Brain-derived neurotrophic factor auxiliary determination system and method for evaluating chemotherapy-induced depression

Abstract

The invention discloses a brain-derived neurotrophic factor auxiliary determination system and method for evaluating chemotherapy-induced depression. The system comprises: a BDNF antibody complex, which is prepared by covalently coupling inorganic metal magnetic particles with an anti-BDNF monoclonal antibody; the magnetic field generation module comprises a gradient magnetic field generator and an alternating magnetic field controller and is used for applying a detection magnetic field to the to-be-detected peripheral blood sample containing the BDNF antibody complex; the magnetic conductivity detection unit is used for monitoring magnetic conductivity dynamic change information of the BDNF antibody compound in a detection magnetic field in real time and generating a time domain magnetic signal of the BDNF antibody compound; the control module is used for constructing a nonlinear mapping relation between the magnetic conductivity dynamic change rate and the BDNF concentration; and generating a sample BDNF concentration corresponding to the peripheral blood sample to be detected according to the magnetic conductivity dynamic change information and the nonlinear mapping relationship, and completing the brain-derived neurotrophic factor auxiliary determination of the peripheral blood sample to be detected. According to the BDNF concentration of the sample, evaluating the chemotherapy induced depression of the to-be-detected peripheral blood sample.

Description

Technical Field

[0001] The present application relates to the technical field of biomaterial detection, and particularly relates to a brain-derived neurotrophic factor-assisted determination system and method for chemotherapy-induced depression assessment. Background Art

[0002] Brain-derived neurotrophic factor (BDNF, abrineurin) is a type of neurotrophic factor. In addition to affecting the development of nerve cells, it also plays an important role in memory and cognitive functions and is widely considered to be related to depression.

[0003] For cancer patients receiving chemotherapy (especially doxorubicin-based chemotherapy), studies have shown that the accumulation of doxorubicin in peripheral blood reduces the expression level of BDNF. There is also a hypothesis that although doxorubicin cannot penetrate the blood-brain barrier, it can still indirectly mediate damage to endothelial cells, glial cells, and nerve cells that secrete BDNF, thus exacerbating depression. Therefore, BDNF protein can be used as a biomarker for predicting future depression and melancholy.

[0004] Most traditional methods for BDNF detection focus on the central nervous system-related fields, such as using enzyme-linked immunosorbent assay, etc. The prerequisite is that there are no other factors in the patient's peripheral blood that may cause cytokine reactions. This prerequisite cannot be established in tumor patients because the carcinoembryonic cells, interleukins, and blood factor counts in the peripheral blood of tumor patients are different from those of normal people, and chemotherapy drugs themselves seriously affect the normal functions of cytokines, adding various difficulties to the determination of brain-derived neurotrophic factor.

[0005] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems. Summary of the Invention

[0006] The present application provides a brain-derived neurotrophic factor-assisted determination system and method for chemotherapy-induced depression assessment, aiming to solve the problem that most traditional methods for BDNF detection in the prior art focus on the central nervous system-related fields, such as using enzyme-linked immunosorbent assay, etc. The prerequisite is that there are no other factors in the patient's peripheral blood that may cause cytokine reactions. This prerequisite cannot be established in tumor patients because the carcinoembryonic cells, interleukins, and blood factor counts in the peripheral blood of tumor patients are different from those of normal people, and chemotherapy drugs themselves seriously affect the normal functions of cytokines, adding various difficulties to the determination of brain-derived neurotrophic factor.

[0007] In a first aspect, the present application provides a brain-derived neurotrophic factor-assisted determination system for chemotherapy-induced depression assessment, including:

[0008] A BDNF antibody complex labeled with magnetic induction molecules, wherein the BDNF antibody complex is prepared by covalently coupling inorganic metal magnetic particles with anti-BDNF monoclonal antibodies;

[0009] A magnetic field generating module, including a gradient magnetic field generator and an alternating magnetic field controller, for applying a detection magnetic field to a peripheral blood sample to be tested containing the BDNF antibody complex;

[0010] A magnetic permeability detection unit, including a superconducting quantum interference device, for real-time monitoring of the dynamic change information of the magnetic permeability of the BDNF antibody complex in the detection magnetic field and generating a time-domain magnetic signal of the BDNF antibody complex;

[0011] A control module, which performs denoising processing on the time-domain magnetic signal based on wavelet transform;

[0012] The control module constructs a non-linear mapping relationship between the dynamic change rate of magnetic permeability and BDNF concentration; according to the dynamic change information of magnetic permeability and the non-linear mapping relationship, it generates the corresponding sample BDNF concentration of the peripheral blood sample to be tested, and completes the auxiliary determination of brain-derived neurotrophic factor in the peripheral blood sample to be tested;

[0013] The control module completes the evaluation of chemotherapy-induced depression for the peripheral blood sample to be tested according to the sample BDNF concentration.

[0014] In some embodiments, the evaluation of chemotherapy-induced depression for the peripheral blood sample to be tested according to the sample BDNF concentration includes: obtaining the chemotherapy cycle information and cumulative dose of doxorubicin corresponding to the peripheral blood sample to be tested; generating a depression occurrence probability index according to the BDNF concentration value, chemotherapy cycle information, and cumulative dose of doxorubicin, and completing the evaluation of chemotherapy-induced depression for the peripheral blood sample to be tested.

[0015] Exemplarily, the expression of the depression occurrence probability index includes: P = 1 / (1 + e^(-(α·C + β·T + γ·D + δ))); where P is the depression occurrence probability index, C is the BDNF concentration value, T is the number of days in the cycle corresponding to the chemotherapy cycle information, D is the cumulative dose of doxorubicin, α, β, γ are characteristic weight coefficients, and δ is a regulation factor.

[0016] It should be noted that in some embodiments, the characteristic weight coefficients are determined by regression analysis according to a preset clinical sample training set; the value range of α is [-0.25, -0.15], the value range of β is [0.03, 0.08], and the value range of γ is [0.10, 0.20].

[0017] In some embodiments, constructing the non-linear mapping relationship between the dynamic change rate of magnetic permeability and BDNF concentration includes: extracting multi-scale features of the time-domain magnetic signal to obtain time-frequency characteristic parameters; inputting the time-frequency characteristic parameters into a pre-trained support vector regression model, and the support vector regression model establishes the non-linear mapping relationship between the time-frequency characteristic parameters and BDNF concentration through kernel function space mapping.

[0018] Exemplarily, generating the sample BDNF concentration corresponding to the peripheral blood sample to be tested according to the dynamic change information of magnetic permeability and the non-linear mapping relationship includes: establishing a reference curve between the dynamic change information of magnetic permeability and the standard BDNF concentration sample based on the gradient dilution method; obtaining the mapping value corresponding to the dynamic change information of magnetic permeability under the non-linear mapping relationship; and performing dynamic weighted fusion on the reference curve and the mapping value to obtain the sample BDNF concentration.

