related product and application of FT3 in female depression diagnosis risk assessment

Abstract

The invention discloses a related product of FT3 in female depression diagnosis 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 female depression. The marker accurately accords with physiological and pathological characteristics of female depression, realizes high-precision early recognition and risk prediction of female depression, and greatly improves the accuracy and reliability of female depression screening and diagnosis. Meanwhile, the marker covers female groups at the age of more than 18 years old, and a technical foundation is laid for realizing low-cost and high-efficiency large-scale depression screening of adult female groups. In conclusion, a brand new technical means is provided for effective diagnosis and risk early warning of female depression, the technical blank in the field of female depression exclusive markers is filled, and the industrial application prospect is wide.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of depression diagnosis, in particular, to FT3 related products and applications in the risk assessment of female depression diagnosis. BACKGROUND

[0002] Depression (clinically diagnosed as major depressive disorder, MDD) is a mental disorder characterized by persistent low mood, decreased interest and impaired social function. About 300 million people worldwide are affected by it, which has become a major public health problem that seriously affects public mental health. The World Health Organization predicts that by 2030, depression will become the leading global disease burden. In recent years, affected by factors such as social pressure and changes in life rhythm, the incidence rate has been increasing year by year, especially among teenagers and working people. Depression not only leads to core symptoms such as low mood, loss of interest, and decreased energy, but also seriously damages social function, professional ability, and quality of life. Some severe patients are accompanied by self-injury ideas or behaviors, which brings heavy health and economic burden to individuals, families and society.

[0003] Studies have shown that if high-risk individuals can be identified at the subclinical stage or early stage of the disease and intervention can be implemented, the risk of disease can be reduced by more than 30%. However, the existing screening and prediction techniques have obvious limitations: subjective scales are easily affected by patient stigma and cognitive bias, and are not sensitive to early symptoms; imaging examinations are costly and complex to operate, and are difficult to popularize; traditional biomarkers are not specific enough and are unstable in predicting the risk of disease. It is worth noting that the prevalence of female depression is about twice that of men, and its occurrence and development are closely related to estrogen level fluctuations, menstrual cycle, pregnancy, and postpartum physiological stages, and has a unique pathological mechanism. However, the existing detection methods do not take into account this gender difference, resulting in a significant lack of early identification efficiency for the female population.

[0004] In view of this, the present application is proposed. SUMMARY

[0005] The purpose of the present application is to provide FT3 related products and applications in the risk assessment of female depression diagnosis.

[0006] The present application is implemented as follows: In a first aspect, the embodiments of the present application provide an application of a detection reagent for the content of a marker in a sample in the preparation of a product for diagnosing or assisting in the diagnosis of female depression; the marker includes FT3 (free triiodothyronine).

[0007] In a second aspect, an embodiment of the present application provides a reagent or kit for diagnosing or assisting in diagnosing female depression, comprising: a detection reagent for detecting the content of the marker as described in the foregoing embodiments.

[0008] In a third aspect, an embodiment of the present application provides a method for constructing a female depression diagnosis model, comprising the following steps: obtaining feature data representing the markers in the training samples and corresponding labeling results, to establish a data set of female samples; the markers are the markers described in the foregoing embodiments; training a model using the data set, to construct the female depression diagnosis model.

[0009] In a fourth aspect, an embodiment of the present application provides a method for evaluating the risk of female depression, comprising: obtaining feature data representing the markers in the subject samples; the markers are the markers described in the foregoing embodiments; obtaining an evaluation result of the risk of depression of the subject according to the feature data of the markers in the subject samples.

[0010] In a fifth aspect, an embodiment of the present application provides a device for diagnosing or assisting in diagnosing female depression, comprising: an obtaining module configured to obtain feature data representing the markers in the subject samples; the markers are the markers described in the foregoing embodiments; a diagnosis module configured to obtain a diagnosis or assistance diagnosis result of depression of the subject according to the feature data of the markers in the subject samples.

[0011] In a sixth aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory; the memory is used to store a program, when the program is executed by the processor, the processor implements the construction method as described in the foregoing embodiments or the method for evaluating the risk of female depression as described in the foregoing embodiments.

[0012] In a seventh aspect, an embodiment of the present application provides a computer readable medium, the computer readable medium stores a computer program, when the computer program is executed by a processor, the construction method as described in the foregoing embodiments or the method for evaluating the risk of female depression as described in the foregoing embodiments are implemented.

[0013] In an eighth aspect, an embodiment of the present application provides an electronic system for diagnosing or assisting in diagnosing female depression, comprising: an obtaining module configured to obtain feature data of markers in a subject sample; an analysis module configured to obtain a diagnosis or assistance diagnosis result of depression of the subject according to the feature data of the markers. wherein the marker comprises at least FT3.

[0014] The present application has the following beneficial effects: The marker provided by the present application comprises FT3, which exhibits significant technical effects in predicting female depression. The marker precisely matches the physiological and pathological characteristics of female depression, achieving high-precision early identification and risk prediction of female depression, providing a key window and objective basis for early active intervention and whole-process management of female depression patients, and greatly improving the accuracy and reliability of female depression screening and diagnosis. At the same time, the marker covers female groups over 18 years old, laying a technical foundation for realizing low-cost and high-efficiency large-scale depression screening of adult female groups. In summary, the present application provides a new technical means for effective diagnosis and risk warning of female depression, fills the technical gap in the field of female depression-specific markers, and has a wide industrial application prospect. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0016] Figure 1 A flowchart of a method for constructing a depression diagnosis model provided by the embodiments of the present application; Figure 2 A flowchart of a depression diagnosis or auxiliary diagnosis method provided by the embodiments of the present application; Figure 3 A structural block diagram of an electronic device provided by the embodiments of the present application; Figure 4 The difference between FT3 in the depression group and the healthy group in the embodiments of the present application; Figure 5 The ROC curve of FT3 in the embodiments of the present application for distinguishing the healthy control group from the depression disorder group. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be described clearly and completely. If the specific conditions are not specified in the embodiments, the conventional conditions or the conditions recommended by the manufacturer are used. If the reagents or instruments used are not specified by the manufacturer, they are all conventional products that can be purchased on the market.