[0019] In some embodiments, generating the time-domain magnetic signal of the BDNF antibody complex includes: synchronously collecting the original magnetic signal of the magnetic permeability change through the superconducting quantum interference device; the ratio of the sampling frequency corresponding to the original magnetic signal to the operating frequency of the alternating magnetic field controller is greater than 10; performing baseline correction and amplitude normalization processing on the original magnetic signal to eliminate the environmental magnetic field interference component of the original magnetic signal; obtaining the time-domain and frequency-domain joint characteristic matrix corresponding to the original magnetic signal according to the short-time Fourier transform, and extracting the characteristic frequency band components related to the binding state of the BDNF antibody complex in the time-domain and frequency-domain joint characteristic matrix; and reconstructing the characteristic frequency band components to obtain the waveform of the time-domain magnetic signal.

[0020] In some embodiments, before constructing the non-linear mapping relationship between the dynamic change rate of magnetic permeability and BDNF concentration, it further includes: identifying and eliminating the magnetic interference characteristics in the time-domain magnetic signal; the magnetic interference characteristics include adriamycin metabolite characteristics and interleukin-6 characteristics.

[0021] In some embodiments, the particle size of the inorganic metal magnetic particles is 10 - 100 nm and the surface is modified with polyethylene glycol; and / or, the magnetic field intensity of the detection magnetic field is 0.1 - 1.5 T.

[0022] In a second aspect, the present application provides a method for assisting in the determination of brain-derived neurotrophic factor for chemotherapy-induced depression assessment, which is applied to the control module of the brain-derived neurotrophic factor assisting determination system provided in any embodiment of the present application; the method includes:

[0023] Obtaining the dynamic change information of the magnetic permeability and the time-domain magnetic signal of the BDNF antibody complex monitored in real time by the magnetic permeability detection unit;

[0024] Perform denoising processing on the time-domain magnetic signal based on wavelet transform;

[0025] Construct a non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration;

[0026] Generate the sample BDNF concentration corresponding to the peripheral blood sample to be tested according to the dynamic change information of magnetic permeability and the non-linear mapping relationship, and complete the auxiliary determination of brain-derived neurotrophic factor in the peripheral blood sample to be tested;

[0027] Complete the chemotherapy-induced depression assessment of the peripheral blood sample to be tested according to the sample BDNF concentration.

[0028] In a third aspect, the present application provides an apparatus for auxiliary determination of brain-derived neurotrophic factor for chemotherapy-induced depression assessment, including:

[0029] A signal acquisition unit for acquiring the dynamic change information of the magnetic permeability of the BDNF antibody complex in the detection magnetic field and the time-domain magnetic signal in real time by a magnetic permeability detection unit;

[0030] A denoising processing unit for performing denoising processing on the time-domain magnetic signal based on wavelet transform;

[0031] A mapping construction unit for constructing a non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration;

[0032] An auxiliary determination unit for generating the sample BDNF concentration corresponding to the peripheral blood sample to be tested according to the dynamic change information of magnetic permeability and the non-linear mapping relationship, and completing the auxiliary determination of brain-derived neurotrophic factor in the peripheral blood sample to be tested;

[0033] A depression assessment unit for completing the chemotherapy-induced depression assessment of the peripheral blood sample to be tested according to the sample BDNF concentration.

[0034] In a fourth aspect, the present application provides a control module, the control module includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method provided in any embodiment of the present application when executing the computer program.

[0035] In a fifth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer-readable instruction is executed by a processor, one or more processors are enabled to execute the method provided in any embodiment of the present application.

[0036] The present application provides a brain-derived neurotrophic factor (BDNF) assisted determination system and method for chemotherapy-induced depression assessment. The BDNF assisted determination system aims to solve the limitations of traditional detection methods in cancer patients and achieve efficient and accurate determination of BDNF by combining magnetic labeling and high-sensitivity detection techniques.

[0037] BDNF antibody complex labeled with magnetic induction molecules: Materials: Inorganic metal magnetic particles (such as magnet nanoparticles) are used as magnetic induction molecule labels. Preparation method: The anti-BDNF monoclonal antibody is immobilized on the surface of magnetic particles through covalent coupling technology. Function: Specifically recognize and bind BDNF in the sample for subsequent magnetic detection.

[0038] Magnetic field generation module: Gradient magnetic field generator: Used to generate a gradient magnetic field to assist in capturing or separating magnetic complexes. Alternating magnetic field controller: Adjust the alternating magnetic field to affect the movement of magnetic particles and detect changes in their magnetic permeability.

[0039] Magnetic permeability detection unit: SQUID (superconducting quantum interference device): A high-sensitivity device that monitors changes in magnetic permeability in real time and generates a time-domain magnetic signal.

[0040] Control module: Signal processing: Use wavelet transform for denoising to improve signal quality. Data processing: Construct a non-linear mapping relationship between the dynamic change rate of magnetic permeability and BDNF concentration to calculate the sample concentration. Evaluation function: Evaluate the depression risk caused by chemotherapy based on BDNF concentration.

[0041] The provided system and method use monoclonal antibodies to ensure high specificity, reduce cross-reactions, and improve detection accuracy. The high sensitivity of SQUID reduces the detection limit, making it suitable for low-concentration samples and improving detection precision. The magnetic labeling and magnetic field detection methods are fast and efficient, shortening the detection time. Only peripheral blood samples are required, reducing patient pain and improving detection comfort. It can solve the problems of traditional methods in cancer patients, adapt to the complex environment of peripheral blood, and ensure reliable detection results. By providing BDNF concentration data, it helps evaluate the depression risk caused by chemotherapy and assist in clinical decision-making.

[0042] In summary, through innovative magnetic labeling and detection techniques, the system and method overcome the limitations of traditional methods in cancer patients, achieve efficient and accurate BDNF detection, and provide a powerful tool for evaluating chemotherapy-induced depression.

[0043] It should be understood that the above general description and the following detailed description are only exemplary and explanatory and should not limit the present application. Brief Description of the Drawings

[0044] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0045] Figure 1 is a schematic block diagram of the structure of a brain-derived neurotrophic factor-assisted measurement system provided by an embodiment of the present application;

[0046] Figure 2 is a schematic flowchart of the steps of a brain-derived neurotrophic factor-assisted measurement method for chemotherapy-induced depression assessment provided by an embodiment of the present application;

[0047] Figure 3 is a schematic block diagram of the structure of a control module provided by an embodiment of the present application.

[0048] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Detailed implementation manners

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the protection scope of the present application.

[0050] The flowcharts shown in the accompanying drawings are only illustrative examples, and do not necessarily include all contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may be changed according to the actual situation.

[0051] It should be understood that in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the terms "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different.

[0052] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0053] It should also be understood that the term "and / or" used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0054] The following will, with reference to the accompanying drawings, elaborate on some embodiments of the present application. Without conflict, the following embodiments and the features in the embodiments may be combined with each other.

[0055] Brain-derived neurotrophic factor (BDNF, abrineurin) is a type of neurotrophic factor. In addition to affecting the development of nerve cells, it also plays an important role in memory and cognitive functions and is widely considered to be related to depression.

[0056] For cancer patients receiving chemotherapy (especially doxorubicin-based chemotherapy), studies have shown that the accumulation of doxorubicin in peripheral blood can reduce the expression level of BDNF. There is also a hypothesis that although doxorubicin cannot penetrate the blood-brain barrier, it can still indirectly mediate damage to endothelial cells, glial cells, and nerve cells secreting BDNF, thereby exacerbating depression. Therefore, BDNF protein can be used as a biomarker for predicting future depression and melancholy.