[0018] There are significant technical challenges in screening high-performance female depression biomarkers, mainly due to the following aspects: (1) High heterogeneity of disease manifestation: Depression in women often shows specific symptom patterns related to hormonal cycles, psychosocial factors, etc. This gender-related heterogeneity makes the potential biomarkers more diverse, increasing the difficulty of finding a unified and universal marker. (2) Complex etiology interweaving: The onset of female depression is closely related to genetic susceptibility, sex hormone fluctuations, environmental influences, and psychosocial stress, etc. Ideal markers that can fully reflect these interactions are extremely rare. (3) High risk of false positives and false negatives: Due to significant physiological changes in women at different life stages (such as adolescence, menopause), often accompanied by specific comorbidities and medication differences, the predictive performance of candidate markers is prone to fluctuation when crossing different age groups or physiological stages, leading to an increased risk of misjudgment. Therefore, developing stable and reliable depression biomarkers for female populations has been an important challenge in the field.

[0019] The marker (or marker combination) provided by the embodiments of the present application is obtained through in-depth and creative screening work, which shows significantly better performance than existing markers (or marker combinations) in predicting female depression. And it shows good generalization ability for women of different ages, which is difficult for many existing markers to achieve.

[0020] Nomenclature "T3" is 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 a key role in the body's endocrine system and control the body's metabolism, protein synthesis, carbohydrate and fat metabolism, neural development, normal growth and maturation of the skeleton, and cardiovascular and renal function. About 99.7% of TT3 is bound to thyroid-binding globulin during circulation, and only 0.3% is in free form, i.e. "FT3", free triiodothyronine, only these FT3 can enter cells through specific membrane transport mechanisms to have biological activity.

[0021] Cortisol, also known as Cortisone, is a glucocorticoid hormone secreted by the outer cortex of the adrenal gland, and is an important biomarker of the adrenal gland. Cortisol secretion is stimulated by feedback control of corticotropin-releasing hormone (CRH) and adrenocorticotropic hormone (ACTH). Cortisol can be detected in serum and urine. The main part of the cortisol cycle is bound to plasma corticosteroid-binding globulin (CBG or transcortin) and albumin, preventing the hormone from penetrating the cell membrane of target cells. Only 3-5% of cortisol in the plasma circulates in the form of unbound free cortisol, i.e. the biologically active form. The detection referred to in this application is for peripheral blood free form Cortisol.

[0022] ADPN, also known as Adiponectin, is a major adipokine secreted by adipose tissue, which exists in the form of a dimer, a trimer or a protein complex of a high molecular weight hexamer in circulation, has anti-inflammatory and insulin-sensitizing properties, and plays a beneficial role in glucose metabolism. A decrease in ADPN levels is associated with obesity, insulin resistance (IR), metabolic syndrome (MS), type 2 diabetes mellitus (T2DM), hypertension and dyslipidemia. ADPN has an anti-inflammatory effect on macrophages, endothelial cells, cardiomyocytes and fibroblasts, which is one of the reasons why ADPN shows protective effects on various organs including the heart, blood vessels and lungs. The detection referred to in this application is for ADPN protein complex circulating in peripheral blood.

[0023] TNF-α, also known as Tumor Necrosis Factor-alpha, is an inflammatory cytokine that plays a key role in apoptosis, cell survival, inflammation and immunity. TNF-α is mainly produced by monocytes / macrophages and T cells, and is also expressed in neutrophils, NK cells, dendritic cells, endothelial cells, keratinocytes, astrocytes and osteoblasts. TNF-α is first synthesized as a 26kDa transmembrane protein, which is cleaved by metalloproteinase TACE to form a soluble mature protein with a molecular weight of about 17kDa. TNF-α is a key mediator of acute and chronic systemic inflammatory responses, not only inducing its own secretion, but also stimulating the production of other inflammatory cytokines and chemokines. The detection referred to in this application is for peripheral blood soluble mature TNF-α.

[0024] The "IL-6" interleukin herein is a widely functional and pleiotropic cytokine, which belongs to a kind of interleukins. IL-6 is expressed by a single gene, and the cDNA translation product is a polypeptide chain of 212 amino acids, which can be cut to form a mature protein of 184 amino acids, with a molecular weight of about 22-27 kDa. It is produced by fibroblasts, monocyte / macrophages, T lymphocytes, B lymphocytes, epithelial cells, keratinocytes, and various tumor cells. Interleukin-1, tumor necrosis factor-a, platelet-derived factor, viral infection, etc. can induce normal cells to produce IL-6. Interleukin 6 can stimulate the proliferation, differentiation and function improvement of cells involved in immune response. IL-6 not only has physiological activity on B cells, but also has physiological effects on T cells, hematopoietic stem cells, liver cells and brain cells. IL-6 is rapidly produced during acute inflammatory response in the process of internal and external injury, stress response, infection and other conditions. The detection mentioned in the present application is for peripheral blood mature IL-6.

[0025] The term "female" covers individuals of different health status (healthy, sub-healthy and ill), different demographic characteristics, different behavioral habits (e.g. smoking / non-smoking, exercising / non-exercising).

[0026] The definitions of "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), with the main difference being the number of symptoms, severity and degree of impact on social function.

[0027] "Mild depressive episode" is "symptom threshold and slight impact on social function", the patient can still maintain daily activities, the number of symptoms: at least 5 depressive symptoms, and must include one of the two core symptoms of emotional low or loss of interest / pleasure; daily work, study, interpersonal communication is only slightly affected, the patient can independently complete most of the affairs, only a small amount of additional effort is needed; no psychotic symptoms (such as hallucinations, delusions), the patient has a clear understanding of his own state, and the subjective pain is light.