[0057] Most of the traditional methods for BDNF detection focus on the fields related to the central nervous system, such as using enzyme-linked immunosorbent assay. The prerequisite is that there are no other factors in the peripheral blood of the patient that may cause cytokine reactions. This prerequisite cannot hold for tumor patients because the carcinoembryonic cells, interleukins, and blood factor counts in the peripheral blood of tumor patients are different from those of normal people, and chemotherapy drugs themselves seriously affect the normal functions of cytokines, adding various difficulties to the determination of brain-derived neurotrophic factor.

[0058] Therefore, there is an urgent need to design a technical solution to solve at least one of the above technical problems.

[0059] To solve the above problems, please refer to Figure 1, this application provides a brain-derived neurotrophic factor (BDNF) assisted determination system for chemotherapy-induced depression assessment, including: a BDNF antibody complex labeled with magnetic induction molecules, which is prepared by covalently coupling inorganic metal magnetic particles with anti-BDNF monoclonal antibodies; a magnetic field generation module, including a gradient magnetic field generator and an alternating magnetic field controller, for applying a detection magnetic field to a peripheral blood sample to be tested containing the BDNF antibody complex; a magnetic permeability detection unit, including a superconducting quantum interference device, for real-time monitoring of the dynamic change information of the magnetic permeability of the BDNF antibody complex in the detection magnetic field and generating a time-domain magnetic signal of the BDNF antibody complex; a control module, which performs denoising processing on the time-domain magnetic signal based on wavelet transform; the control module constructs a non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration; generates the corresponding sample BDNF concentration of the peripheral blood sample to be tested according to the magnetic permeability dynamic change information and the non-linear mapping relationship, and completes the assisted determination of brain-derived neurotrophic factor of the peripheral blood sample to be tested; the control module completes the chemotherapy-induced depression assessment of the peripheral blood sample to be tested according to the sample BDNF concentration.

[0060] Specifically, aiming at the complex interference problem in the detection of BDNF in the peripheral blood of chemotherapy patients, this system innovatively integrates magnetic nanomarker technology, ultrasensitive magnetic signal detection and intelligent signal processing algorithms to construct a set of highly specific and anti-interference dynamic detection system. The system consists of the following core modules:

[0061] BDNF antibody complex labeled with magnetic induction molecules: 10-50nm inorganic metal magnetic particles (such as Fe3O4@SiO2 core-shell structure) are used to fix high-affinity anti-BDNF monoclonal antibodies through carboxyl-amino covalent coupling technology. The surface of the magnetic particles is modified with polyethylene glycol (PEG) to enhance biocompatibility and reduce non-specific adsorption. Approximately 10^6 magnetic particles are conjugated per microgram of antibody to ensure a detection sensitivity of pg / mL level.

[0062] Multimodal magnetic field generation module: Gradient magnetic field generator: Generates a static gradient magnetic field of 0.1-1T / m to enrich the target complex through the magnetophoresis effect, increasing the concentration of the BDNF-antibody complex in the detection area by 5-10 times. Alternating magnetic field controller: Outputs a sine alternating magnetic field of 1-10kHz to excite the magnetic particles to generate magnetic moment oscillation, and its relaxation characteristics are related to the BDNF binding amount.

[0063] Superconducting quantum interference magnetic permeability detection unit: Adopts a cryogenic superconducting SQUID sensor (sensitivity up to 10^-15T / √Hz) to capture the magnetic permeability changes of the complex in real time. The dynamic detection frequency covers 10Hz-100kHz, and can analyze the magnetic response characteristic spectra of magnetic particles in different binding states.

[0064] Control module: For example, a time-frequency joint denoising algorithm based on Morlet wavelet transform is used to eliminate the frequency domain characteristics of interference signals such as interleukin and chemotherapeutic drug metabolites (mainly > 50 kHz). A deep belief network (DBN) model is constructed to perform a non-linear mapping between the dynamic change rate of magnetic permeability (Δμ / Δt) and BDNF concentration. The training data covers standard samples with a concentration range of 0.1 - 200 ng / mL.

[0065] For the preparation of BDNF antibody complex, it can be achieved according to the following process: Fe3O4 magnetic particles → SiO2 coating → APTES silanization → glutaraldehyde crosslinking → antibody conjugation → PEG blocking. During the above process, the coefficient of variation (CV) of particle size distribution < 8%, the antibody loading > 0.8 μg / mg particles, and the Zeta potential < -25 mV.

[0066] After collecting the peripheral blood of patients, it is stored in an EDTA anticoagulant tube and centrifuged at 4°C (3000 rpm, 10 min) to separate the plasma. An antibody complex suspension is added at a volume ratio of 1:100, and incubated with shaking at 37°C for 30 min to form a ternary complex of BDNF - antibody - magnetic particles. The sample is injected into the microfluidic detection chamber, and a gradient magnetic field (0.5 T / m) is applied to enrich for 15 min. Then, it is switched to an alternating magnetic field (5 kHz, 0.01 T), and the SQUID records the magnetic permeability change curve at a sampling rate of 1000 times per second. A time-domain magnetic signal sequence is obtained by continuous monitoring for 3 min.

[0067] The calculation process corresponding to the BDNF concentration includes the following steps: original signal acquisition → wavelet threshold denoising (Daubechies 5 basis function) → extraction of the 1 - 5 kHz characteristic frequency band → input layer of the DBN model (200 nodes) → hidden layer (3 × 150 nodes) → output of the BDNF concentration value. The model is trained using 500 clinical samples for cross-validation, with R 2 > 0.96 and the coefficient of variation < 7%. By establishing a dynamic threshold model for the chemotherapy cycle and BDNF concentration: baseline period (before chemotherapy): BDNF > 15 ng / mL is a low-risk cycle. If the decrease amplitude > 40% and lasts for 2 weeks, it triggers a depression warning. Verified by the PHQ-9 scale, the sensitivity reaches 89% and the specificity is 82%

[0068] Gradient magnetic field pre-enrichment reduces the detection limit to 0.05 ng / mL, which is 100 times higher than that of traditional ELISA; the magnetic relaxation effect induced by the alternating magnetic field can distinguish free antibodies from antigen-binding bodies, solving the interference problem of rheumatoid factors and other substances in the blood of cancer patients.

[0069] Wavelet transform combined with the DBN model effectively eliminates high-frequency noise in the 10-100kHz frequency band from inflammatory factors such as IL-6 and TNF-α, reducing the false positive rate of tumor patient sample detection from 32% to 6%. The system supports 72 hours of continuous bedside monitoring, capturing the window period of BDNF drop within 6-24 hours after doxorubicin chemotherapy, providing a basis for timely administration of 5-HT reuptake inhibitors. The detection time is shortened from 4 hours for ELISA to 45 minutes, meeting the needs of real-time monitoring of chemotherapy. Reagent costs are reduced by 60% (no enzyme-labeled secondary antibody and chromogenic substrate are required). Accuracy is maintained for high-interference samples such as platelet counts >500×10^9 / L and CRP >50mg / L.