[0028] "Moderate depressive episode" is between mild and severe, which is "more symptoms and significant impairment of social function", the patient needs to actively adjust to cope with daily life. The number of symptoms: 6-7 depressive symptoms are met, one of the core symptoms (emotional low / loss of interest) is required, accompanied by more additional symptoms such as sleep disorders, decreased energy, self-blame, etc. Social function: work efficiency is significantly decreased, interpersonal communication is significantly difficult (such as avoiding social interaction), and completing household chores, learning and other affairs requires a small amount of assistance from others. Key features: no psychotic symptoms, but the subjective pain is strong, some patients may have a short period of helplessness or negative thoughts.

[0029] “Severe depressive episode” is the most severe grade, which is “symptoms are comprehensive and social function is severely impaired”, even accompanied by psychotic symptoms, requiring emergency intervention. The number of symptoms: meet 8 or more depressive symptoms, the core symptoms show extreme (such as all-day persistent low mood, complete loss of any interest), and may also appear sudden weight loss / weight gain, severe sleep disorders (such as all-night sleeplessness or sleepiness), suicidal thoughts, etc. Social function: almost unable to complete any daily activities (such as unable to get up, not eating, not communicating with others), requiring full-time care by others, and may even appear self-injury or suicidal behavior in severe cases. Key features: may be accompanied by psychotic symptoms (such as depression-related hallucinations, such as hearing voices criticizing oneself; or delusions, such as firmly believing that oneself is “guilty” “worthless”), and some patients may appear catatonic state (limb stiffness, no active behavior).

[0030] The term “risk assessment” refers to the process of assessing the risk or probability of a subject currently suffering from depression based on the characteristic data of a biomarker or a combination of biomarkers. It includes but is not limited to assessing the risk of developing depression for subjects who have or have not developed relevant symptoms or signs; or determining whether a subject currently has depression for subjects who have or have not developed relevant symptoms or signs.

[0031] The term “preset threshold” refers to the comparison of the parameters of a marker or a combination of markers in a subject's sample with the preset threshold when diagnosing the risk of disease, and the risk of disease of the subject is output according to the comparison result.

[0032] Specifically, the preset threshold includes but is not limited to a positive judgment value, a prediction probability threshold, a dependent variable threshold, and other critical values that can be used to divide the results and determine the boundaries. The threshold is set based on the performance requirements (such as sensitivity, specificity, accuracy, etc.) of the target detection scene, and is determined through clinical data verification, statistical model analysis (such as ROC curve analysis, Youden index calculation, etc.) or industry standard calibration, etc. to ensure its determination effectiveness and reliability in risk assessment methods or prediction models.

[0033] The term “Z-score Standardization” refers to the process of subtracting the mean (μ) of each marker in the training set data from the original concentration data of the marker, and then dividing by its standard deviation (σ). The data generated by this method (i.e. the data after standardization) has a mean of 0 and a standard deviation of 1, which is suitable for eliminating the differences in dimensions and numerical ranges between different markers.

[0034] The term "Min-Max Normalization" refers to a method that scales all the marker concentration data linearly to a fixed range, usually between [0, 1], by subtracting the minimum value (min) of each marker in the training set from its original concentration data, and then dividing by the full range (max-min) of the marker in the training set.

[0035] The term "Robust Scaling" is a normalization method that is robust to outliers in the data. Clinical sample data (e.g. blood markers) can have extreme values, and Z-score and Min-Max methods are susceptible to these extreme values. Robust scaling uses statistical quantities that are less affected by outliers: the median and the interquartile range (IQR, the difference between the 75th percentile and the 25th percentile), to perform the scaling. It achieves this by subtracting the median from the original data, and then dividing by the IQR, which is less affected by extreme outliers.

[0036] The term "Logarithmic Transformation" is a transformation method that is suitable for handling skewed distribution data. Biomarker concentration data (e.g. hormones) often have skewed distribution (e.g. data is concentrated in the low value region, with a long tail trailing to the high value region). Logarithmic transformation (e.g. taking natural logarithm log(x), or using log(x+1) to avoid 0 values) can convert this skewed distribution to data that is closer to symmetric normal distribution, which helps to improve the performance and stability of certain diagnostic models (e.g. logistic regression model).

[0037] In one aspect, the present application provides a use of a detection reagent for a marker in a sample in the preparation of a product for diagnosing or aiding in the diagnosis of depression in a female subject; the marker comprises free triiodothyronine.

[0038] In some embodiments, the marker further comprises cortisol and / or a cytokine. The cytokine comprises at least one of ADPN, IL-6 and TNFα.

[0039] In some embodiments, the marker is selected from the combination of any one of (a)~(i): (a) FT3 and cortisol; (b) FT3 and ADPN; (c) FT3 and IL6; (d) FT3, cortisol and ADPN; (e) FT3, cortisol and IL6; (f) FT3, cortisol and TNFα; (g) FT3, cortisol, ADPN and IL6; (h) FT3, cortisol, IL6 and TNFα; (i) FT3, cortisol, ADPN, IL-6 and TNFα.

[0040] In some embodiments, the female is aged greater than 18 years.

[0041] In some embodiments, the female is aged between 18 and 65 years.

[0042] In some embodiments, the female is a non-peripartum female.

[0043] In some embodiments, the depressive disorder covers mild depressive episode, moderate depressive episode and severe depressive episode.

[0044] In some embodiments, the severe depressive episode includes severe depressive episode without psychotic features and / or severe depressive episode with psychotic features.

[0045] In some embodiments, the product includes a reagent, a kit, an electronic system or a device.

[0046] In some embodiments, the ex vivo marker (with a certain concentration or ratio of the marker) or the peripheral blood or serum containing the marker of any of the preceding embodiments is used alone as an auxiliary diagnostic or diagnostic product for female depressive disorder or as a calibrator or quality control product.