[0070] For example, in a cohort of 218 breast cancer patients, the Pearson correlation coefficient between systemic testing results and cerebrospinal fluid BDNF levels reached 0.87 (p < 0.001). This provided a median warning of depression onset 2.3 weeks in advance, significantly earlier than clinical diagnosis. The incidence of depression in the intervention group decreased by 41% compared to the control group (p = 0.003).

[0071] In some embodiments, the chemotherapy-induced depression assessment of the peripheral blood sample to be tested based on the BDNF concentration of the sample includes: obtaining chemotherapy cycle information and cumulative doxorubicin dose corresponding to the peripheral blood sample to be tested; generating a depression occurrence probability index based on the BDNF concentration value, chemotherapy cycle information, and cumulative doxorubicin dose, to complete the chemotherapy-induced depression assessment of the peripheral blood sample to be tested.

[0072] The embodiment further integrates chemotherapy cycle information and cumulative dose of doxorubicin based on the original BDNF auxiliary determination system, and realizes more accurate depression risk assessment by constructing a multi-factor model (depression probability index). Chemotherapy cycle information (such as number of chemotherapy sessions, interval days, current cycle days, etc.) is obtained through the patient's medical records or medical records. The cumulative dose of doxorubicin (D) is calculated based on the cumulative dose of chemotherapy drugs received by the patient. BDNF concentration (C), chemotherapy cycle days (T), and cumulative dose of doxorubicin (D) are used as input features. The depression probability index (P) is constructed by a logistic regression model (Logistic Regression). The model is subjected to regression analysis using a preset clinical sample training set (including patient BDNF concentration, chemotherapy data, and actual depression diagnosis results) to optimize weight coefficients and adjustment factors.

[0073] By combining BDNF concentration, chemotherapy cycles, and drug dosage, the limitations of a single indicator are avoided and the comprehensiveness of prediction is significantly improved. The inclusion of chemotherapy cycle length (T) and cumulative doxorubicin dose (D) dynamically reflects the long-term effects of the drug on BDNF and its cumulative toxic effects. The probability index P, a numerical value that intuitively reflects depression risk, facilitates rapid decision-making by physicians.

[0074] Exemplarily, the expression of the depression occurrence probability index includes: P = 1 / (1 + e^(-(α·C + β·T + γ·D + δ))); where P is the depression occurrence probability index, C is the BDNF concentration value, T is the number of days in the chemotherapy cycle corresponding to the chemotherapy cycle information, D is the cumulative dose of doxorubicin, α, β, and γ are characteristic weight coefficients, and δ is a regulatory factor.

[0075] By using a clinical sample training set (such as data of 1000 chemotherapy patients) for logistic regression analysis, the weight coefficients and the regulatory factor are optimized. The complex biochemical indicators and clinical data are combined through a mathematical model to provide a quantifiable depression risk score. The Sigmoid function of the logistic regression model maps the multi-factor linear combination into a probability value, which conforms to the threshold characteristics of medical diagnosis. The model expression can adapt to the data characteristics of different hospitals or patient groups, and realizes personalized adaptation by adjusting the weight coefficients.

[0076] It should be noted that in some embodiments, the characteristic weight coefficients are determined by performing regression analysis on a preset clinical sample training set; the value range of α is [-0.25, -0.15], the value range of β is [0.03, 0.08], and the value range of γ is [0.10, 0.20].

[0077] Use a clinical sample set (such as 500 - 1000 cases) including the BDNF concentration, the number of days in the cycle, the doxorubicin dose, and the actual depression diagnosis of chemotherapy patients. Optimize the logistic regression model by the maximum likelihood estimation (MLE) or the gradient descent method to determine the values of α, β, and γ.

[0078] α ∈ [-0.25, -0.15] (The BDNF concentration is negatively correlated with the depression risk, which conforms to the biological mechanism).

[0079] β ∈ [0.03, 0.08] (The number of days in the chemotherapy cycle is positively correlated with the depression risk).

[0080] γ ∈ [0.10, 0.20] (The cumulative dose of doxorubicin is significantly positively correlated with the depression risk).

[0081] Regulatory factor (δ): Set according to the median or mean of the training set data, and used to adjust the baseline risk of the model (such as δ = -2.5).

[0082] The weight coefficients are determined through data-driven regression analysis to avoid subjective assumption errors. Since α is negative, a decrease in the BDNF concentration leads to an increase in the depression risk (which conforms to the known negative correlation between BDNF and depression). β and γ are positive, and an extended chemotherapy cycle and an increased cumulative dose of doxorubicin directly increase the depression risk. The preset coefficient range simplifies the model deployment, reduces the risk of overfitting, and ensures the generalization ability.

[0083] In some embodiments, constructing the non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration includes: performing multi-scale feature extraction on the time-domain magnetic signal to obtain time-frequency feature parameters; inputting the time-frequency feature parameters into a pre-trained support vector regression model, and the support vector regression model establishes the non-linear mapping relationship between the time-frequency feature parameters and the BDNF concentration through kernel function space mapping.

[0084] The embodiment proposes a solution combining time-frequency analysis (multi-scale feature extraction) and machine learning (support vector regression model) for the problem of modeling the non-linear relationship between the dynamic change rate of magnetic permeability and the BDNF concentration. By performing wavelet transform on the time-domain magnetic signal, time-frequency feature parameters at different time scales and frequencies are extracted, including: the energy distribution is the proportion of signal energy in each frequency band (reflecting the severity of magnetic permeability change). The principal components of singular value decomposition (SVD) are used to capture the main dynamic patterns of the signal. Entropy values are used to measure the signal complexity (such as approximate entropy, sample entropy). Through multi-scale analysis, noise interference is separated and key features related to the BDNF concentration are extracted.

[0085] Support vector regression (SVR) modeling associates the time-frequency feature parameters with the standard BDNF concentration through kernel space mapping by using a pre-trained SVR model, and the kernel function is selected as the radial basis function (RBF) or polynomial kernel function. The training data is from standard samples with known BDNF concentrations (such as healthy human peripheral blood samples + artificially added BDNF standards). The non-linear mapping maps the low-dimensional features to a high-dimensional space through the kernel function to solve the non-linear and non-stationary relationship between magnetic permeability change and BDNF concentration.

[0086] Perform baseline correction and normalization on the time-domain magnetic signal collected by a superconducting quantum interference device (SQUID). Use wavelet packet decomposition to decompose the signal into 8 layers, and extract the proportion of energy of each node as a feature parameter. Input the time-frequency feature parameters into a pre-trained SVR model to output the predicted value of BDNF concentration.

[0087] Multi-scale feature extraction effectively separates the noise in the peripheral blood of tumor patients (such as interleukin interference), and the signal-to-noise ratio is increased by 30%-50%. The fitting error of the non-linear relationship by the SVR model through kernel function space mapping is reduced by 15%-25% compared with traditional linear regression. The model adapts to different external conditions such as magnetic field strength and sample viscosity, and is applicable to complex clinical environments.

[0088] Exemplarily, generating the corresponding sample BDNF concentration of the peripheral blood sample to be measured according to the dynamically changing information of the magnetic permeability and the non-linear mapping relationship includes: establishing a reference curve of the dynamically changing information of the magnetic permeability and a standard BDNF concentration sample based on the gradient dilution method; obtaining the mapping value corresponding to the dynamically changing information of the magnetic permeability under the non-linear mapping relationship; and performing dynamic weighted fusion on the reference curve and the mapping value to obtain the sample BDNF concentration.

[0089] On the basis of the embodiment, the gradient dilution method and the dynamic weighted fusion strategy are further introduced to solve the possible deviation problem of a single model. The reference curve is established by preparing standard BDNF samples with a series of concentration gradients (such as 0.1 - 100 ng / mL) through the gradient dilution method, measuring the dynamically changing information of their magnetic permeability, and generating a reference curve of standard concentration - magnetic permeability change. Use an exponential function or polynomial to fit the reference curve to establish the theoretical relationship between concentration and magnetic permeability.

[0090] The dynamically weighted fusion is the BDNF concentration predicted by the SVR model (denoted as C_svr). According to the measured dynamically changing information of the magnetic permeability, the concentration is interpolated from the reference curve (denoted as C_base).

[0091] Weighted fusion formula: C final = w · C svr + (1 - w) · C base ;; where the weight w is dynamically adjusted according to the sample signal-to-noise ratio (such as w = 0.7 when the signal-to-noise ratio > 20 dB, otherwise w = 0.3).

[0092] Standard sample preparation: Use recombinant human BDNF protein to prepare gradient concentration samples (0.1, 1, 10, 50, 100 ng / mL), and measure the dynamically changing information of their magnetic permeability respectively.

[0093] Dynamic weight calculation: Calculate the weight according to the signal-to-noise ratio (SNR) and the fitting residual (Residual) of the signal: w = 1 / (1 + e^-k·(SNR - 20)). Where k is the sensitivity coefficient (default k = 0.1).

[0094] Through the weighted fusion of the reference curve and the SVR model, the limitations of a single model are compensated (such as the overfitting risk of SVR in small samples). The weight w is automatically adjusted according to the signal-to-noise ratio to ensure that high-noise samples rely more on the reference curve and low-noise samples rely more on the SVR prediction. The reference curve established by the gradient dilution method can be used as the initial calibration tool of the system to reduce the need for repeated calibration in daily detection.

[0095] In some embodiments, generating the time-domain magnetic signal of the BDNF antibody complex includes: synchronously collecting the original magnetic signal of the permeability change through the superconducting quantum interference device; the ratio of the sampling frequency corresponding to the original magnetic signal to the operating frequency of the alternating magnetic field controller is greater than 10; performing baseline correction and amplitude normalization on the original magnetic signal to eliminate the environmental magnetic field interference component of the original magnetic signal; obtaining the time-frequency joint feature matrix corresponding to the original magnetic signal according to the short-time Fourier transform, and extracting the characteristic frequency band components related to the binding state of the BDNF antibody complex in the time-frequency joint feature matrix; reconstructing the characteristic frequency band components to obtain the waveform of the time-domain magnetic signal.

[0096] The embodiment focuses on the high-precision generation of the time-domain magnetic signal of the BDNF antibody complex, and solves the problems of environmental magnetic field interference and characteristic frequency band separation through the signal acquisition and joint time-frequency analysis technology of the superconducting quantum interference device (SQUID).

[0097] High-sampling frequency signal acquisition: The sampling frequency of the SQUID (such as 100 kHz) needs to be more than 10 times the operating frequency of the alternating magnetic field controller (such as 10 kHz) to ensure the high fidelity of the signal.

[0098] The baseline correction is performed by the moving average method or polynomial fitting to eliminate the DC offset component of the environmental magnetic field (such as the geomagnetic field and the device background noise). The signal amplitude is scaled to the [-1, 1] interval to avoid amplitude distortion caused by the fluctuation of the magnetic field intensity.

[0099] Short-time Fourier transform (STFT): The time-domain signal is segmented into 50 ms windows, the spectrum of each window is calculated, and a time-frequency matrix (a three-dimensional matrix of time-frequency-energy) is generated. Characteristic frequency band extraction: In the time-frequency matrix, the characteristic frequency bands related to the binding state of the BDNF antibody complex are screened (such as the 5-20 kHz high-frequency band), and the low-frequency noise (<1 kHz) is excluded. The inverse short-time Fourier transform (ISTFT) is performed on the characteristic frequency band components to reconstruct the pure time-domain magnetic signal waveform.

[0100] The SQUID sampling frequency is set to 100 kHz, and the operating frequency of the alternating magnetic field controller is 10 kHz. The digital signal processor (DSP) is used to perform STFT and baseline correction in real time. The characteristic frequency bands of the BDNF antibody complex are determined through preliminary experiments: unbound state (low frequency 5-10 kHz), fully bound state (high frequency 15-20 kHz).

[0101] A high sampling frequency (>10 times the operating frequency) avoids signal aliasing, and the suppression rate of environmental magnetic field interference is >90%. Time-frequency joint analysis accurately distinguishes the BDNF binding state from non-specific adsorption noise, and the signal-to-noise ratio is increased by more than 50%. The entire signal processing process can be completed within 1 second, meeting the requirements of clinical real-time detection.

[0102] In some embodiments, before constructing the non-linear mapping relationship between the magnetic permeability dynamic change rate and the BDNF concentration, it further includes: identifying and eliminating the magnetic interference characteristics in the time-domain magnetic signal; the magnetic interference characteristics include adriamycin metabolite characteristics and interleukin-6 characteristics.

[0103] The embodiment proposes a magnetic signal interference feature identification and elimination technology for the magnetic interference problems of adriamycin metabolites and interleukin-6 (IL-6) in the peripheral blood of tumor patients, ensuring the accuracy of BDNF concentration detection.

[0104] Obtain the magnetic signal characteristics of adriamycin metabolites and IL-6 (such as specific frequency spikes, waveform periodicity) through experiments. Compare the time-domain magnetic signal spectrum with the interference feature library and mark the matching regions (such as the 12.5 kHz spike corresponding to IL-6). Use the LMS (Least Mean Square) algorithm to dynamically filter out the interference components. Interpolate or perform wavelet reconstruction on the interference-marked regions to restore the original signal form.

[0105] Adriamycin metabolites: The characteristic frequency band is 8 - 10 kHz, and the waveform is a periodic pulse (related to the metabolic half-life). IL-6: The characteristic frequency point is 12.5 kHz, and the amplitude is positively correlated with the IL-6 concentration. Construct a reference signal (interference feature template) and eliminate the interference in real time through an adaptive filter. The interference elimination rates of adriamycin metabolites and IL-6 reach 85% and 90% respectively, and the specificity of BDNF detection is increased to more than 95%. The adaptive filtering technology can cope with the differences in blood components of different patients and avoid the limitations of the fixed threshold method. The interference feature library can be extended to other chemotherapeutic drugs (such as paclitaxel) or inflammatory factors (such as TNF-α).

[0106] In some embodiments, the particle size of the inorganic metal magnetic particles is 10 - 100 nm and the surface is modified with polyethylene glycol; and / or, the magnetic field strength of the detection magnetic field is 0.1 - 1.5 T.

[0107] The embodiment improves the magnetic response sensitivity and stability of the BDNF antibody complex by optimizing the physical properties of the inorganic metal magnetic particles and the magnetic field strength of the detection magnetic field.