[0047] In some embodiments, the method for diagnosing or assisting in diagnosing female depressive disorder is the method for assessing the risk of female depressive disorder of any of the subsequent embodiments or embodiments.

[0048] In some embodiments, FT3 is used as an auxiliary diagnostic criterion for depressive disorder in a subject: when the peripheral blood collected from the subject at the time of visit, the level of FT3 is ≤ (2.84-2.995) pg / ml, which indicates that the subject has a higher risk of being diagnosed with depressive disorder.

[0049] In another aspect, the embodiments of the present application provide a reagent or kit for diagnosing or assisting in diagnosing female depressive disorder, which comprises a detection reagent with a marker content as described in any of the preceding embodiments or embodiments.

[0050] In some embodiments, the reagent or kit further comprises an instruction, which records an instruction indicating that the marker level corresponding to the detection reagent is used for diagnosis or auxiliary diagnosis of depression in adult women.

[0051] In another aspect, referring to Figure 1 which shows a method for constructing a female depression diagnosis model provided by an embodiment of the present application, comprising the following steps: S100, obtaining feature data representing markers in training samples and corresponding annotation results, establishing a data set of female samples; the markers are the markers described in any of the preceding embodiments or embodiments.

[0052] In some embodiments, the annotation result comprises a label representing the risk of depression in the sample.

[0053] In some embodiments, the risk of depression includes whether or not the subject has depression.

[0054] In some embodiments, the label can be a character or a string. The content of the diagnosis result corresponds to the content of the annotation result.

[0055] In some embodiments, the feature data representing the markers in the training samples is the detection result of the marker content or the value after standardization processing of the detection result.

[0056] In some embodiments, the standardization processing method includes at least one of Z-score standardization, Min-Max normalization, robust scaling, and logarithmic transformation.

[0057] S110, training the model using the data set to construct the female depression diagnosis model.

[0058] The diagnosis model of the embodiments of the present application is not particularly limited, and a diagnosis model commonly used in the art for predicting the risk of disease can be selected.

[0059] In some embodiments, the diagnosis model can be selected from any one of logistic regression, random forest, XGboost, support vector machine (SVM), decision tree (DT), K nearest neighbor (KNN), naive Bayes (NB), LightGBM, and CatBoost.

[0060] In some embodiments, the class and number of training samples can be routinely selected by those skilled in the art, and the number of total training samples or training samples of various classes (e.g., healthy population group, depression patient group) can be independently ≥ any value selected from 10, 50, 100, 200, 300, 400, and 500 or a range between any two of them.

[0061] In another aspect, referring to Figure 2 It is shown that the embodiments of the present application further provide a method for assessing the risk of female depression (a method for diagnosing or assisting in diagnosing female depression), which comprises the following steps: S200, obtaining characteristic data of a marker in a sample of a subject; the marker is the marker described in any of the preceding embodiments or implementation manners; S210, obtaining an assessment result of the risk of depression of the subject according to the characteristic data of the marker in the sample of the subject.

[0062] In some embodiments, the characteristic data of the marker is a detection result of the content of the marker or a value obtained by standardizing the detection result.

[0063] In some embodiments, the depression covers mild depression, moderate depression and severe depression.

[0064] In some embodiments, the severe depression includes severe depression without psychosis and / or severe depression with psychosis.

[0065] In some embodiments, the step of obtaining an assessment result of the risk of depression of the subject according to the characteristic data of the marker in the sample of the subject includes comparing the detection result of the content of the marker in the sample of the subject with a first preset threshold, and obtaining an assessment result of the risk of depression of the subject according to the comparison result.

[0066] In some embodiments, the step of obtaining an assessment result of the risk of depression of the subject according to the characteristic data of the marker in the sample of the subject includes obtaining a result calculated by a preset model from a value obtained by standardizing 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 an assessment result of the risk of depression of the subject according to the comparison result.

[0067] In some embodiments, the first preset threshold or the second preset threshold is obtained based on the principle of maximizing the Youden index.

[0068] In particular, the first preset threshold value herein refers to a positive judgment value, which is a critical single concentration value of a marker determined according to the sensitivity and specificity requirements of a clinic when using a ROC curve or a model to fit data. In one embodiment, the detection concentration value of the marker is directly compared with the positive judgment value, and a diagnosis or auxiliary diagnosis result of depression of the subject is output according to the comparison result. For example, when the marker is free triiodothyronine, the detection concentration value of free triiodothyronine is directly compared with the positive judgment value, and a diagnosis or auxiliary diagnosis result of depression of the subject is output according to the comparison result. For another example, when the marker is selected from the following combinations: (a) FT3 and cortisol; (b) FT3 and ADPN; (c) FT3 and IL6; (d) FT3, cortisol and ADPN; (e) FT3, cortisol and IL6; (f) FT3, cortisol and TNFα; (g) FT3, cortisol, ADPN and IL6; (h) FT3, cortisol, IL6 and TNFα; (i) FT3, cortisol, ADPN, IL-6 and TNFα, a corresponding first preset threshold value is set for each marker in the combination respectively, and after comparison respectively, a diagnosis or auxiliary diagnosis result of depression of the subject is output according to the comparison result.

[0069] In particular, the second preset threshold value herein can be a prediction probability threshold value, which refers to a prediction probability threshold value (P value) of a model determined according to the sensitivity and specificity requirements of a clinic when the diagnosis model is a logistic regression model, a random forest model or other models. In one embodiment, the P value of the corresponding marker feature data is calculated by bringing the marker feature data into a preset model, and the P value is compared with the prediction probability threshold value of the model, and a diagnosis or auxiliary diagnosis result of depression of the subject is output according to the comparison result.

[0070] The second preset threshold value herein can also be a dependent variable threshold value, which refers to a preset dependent variable threshold value of a model determined according to the sensitivity and specificity requirements of a clinic when the diagnosis model is a function formula. In one embodiment, the dependent variable is calculated by bringing the marker feature data into the function formula, and the dependent variable is compared with the dependent variable threshold value of the function formula, and a diagnosis or auxiliary diagnosis result of depression of the subject is output according to the comparison result.

[0071] The logistic regression model can be a function formula, or a combination of a function formula and a P value calculation formula.

[0072] In some embodiments, the step of obtaining the result indicative of the risk assessment of depression 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 constructing method according to any of the preceding embodiments or aspects, to obtain the result indicative of the risk assessment of depression of the subject.

[0073] In some embodiments, the female is the female according to any of the preceding embodiments or aspects.

[0074] In another aspect, the embodiments of the present application also provide a device for diagnosing or assisting diagnosis of depression in a female, comprising: a obtaining module configured to obtain characteristic data representing a marker in a sample of a subject; the marker is the marker according to any of the preceding embodiments or aspects; a diagnosing module configured to obtain a result indicative of diagnosis or assisting diagnosis of depression of the subject according to the characteristic data of the marker in the sample of the subject.

[0075] In some embodiments, the characteristic data of the marker is a detection result of the content of the marker or a value standardized from the detection result.

[0076] In some embodiments, the step of obtaining the result indicative of diagnosis or assisting diagnosis of depression 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 result indicative of diagnosis or assisting diagnosis of depression of the subject according to the comparison result.

[0077] In some embodiments, the step of obtaining the result indicative of diagnosis or assisting diagnosis of depression of the subject according to the characteristic 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 the result indicative of diagnosis or assisting diagnosis of depression of the subject according to the comparison result.

[0078] In some embodiments, the step of obtaining the result indicative of diagnosis or assisting diagnosis of depression 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 constructing method according to any of the preceding embodiments or aspects, to obtain the result indicative of diagnosis or assisting diagnosis of depression of the subject.

[0079] The module provided by the embodiments of the present application can be stored in the memory in the form of software or firmware (Firmware) or solidified in the operating system (Operating System, OS) of the electronic device provided by the present application, and can be executed by the processor in the electronic device. At the same time, the data, program code and the like required for executing the above-mentioned module can be stored in the memory.

[0080] In another aspect, the embodiments of the present application also provide an electronic device, which comprises a processor and a memory; the memory is used for storing a program, when the program is executed by the processor, the processor realizes the construction method as described in any of the preceding embodiments or implementation forms or the female depression risk assessment method as described in any of the preceding embodiments or implementation forms.

[0081] Please refer to Figure 3 A structural block diagram of the electronic device 100 provided by the embodiments of the present application is shown in FIG. 1. The electronic device 100 can comprise a memory 110, a processor 120, a bus 130 and a communication interface 140, and the memory 110, the processor 120 and the communication interface 140 are electrically connected with each other to realize the transmission or interaction of data. For example, these elements can be electrically connected with each other through one or more buses 130 or signal lines.

[0082] The memory 110 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) and the like.

[0083] 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.

[0084] 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.

[0085] 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 as described in any of the foregoing embodiments or implementation methods, or the female depression risk assessment method as described in any of the foregoing embodiments or implementation methods.

[0086] In some implementations, the computer-readable medium can be a general-purpose storage medium, such as a removable disk or hard disk.

[0087] On the other hand, embodiments of the present invention also provide an electronic system for diagnosing or assisting in the diagnosis of depression in women, 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 indicative or auxiliary diagnostic result for depression based on characteristic data of biomarkers in the subject sample; The marker is the same as the marker in any of the preceding embodiments or implementation manners.

[0088] In some implementation manners, the step of obtaining a diagnosis or auxiliary diagnosis result of depression of the subject according to the characteristic data of the marker is the same as that in any of the preceding embodiments or implementation manners, and will not be repeated here.

[0089] In addition, the embodiment of the present application further provides a treatment method for female depression, which comprises the following steps: The female depression risk assessment method in any of the preceding embodiments or implementation manners is used to assess the risk of depression of the subject, and a depression risk assessment result is obtained. According to the depression risk assessment result, the corresponding treatment is performed on the high-risk patient.

[0090] In optional implementation manners, the treatment mode comprises 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), drug therapy and physical therapy.

[0091] In optional implementation manners, the drug therapy comprises any one or more of selective serotonin reuptake inhibitors (SSRIs), serotonin and norepinephrine reuptake inhibitors (SNRIs), norepinephrine and specific serotoninergic antidepressants (NaSSAs) and other drugs.

[0092] In optional implementation manners, the SSRIs comprise any one or more of fluoxetine (Prozac), paroxetine, sertraline (Zoloft), fluvoxamine, citalopram and escitalopram. The SNRIs comprise venlafaxine and duloxetine. The NaSSAs comprise mirtazapine. The other drugs comprise bupropion and agomelatine.

[0093] The features and performances of the present application are further described in detail below in combination with embodiments.

[0094] The sample type used in the embodiments: the sample refers to a human peripheral blood sample, including plasma or serum.

[0095] The sampling method of the sample used in the embodiments: 5ml of venous blood of the patient with depressive disorder and the healthy person in an empty stomach state is collected, the sampling method is a well-known negative pressure blood collection technology, the serum is separated by centrifugation at 3000rpm for 10min, and is stored in a refrigerator at-80℃ for detection.

[0096] The detection method of the marker: the detection kit used in the examples for FT3 (item number 1302533005M) + Cortisol (item number 130270002M) + TNFα (item number 130216006M) + IL-6 (item number 130216504M) + ADPN (item number 130505009S) is from Shenzhen Xin Industry Biomedical Engineering Co., Ltd., and the detection is carried out according to the operation steps in the instruction manual of the kit.

[0097] Example 1, marker discovery for assisting diagnosis of depressive disorder 1.1 Information of research samples: Sample source and population information: peripheral blood samples of depressive disorder patients were continuously collected (collected continuously within a period of time) from A hospital, including 45 cases of depressive disorder patients and 32 cases of healthy physical examination population serum samples, excluding perinatal population, divided into depressive disorder group and healthy control group, the age and gender distribution of the two groups of subjects are shown in Table 1.