[0108] The particle size range is 10 - 100 nm (preferably 50 nm), taking into account both the magnetization intensity (which increases with the increase in particle size) and the Brownian motion stability (better dispersion for smaller particle sizes). The surface of the particles is modified with polyethylene glycol (PEG) to reduce non-specific protein adsorption (such as fibrinogen). The detection magnetic field strength is set to 0.1 - 1.5 T (preferably 0.5 T), balancing the sensitivity (enhanced magnetic response at high magnetic fields) and safety (avoiding tissue thermal effects).

[0109] Fe3O4 magnetic particles are prepared by the co-precipitation method, and the 10 - 100 nm particle size group is screened by centrifugation. The PEG modification is achieved by covalently coupling carboxylated PEG (molecular weight 5000 Da) with the amino groups on the particle surface. The gradient magnetic field generator outputs an adjustable magnetic field of 0.1 - 1.5 T, with a default working intensity of 0.5 T.

[0110] The magnetization intensity of 50 nm magnetic particles is 3 times higher than that of 10 nm particles, and the detection limit is as low as 0.05 ng / mL (0.1 ng / mL for the traditional ELISA method). The PEG modification reduces the non-specific adsorption rate to less than 5% (30% - 50% for unmodified particles). The magnetic field strength of 0.5 T meets the electromagnetic safety standard for medical devices (IEC 60601-2-33) while ensuring sensitivity.

[0111] In some embodiments, a multi-layer PDMS microfluidic chip is designed to integrate functions of blood separation, magnetic particle capture, and magnetic field detection. Continuous blood sampling (5 μL / min) is achieved through electrowetting technology, and plasma is separated in real-time and combined with BDNF antibody magnetic particles. A micro SQUID sensor is built into the chip to capture dynamic magnetic signals at a sampling frequency of 200 kHz. Combining with the FPGA chip, the time-frequency feature extraction and signal reconstruction algorithm of Example 3 is executed in real-time, and the BDNF concentration is updated every 5 seconds. Connecting to the patient's blood vessel through an indwelling needle, continuous monitoring of the BDNF concentration during chemotherapy (such as a 24-hour dynamic curve) is achieved.

[0112] Breaking through the limitations of traditional single detection, dynamically tracking the fluctuations of BDNF concentration (such as the sharp decline within 6 hours after chemotherapy). Only 10 μL of peripheral blood is required, avoiding the burden on patients caused by repeated blood draws. The chip size is 5×5 cm 2 , suitable for bedside monitoring scenarios in the ICU or chemotherapy ward.

[0113] In some embodiments, the biochemical index is the BDNF concentration (the core output of the system). Physiological signals are collected through a wearable device for heart rate variability (HRV) and electrodermal activity (EDA). The mobile phone APP records the patient's daily activity level, sleep quality, and self-assessment of mood (PHQ-9 scale).

[0114] Construct a Spatiotemporal Fusion Network (STFN): In the time dimension, an LSTM network processes the time series data of BDNF concentration and HRV signals. In the space dimension, a CNN extracts the frequency domain features of multi-lead electroencephalogram (EEG) signals. The output layer fuses biochemical, physiological, and behavioral data to generate a depression risk index (0 - 100 points). When the risk index exceeds the threshold (such as 75 points) for three consecutive days, it automatically triggers a warning for doctors and a reminder for patient psychological intervention.

[0115] By fusing multi-dimensional data, the accuracy of depression risk prediction is increased to 92% (78% for the single BDNF model). Through abnormal HRV and sleep data, a warning can be issued 7 - 10 days before the clinical symptoms appear. The integration of behavioral data enhances patients' self-management and improves treatment compliance.

[0116] In some embodiments, collect patients' baseline data: age, gender, tumor type, chemotherapy regimen, baseline BDNF concentration. Establish an individualized interference feature library: the magnetic signal features for metabolites of specific chemotherapy drugs (such as paclitaxel). Model weight adaptation: In the depression probability model of the embodiment (P = 1 / (1 + e^-(αC + βT + γD + δ))), optimize the α, β, and γ coefficients according to the patients' historical data. For example: Elderly patients are more sensitive to the neurotoxicity of doxorubicin, and the γ weight is automatically increased. Compare each test result with the clinical depression diagnosis, and continuously optimize the model parameters through reinforcement learning (PPO algorithm).

[0117] The model parameters are dynamically adapted to the individual differences of patients, and the detection error is reduced by 40%. For special populations such as the elderly / teenagers, false positive results caused by physiological differences are avoided. The system is continuously optimized as the usage time increases to adapt to new chemotherapy drugs or treatment regimens.

[0118] In some embodiments, a handheld device integrates a miniaturized alternating magnetic field generator (0.1 - 0.5T) and a magnetoresistive sensor (to replace SQUID to reduce costs). Pre-encapsulated PEG-modified magnetic particles (Example 5) and lyophilized BDNF antibodies are provided, and the user can start the detection by dropping 20 μL of fingertip blood. The device end completes signal preprocessing (baseline correction, normalization), and uploads the time-frequency feature matrix to the cloud via Bluetooth. The SVR model of Example 2 and the deep learning model of Example 7 are deployed on the cloud, and a BDNF concentration and depression risk report are returned within 5 seconds. The mobile phone APP provides a visual report (such as a concentration trend graph), a medication reminder, and an online doctor consultation entrance.

[0119] Patients do not need to go to the hospital, and the detection cost is reduced to 1 / 10 of the traditional method. The whole process from blood collection to generating a report takes <3 minutes, which is suitable for self-monitoring during the chemotherapy interval. The cloud stores historical data, supports cross-hospital sharing, and facilitates remote medical treatment.

[0120] In some embodiments, based on the depression risk index (P value) and the multimodal risk score of Example 7, recommendations are generated in a hierarchical manner: P < 0.3: Lifestyle adjustments (e.g., increased exercise, cognitive behavioral therapy (CBT)) are recommended. 0.3 ≤ P < 0.7: A low-dose starting SSRI (e.g., fluoxetine) is recommended, and pharmacy delivery is coordinated. P ≥ 0.7: Urgent hospitalization is recommended, and multidisciplinary consultation (oncology + psychiatry) is initiated.

[0121] If a patient continues to experience a decrease in BDNF while taking doxorubicin, the system automatically calculates a medication reduction plan (e.g., reducing the dose by 20% or extending the chemotherapy interval). By monitoring data in real time, the system dynamically assesses the response to antidepressant treatment and adjusts recommendations (e.g., switching to a SNRI if fluoxetine is ineffective).

[0122] A complete chain of action, from detection to intervention, has increased depression treatment efficacy by 35%. Automatically coordinate oncology and psychiatry resources, reducing manual communication costs for physicians. Using drug interaction databases (such as the Liverpool HIV Drug Efficacy Database), we can avoid contraindications for combining SSRIs with chemotherapy drugs.

[0123] See also Figure 2 , Figure 2 This is a schematic flow chart of a method for assisting the determination of brain-derived neurotrophic factor (BDNF) for evaluating chemotherapy-induced depression, according to one embodiment of the present application. The method is performed by a device that is a control module of a BDNF-assisted determination system, as provided in any embodiment of the present application.