[0098] Table 1 Sample information

[0099] 1.2 Experimental method The concentration of potential markers in depressive group and healthy group samples was detected by using the detection kit and detection method provided in the example. The detection was carried out according to the operation steps in the instruction manual of the kit as described above, and the difference of potential marker level between depressive group and healthy group was compared.

[0100] Difference analysis of potential markers between depressive group and healthy group, the results are shown in Table 2.

[0101] Table 2 Difference analysis results of potential markers between depressive group and healthy group

[0102] As shown in Table 2, among the 17 potential markers, the levels of metabolic indicators 25-OH VD, endocrine indicators FT3, cortisol, inflammatory indicators TNFα, IL-6 and APDN showed significant differences between healthy group and depressive group.

[0103] Example 2, role of FT3 in small sample size of adult female depressive disorder auxiliary diagnosis 2.1 Information of research samples: Sample source and population information: Peripheral blood samples were continuously collected from adult women aged 19-65 years from Hospital A, including serum samples from 41 patients with depressive disorders and 33 healthy individuals undergoing physical examinations. Perinatal patients were excluded. The samples were divided into a depression group and a healthy group. The mean ages of the two groups were 37 and 30 years, respectively, with no significant difference. P =0.194).

[0104] Experimental Methods: The concentration of FT3 in samples from adult women in a depression group and a healthy group was detected using the FT3 detection kit and method provided in the examples. The detection was performed according to the instructions provided with the aforementioned kit. 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 adult women with depressive disorders and healthy individuals.

[0105] 2.2 Analysis of differences in FT3 between the depressed group and the healthy group like Figure 4 As shown, the FT3 level in the depressed group was significantly lower than that in the healthy group. p <0.0001).

[0106] 2.3 Results of ROC curve analysis of FT3 in diagnosing depressive disorders like Figure 5 As shown, the ROC curve AUC of FT3 distinguishing between the healthy and depressed groups of adult women was 0.721, with an optimal threshold of 2.995 pg / ml, a sensitivity of 0.78, and a specificity of 0.64, demonstrating that FT3 has good diagnostic performance as an auxiliary diagnostic biomarker for depressive disorders in adult women.

[0107] Example 3: The role of biomarkers and biomarker combinations in the auxiliary diagnosis of depressive disorders 3.1 Study population and sample sources, experimental methods and data analysis methods 3.1 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 3.

[0108] Table 3. Sample distribution at different disease stages

[0109] 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 adult female patients with depressive disorders and healthy individuals from Hospital C, excluding the perinatal population. The samples included 90 patients with depressive disorders and 51 healthy individuals undergoing physical examinations. They were divided into a depression group and a healthy group. The age and disease distribution of the two groups are shown in Tables 4 and 5 below.

[0110] Table 4. Age distribution of the sample

[0111] Both the healthy group and the depressed group covered people of different age groups. Statistically, there was no significant difference in the age distribution between the healthy group and the depressed group according to the chi-square test.

[0112] Table 5. Distribution of disease status in the sample

[0113] The patient group covered patients with depression of different severities, 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.

[0114] 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.

[0115] 3.2 The role of FT3 and biomarker combination in constructing a logistic regression model for the diagnosis of depressive disorders in adult women. 3.2.1 Experimental methods, differences in marker levels between groups, and model construction methods The concentration of FT3 marker in serum was detected using the detection kit and method provided in the foregoing embodiments. The detection was performed according to the instructions of the aforementioned kit, and the differences in FT3 between the healthy control group and the depressive disorder group were statistically analyzed. The results are shown in Table 6.

[0116] Table 6 Test Results

[0117] The results showed that the FT3 level in the depressed group was significantly lower than that in the healthy group. p <0.001).

[0118] 3.2.2 Model Construction A logistic regression prediction model was constructed using each marker (FT3, cortisol, TNFα, IL-6, APDN). The healthy group and the depression group in adult women were randomly divided into training set and test set in the ratio of 3:1, the training set was used for model establishment, and the test set was used to test the performance of the established model. Before constructing the logistic regression model, the dimension of each marker was eliminated by Z-score standardization method.

[0119] The calculation formula of the logistic regression model prediction probability is: P = 1 / (1 + e -Y ), where e is a natural constant, Y is a linear formula, and P is the prediction probability. Based on the model prediction probability, the AUC was calculated using ROC curve analysis, and the threshold value corresponding to the maximum Youden index was selected as the prediction probability standard. The sensitivity and specificity of the model were calculated to evaluate the ability of the model to distinguish between the healthy group and the depression group. The results are shown in Table 7.

[0120] Table 7 Results

[0121] Based on Table 7, in the samples provided in step 3.1, there was a significant difference between FT3 in depressed patients and healthy people, which was basically consistent with the conclusion of the samples provided in step 2.1. Further, FT3 had good diagnostic performance for the auxiliary diagnosis of female depression with an AUC > 0.7. The AUC of the combined detection scheme of FT3 and any one or more of the cortisol, ADPN, IL6, and TNFα provided in this scheme was all > 0.7, which could be used for the diagnosis of depression in patients.

[0122] Among them, from the results of the test set: The AUC of FT3 for the auxiliary diagnosis of depression in adult women reached 0.75, which had good diagnostic performance. Based on this model, when FT3 ≤ 2.84 pg / mL, it was considered as a high risk of depression disorder. The AUC of the test set of the two joint detection schemes of FT3 and cortisol is improved by 0.04, and the diagnostic performance is better than that of the single FT3 diagnostic scheme; it is shown that the two joint detection schemes of FT3 and cortisol have higher diagnostic value for depression disorder in adult women. The inventors speculate that FT3 and cortisol play an important role in the neuroregulation and emotion regulation of adult women, and they interact with each other and are relatively independent, and because of the influence of estrogen fluctuation and special physiological stage, individual-specific differences are presented, part of the patients are mainly HPT axis abnormal, showing FT3 reduction, and neuro-metabolic disorder is the core pathology, while part of the patients are mainly HPA axis abnormal, showing cortisol elevation, and stress endocrine imbalance drives the occurrence of the disease; there are also some patients with abnormalities in both axes. The two joint detection of FT3 and cortisol can capture the pathological heterogeneity of depression in adult women more comprehensively through the dual dimensions of "neuro-metabolic regulation-stress state evaluation", make up for the shortcomings of single index, and thus improve the diagnostic efficiency.