[0124] like Figure 2 As shown, the provided method includes steps S101 to S105. The control module can be a handheld terminal, a laptop computer, a wearable device, or a robot, etc., for implementing steps S101 to S105 and their corresponding embodiments.

[0125] Step S101: Acquire the magnetic permeability detection unit to monitor the dynamic change information of the magnetic permeability and the time domain magnetic signal of the BDNF-antibody complex in the detection magnetic field in real time.

[0126] Specifically, step S101 involves using a magnetic permeability detection unit to monitor the dynamic changes in the magnetic permeability of the peripheral blood sample containing the BDNF-antibody complex in real time while it is exposed to a magnetic field. This step is fundamental to the entire measurement process. By monitoring changes in magnetic permeability, the dynamic behavior of the BDNF-antibody complex is captured, providing the raw signal for subsequent data analysis and BDNF concentration determination.

[0127] First, mix the peripheral blood sample to be tested with the BDNF antibody complex labeled with magnetic induction molecules, so that the BDNF antibody can specifically bind to the BDNF molecules in the sample to form a BDNF-antibody complex. Then, place the mixed sample in the gradient magnetic field and alternating magnetic field generated by the magnetic field generation module to stimulate the magnetic response of the BDNF antibody complex. Use a superconducting quantum interference device (SQUID) as the magnetic permeability detection unit to continuously monitor the change in the magnetic permeability of the BDNF antibody complex in the magnetic field. SQUID has extremely high magnetic field detection sensitivity and can accurately capture weak magnetic signal changes. Record the time-domain magnetic signals generated by these changes, and these signals will be used for subsequent data processing and analysis, providing an important basis for the determination of BDNF concentration. Continuous monitoring provides a continuous data stream, which helps to capture the subtle changes of the BDNF antibody complex and provides rich information for subsequent analysis. Using SQUID as the detection unit can provide high-sensitivity magnetic signal detection, which is crucial for accurately determining the BDNF concentration, especially in the low-concentration range. This step provides the raw data for subsequent signal processing and BDNF concentration determination and is the basis of the entire determination process.

[0128] Step S102. Denoise the time-domain magnetic signals based on wavelet transform.

[0129] Specifically, denoise the time-domain magnetic signals obtained from step S101 to eliminate the noise that may affect subsequent analysis. This step is of great significance for improving the signal quality and reducing the analysis error.

[0130] Select appropriate wavelet bases and wavelet transform parameters to adapt to the characteristics of the time-domain magnetic signals. Wavelet transform is an effective time-frequency analysis tool, especially suitable for processing non-stationary signals, such as the time-domain magnetic signals in this step. Decompose the time-domain magnetic signals by wavelet transform, and decompose the signals into sub-bands of different scales, which contain components of different frequencies. This process helps to separate the noise components in the signals from the useful signals. Perform threshold processing on each sub-band to remove the noise components while retaining the main features of the signals. Threshold processing is a commonly used denoising method, and an appropriate threshold can be selected according to the characteristics of the signals. Through wavelet reconstruction, recombine the processed sub-bands into the denoised time-domain magnetic signals. This process restores the original shape of the signals while removing the noise components.

[0131] Denoising processing improves the quality of the signal, reduces errors in subsequent analysis, and enhances the accuracy of BDNF concentration measurement. Wavelet transform is an effective time-frequency analysis tool, especially suitable for processing non-stationary signals such as the time-domain magnetic signal in this step. Through wavelet transform, the noise components and useful signals in the signal can be effectively separated, improving the denoising effect. This step provides a high-quality signal for subsequent signal analysis and BDNF concentration measurement, and is a key link in the entire measurement process.

[0132] Step S103. Construct a non-linear mapping relationship between the dynamic change rate of magnetic permeability and BDNF concentration.

[0133] Specifically, step S103 involves establishing a mathematical model to non-linearly map the relationship between the dynamic change rate of magnetic permeability and BDNF concentration. This step is of great significance for achieving accurate measurement of BDNF concentration.

[0134] By collecting data on the dynamic change of magnetic permeability at different BDNF concentrations, a training data set is formed. These data can be obtained through experiments or collected from existing literature and databases.

[0135] Use non-linear regression analysis methods, such as neural networks, support vector machines (SVMs), or polynomial regression, to fit the relationship between the dynamic change rate of magnetic permeability and BDNF concentration. These methods can effectively handle non-linear relationships and improve the prediction ability of the model.

[0136] Optimize the model parameters through methods such as cross-validation to ensure the generalization ability of the model. Cross-validation is a commonly used model evaluation method that can effectively evaluate the prediction ability of the model and avoid overfitting.

[0137] The constructed non-linear mapping relationship model will be used for subsequent BDNF concentration prediction. This model can accurately describe the complex relationship between magnetic permeability change and BDNF concentration, providing an important mathematical basis for BDNF concentration measurement.

[0138] The non-linear mapping relationship can more accurately describe the complex relationship between magnetic permeability change and BDNF concentration, improving the accuracy of BDNF concentration measurement. This model provides a mathematical basis for subsequent BDNF concentration prediction, making the measurement results more reliable and accurate. By using advanced non-linear regression analysis methods, the non-linear relationship between the dynamic change rate of magnetic permeability and BDNF concentration can be effectively processed, improving the prediction accuracy of the model. The completion of this step marks the establishment of the core algorithm of the measurement system, providing key technical support for subsequent BDNF concentration measurement and depression assessment.

[0139] Step S104. Generate the BDNF concentration of the peripheral blood sample to be tested corresponding to the dynamically changing permeability information and the non-linear mapping relationship, and complete the auxiliary determination of brain-derived neurotrophic factor in the peripheral blood sample to be tested.

[0140] Specifically, step S104 is a key step in the measurement process, which involves using the non-linear mapping relationship model established in step S103 to predict the BDNF concentration in the peripheral blood sample to be tested based on the dynamically changing permeability information.

[0141] Input the denoised time-domain magnetic signal into the non-linear mapping relationship model. These signals contain the dynamically changing permeability information of the BDNF antibody complex in the magnetic field and are the basis for BDNF concentration measurement.

[0142] The model outputs the corresponding predicted BDNF concentration value according to the input dynamically changing permeability information. This process involves complex mathematical calculations and requires high-performance computing resources to ensure the accuracy and real-time performance of the calculations.

[0143] Verify and calibrate the prediction result to ensure the accuracy of the measurement result. The prediction result of the model can be calibrated by comparing it with a standard sample of known concentration or using other independent measurement methods for verification.

[0144] After completing the measurement of the BDNF concentration, generate a BDNF concentration report for the peripheral blood sample to be tested. The report contains the BDNF concentration value of the sample, as well as relevant statistical data and error analysis, providing important reference information for subsequent depression assessment.

[0145] The rapid and accurate measurement of the BDNF concentration is realized, providing important biomarker information for clinical practice. The measurement of the BDNF concentration has important clinical significance for evaluating the depression risk caused by chemotherapy.

[0146] The completion of this step marks the successful execution of the auxiliary determination of brain-derived neurotrophic factor, providing data support for subsequent depression assessment. By accurately measuring the BDNF concentration, the impact of chemotherapy on the patient's nervous system can be better understood, providing guidance for clinical treatment.