[0123] In addition, in the two joint detection schemes, the test set AUC of FT3+ADPN, FT3+IL6 also reaches 0.73, which has good diagnostic value.

[0124] In the three joint detection schemes, the test set AUC of FT3+cortisol+ADPN, FT3+cortisol+IL6, FT3+cortisol+TNFα also reaches 0.77-0.78, which has good diagnostic value.

[0125] In the four joint detection schemes, the test set AUC of FT3+cortisol+ADPN+IL6 and FT3+cortisol+IL6+TNFα also reaches 0.77-0.78, which has good diagnostic value.

[0126] In addition, the test set AUC of the five joint detection schemes of FT3+cortisol+ADPN+IL-6+TNFα also reaches 0.79, which has good diagnostic performance.

[0127] Example 4: Diagnostic performance verification based on random forest.

[0128] Based on the enrollment samples of Example 3, a random forest model was constructed for FT3, cortisol, ADPN single marker or marker combination: (1) Data set division: the healthy group and the depression group were randomly divided into training set and test set according to the ratio of 3:1 respectively, the training set was used for model training, and the test set was used for evaluating the performance of the model. (2) The optimization of random forest model parameters includes mtry (the number of randomly selected features when node splitting), ntree (the number of decision trees) and nodesize (the minimum number of samples required for leaf node splitting). The best hyperparameters were searched using grid search method, and AUC was used as the optimization index. The combination of hyperparameters with the highest average value of ten-fold cross-validation AUC was selected. (3) Model evaluation: based on the best combination of hyperparameters, the training set data was used to train the model parameters, and the prediction probability of the training set was obtained. ROC curve analysis was used to determine the threshold of prediction classification. Based on the random forest model obtained by training, the test set data was predicted to obtain the prediction probability and prediction classification, and AUC, sensitivity and specificity were calculated to evaluate the ability of the model to distinguish between healthy group and depression group.

[0129] The results are shown in Table 8.

[0130] Table 8 Results

[0131] After verifying part of the joint detection scheme, the test set results of the random forest model showed that FT3, two joint detection of FT3 and cortisol, three joint detection of FT3, cortisol and ADPN, and five joint detection of FT3+cortisol+ADPN+IL-6+TNFα had good diagnostic performance for adult female depression. Especially the two joint detection of FT3 and cortisol, the diagnostic performance was improved compared with single detection, so the invention speculated that FT3 and cortisol had certain complementary effect. Consistent with the conclusion of the logistic regression model.

[0132] Example 5 Diagnosis performance verification based on support vector machine.

[0133] Based on the enrollment samples of Example 3, the VD, FT3, TNF-alpha, cortisol, IL-6, ADPN single marker or marker combination was used to construct a support vector machine model: (1) data set division and pretreatment: the health group and the depression group were randomly divided into training set and test set according to the ratio of 3:1, the training set was used for model training, and the test set was used for evaluating the performance of the model. The quantitative variables were normalized by YeoJohnson method. The quantitative variables were standardized by Z-score method. (2) The kernel function of support vector machine model was selected as radial basis kernel, and the optimization hyperparameters included cost (cost) and rbf_sigma (the influence range of single training sample in feature space). The best hyperparameter combination was searched by grid search method, and the AUC was used as the optimization index, and the hyperparameter combination with the highest average value of ten-fold cross validation AUC was selected. (3) Model evaluation: based on the best hyperparameter combination, the training set data was used to train the model parameters, and the prediction probability of the training set was obtained, and the threshold of prediction classification was determined by using ROC curve analysis. Based on the support vector machine model obtained by training, the test set data was predicted to obtain the prediction probability and prediction classification, and the AUC, sensitivity and specificity were calculated to evaluate the ability of the model to distinguish the health group and the depression group.

[0134] The results are shown in Table 9.

[0135] Table 9 Results

[0136] After verifying part of the joint detection scheme, the test set results of the support vector machine model showed that FT3, two joint detection of FT3 and cortisol, and five joint detection of FT3+cortisol+ADPN+IL-6+TNF-alpha had good diagnostic performance for adult female depression. Especially the two joint detection of FT3 and cortisol, the diagnostic performance was improved compared with single detection, so the application speculated that FT3 and cortisol had certain complementary effect. The conclusion was consistent with that of the logistic regression model.

[0137] Experiments show that among a variety of mainstream machine learning models, the markers or marker combinations of the embodiments of the application show stable and significant diagnostic performance for female depression, and the diagnostic efficacy is not dependent on the selection of a specific model, and has wide applicability and reliability.

[0138] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. Use of a test reagent for detecting the content of a marker in a sample in the manufacture of a product for diagnosing or aiding in the diagnosis of depression in a female; the marker comprising FT3.

2. Use according to claim 1, characterized in that, The marker further comprises one or more of cortisol, ADPN, IL6 and TNFα; Optionally, the marker is selected from the combination of any one of (a)~(i): (a) FT3 and cortisol; (b) FT3 and ADPN; (c) FT3 and IL6; (d) FT3, cortisol and ADPN; (e) FT3, cortisol and IL6; (f) FT3, cortisol and TNFα; (g) FT3, cortisol, ADPN and IL6; (h) FT3, cortisol, IL6 and TNFα; (i) FT3, cortisol, ADPN, IL-6 and TNFα.

3. Use according to claim 1 or 2, characterized in that, The female is aged greater than 18 years; Optionally, the female is aged between 18 and 65 years; Optionally, the female is a non-perinatal female; Optionally, the depression covers: mild depressive episode, moderate depressive episode and severe depressive episode; Optionally, the severe depressive episode comprises: severe depressive episode without psychosis and / or severe depressive episode with psychosis; 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 female depression, characterized by, It at least comprises: a test reagent for detecting the content of a marker in a sample; the marker comprising free triiodothyronine; Optionally, the reagent or kit further comprises an instruction, which records instructions indicating the use of the marker level corresponding to the test reagent for the diagnosis or auxiliary diagnosis of depression in an adult female; Optionally, the marker is selected from the combination of any one of (a)~(i): (a) FT3 and cortisol; (b) FT3 and ADPN; (c) FT3 and IL6; (d) FT3, cortisol and ADPN; (e) FT3, cortisol and IL6; (f) FT3, cortisol and TNFα; (g) FT3, cortisol, ADPN and IL6; (h) FT3, cortisol, IL6 and TNFα; (i) FT3, cortisol, ADPN, IL-6 and TNFα.

5. A method of constructing a female depression diagnosis model, characterized by, It comprises the following steps: Obtaining feature data representing markers in a training sample and corresponding labeling results, establishing a data set of female samples; the markers are the markers described in claim 1 or 2; Training a model using the data set to construct the female depression diagnosis model; Optionally, the diagnosis model is selected from any one of: a logistic regression model, a random forest model, an XGboost model, a support vector machine model, a decision tree model, a K-nearest neighbor model, a naive Bayes model, a LightGBM model and a CatBoost model.

6. The construction method of claim 5, wherein, The feature data representing markers in a training sample is: a detection result of the content of a marker 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 labeling result comprises a label representing a risk of depression of the subject.

7. A method of assessing the risk of depression in a woman, characterized in that, It comprises: obtaining feature data representing a marker in a sample of a subject; the marker comprises FT3; obtaining a risk assessment result of depression of the subject according to the feature data of the marker in the sample of the subject; Optionally, the marker is selected from the combination of any one of (a)~(i): (a) FT3 and cortisol; (b) FT3 and ADPN; (c) FT3 and IL6; (d) FT3, cortisol and ADPN; (e) FT3, cortisol and IL6; (f) FT3, cortisol and TNFα; (g) FT3, cortisol, ADPN and IL6; (h) FT3, cortisol, IL6 and TNFα; (i) FT3, cortisol, ADPN, IL-6 and TNFα; Optionally, the feature data of the marker is a detection result of a content of the marker or a value standardized from the detection result; Optionally, the step of obtaining a risk assessment result 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 risk assessment result of depression of the subject according to a comparison result; Optionally, the step of obtaining a risk assessment result of depression of the subject according to the feature data of the marker in the sample of the subject comprises: obtaining a value standardized from the detection result of the content of the marker in the sample of the subject, calculating a result from the value standardized from the detection result of the content of the marker in the sample of the subject according to a preset model, comparing the calculated result with a second preset threshold, and obtaining a risk assessment result of depression of the subject according to a comparison result; Optionally, the step of obtaining a risk assessment result of depression of the subject according to the feature data of the marker in the sample of the subject comprises: inputting the feature 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 a risk assessment result of depression of the subject; Optionally, the depression covers mild depression episode, moderate depression episode and severe depression episode. Optionally, the severe depression episode comprises severe depression episode without psychosis and / or severe depression episode with psychosis. Optionally, the female is the female of claim 3.

8. A device for diagnosing or aiding in the diagnosis of female depression, characterized in that It comprises: an obtaining module configured to obtain feature data representing a marker in a sample of a subject; the marker is the marker of claim 1 or 2; a diagnosing module configured to obtain a diagnosis or auxiliary diagnosis result of depression of the subject according to the feature data of the marker in the sample of the subject; Optionally, the feature data of the marker is a detection result of a content of the marker or a value standardized from the detection result. Optionally, the step of obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression 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 result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the comparison result. Optionally, the step of obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the characteristic data of the marker in the sample of the subject comprises: obtaining the result calculated by a preset model from the value of the marker content in the sample of the subject after standardization, comparing the calculated result with a second preset threshold, and obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the comparison result. Optionally, the step of obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the characteristic data of the marker in the sample of the subject comprises: inputting the characteristic data of the marker in the sample of the subject into the diagnostic model constructed by the construction method of claim 5 or 6 to obtain the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject.

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

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

11. An electronic system for the diagnosis or aided diagnosis of female depression, characterized by, The electronic system comprises: an acquisition module configured to acquire characteristic data of a marker in a sample of a subject; an analysis module configured to obtain a result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the characteristic data of the marker in the sample of the subject; wherein the marker comprises at least FT3; Optionally, the marker is selected from the combination of any one of (a)~(i): (a) FT3 and cortisol; (b) FT3 and ADPN; (c) FT3 and IL6; (d) FT3, cortisol and ADPN; (e) FT3, cortisol and IL6; (f) FT3, cortisol and TNFα; (g) FT3, cortisol, ADPN and IL6; (h) FT3, cortisol, IL6 and TNFα; (i) FT3, cortisol, ADPN, IL-6 and TNFα; Optionally, the step of obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the characteristic data of the marker in the sample of the subject comprises: comparing the content of the marker in the sample of the subject with a first preset threshold, and obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the comparison result. Optionally, the step of obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the characteristic data of the markers in the sample of the subject comprises: obtaining the result of the calculation of the normalized value of the detection result of the content of the markers in the sample of the subject by the preset model, comparing the calculated result with a second preset threshold, and obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the comparison result. Optionally, the step of obtaining the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject according to the characteristic data of the markers in the sample of the subject comprises: inputting the characteristic data of the markers in the sample of the subject into the diagnostic model constructed by the construction method of claim 5 or 6 to obtain the result indicative of the diagnosis or auxiliary diagnosis of depression of the subject.

Images