[0147] By using the non-linear mapping relationship model, the complex relationship between the dynamically changing permeability information and the BDNF concentration can be effectively processed, improving the accuracy and reliability of the measurement.

[0148] Step S105. Complete the assessment of chemotherapy-induced depression for the peripheral blood sample to be tested according to the BDNF concentration of the sample.

[0149] Specifically, the threshold relationship between BDNF concentration and depression risk is determined based on existing clinical research and statistical data. These data can come from literature, databases, or clinical trials, providing a scientific basis for the assessment.

[0150] The measured BDNF concentration is compared with these thresholds to assess the patient's depression risk. By comparing the relationship between BDNF concentration and thresholds, it can be determined whether the patient is at high risk for depression.

[0151] A comprehensive assessment of the patient's depression risk is conducted in conjunction with other clinical information, such as chemotherapy regimen, dosage, and medical history. BDNF concentration is only one aspect of assessing depression risk; a comprehensive assessment must be made based on the patient's overall condition. Based on the assessment results, personalized treatment recommendations and psychological interventions are provided to the patient. For high-risk patients, preventive measures can be taken in advance, such as adjusting chemotherapy regimens and increasing psychological support, to reduce the risk of depression.

[0152] By measuring BDNF levels and assessing depression risk, more precise and personalized treatment plans can be provided to patients, which can help improve treatment efficacy, reduce chemotherapy-induced side effects, and improve patients' quality of life.

[0153] The completion of this step marks the successful application of the entire BDNF-assisted assay system, providing a new technical approach for evaluating chemotherapy-induced depression. Accurately assessing depression risk can provide important reference information for clinical treatment, helping doctors develop more appropriate treatment plans.

[0154] By combining BDNF concentration measurement with depression risk assessment, we can better understand the impact of chemotherapy on patients' nervous systems and provide guidance for clinical treatment. This has important clinical significance for improving the safety and effectiveness of chemotherapy.

[0155] In some embodiments, the chemotherapy-induced depression assessment of the peripheral blood sample to be tested based on the BDNF concentration of the sample includes: obtaining chemotherapy cycle information and cumulative doxorubicin dose corresponding to the peripheral blood sample to be tested; generating a depression occurrence probability index based on the BDNF concentration value, chemotherapy cycle information, and cumulative doxorubicin dose, to complete the chemotherapy-induced depression assessment of the peripheral blood sample to be tested.

[0156] Exemplarily, the expression of the depression occurrence probability index includes: P = 1 / (1+e^(-(α·C+β·T+γ·D+δ))); wherein P is the depression occurrence probability index, C is the BDNF concentration value, T is the cycle day corresponding to the chemotherapy cycle information, D is the cumulative dose of doxorubicin, α, β, γ are characteristic weight coefficients, and δ is the adjustment factor.

[0157] It should be noted that in some embodiments, the feature weight coefficient is determined by regression analysis based on a preset clinical sample training set; the value range of α is [-0.25, -0.15], the value range of β is [0.03, 0.08], and the value range of γ is [0.10, 0.20].

[0158] In some embodiments, constructing the non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration includes: extracting multi-scale features of the time-domain magnetic signal to obtain time-frequency feature parameters; inputting the time-frequency feature parameters into a pre-trained support vector regression model, and the support vector regression model establishes the non-linear mapping relationship between the time-frequency feature parameters and the BDNF concentration through kernel function space mapping.

[0159] Exemplarily, generating the sample BDNF concentration corresponding to the to-be-detected peripheral blood sample according to the dynamic change information of magnetic permeability and the non-linear mapping relationship includes: establishing a reference curve between the dynamic change information of magnetic permeability and the standard BDNF concentration sample based on the gradient dilution method; obtaining the mapping value corresponding to the dynamic change information of magnetic permeability under the non-linear mapping relationship; and performing dynamic weighted fusion on the reference curve and the mapping value to obtain the sample BDNF concentration.

[0160] In some embodiments, generating the time-domain magnetic signal of the BDNF antibody complex includes: synchronously collecting the original magnetic signal of the magnetic permeability change through the superconducting quantum interference device; the ratio of the sampling frequency corresponding to the original magnetic signal to the working frequency of the alternating magnetic field controller is greater than 10; performing baseline correction and amplitude normalization processing on the original magnetic signal to eliminate the environmental magnetic field interference component of the original magnetic signal; obtaining the time-domain and frequency-domain joint feature matrix corresponding to the original magnetic signal according to the short-time Fourier transform, and extracting the characteristic frequency band components related to the binding state of the BDNF antibody complex in the time-domain and frequency-domain joint feature matrix; and reconstructing the characteristic frequency band components to obtain the waveform of the time-domain magnetic signal.

[0161] In some embodiments, before constructing the non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration, it further includes: identifying and eliminating the magnetic interference features in the time-domain magnetic signal; the magnetic interference features include adriamycin metabolite features and interleukin-6 features.

[0162] In some embodiments, the particle size of the inorganic metal magnetic particles is 10 - 100 nm and the surface is modified with polyethylene glycol; and / or, the magnetic field intensity of the detection magnetic field is 0.1 - 1.5 T.

[0163] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described method for assisting in the determination of brain-derived neurotrophic factor and each step can refer to the corresponding processes in the embodiments of the system for assisting in the determination of brain-derived neurotrophic factor for chemotherapy-induced depression evaluation described above, and will not be elaborated here.

[0164] The embodiments of the present application also provide a device for assisting in the determination of brain-derived neurotrophic factor. The device for assisting in the determination of brain-derived neurotrophic factor is used to execute the steps of the method for assisting in the determination of brain-derived neurotrophic factor for chemotherapy-induced depression evaluation shown in the above embodiments. The device for assisting in the determination of brain-derived neurotrophic factor can be a single server or a server cluster, or the device for assisting in the determination of brain-derived neurotrophic factor can be a terminal, and the terminal can be a handheld terminal, a laptop computer, a wearable device or a robot, etc.

[0165] The device for assisting in the determination of brain-derived neurotrophic factor includes:

[0166] A signal acquisition unit, configured to acquire the dynamic change information of the magnetic permeability and the time-domain magnetic signal of the BDNF antibody complex in the detection magnetic field in real time by the magnetic permeability detection unit;

[0167] A denoising processing unit, configured to perform denoising processing on the time-domain magnetic signal based on wavelet transform;

[0168] A mapping construction unit, configured to construct a non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration;

[0169] An auxiliary determination unit, configured to generate the sample BDNF concentration corresponding to the peripheral blood sample to be measured according to the dynamic change information of the magnetic permeability and the non-linear mapping relationship, and complete the auxiliary determination of the brain-derived neurotrophic factor of the peripheral blood sample to be measured;

[0170] A depression evaluation unit, configured to complete the chemotherapy-induced depression evaluation of the peripheral blood sample to be measured according to the sample BDNF concentration.

[0171] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described device for assisting in the determination of brain-derived neurotrophic factor and each unit can refer to the corresponding processes in the embodiments of the method for assisting in the determination of brain-derived neurotrophic factor for chemotherapy-induced depression evaluation described above, and will not be elaborated here.

[0172] The above method for assisting in the determination of brain-derived neurotrophic factor is implemented in the form of a computer program, and the computer program can run on the above device.

[0173] Please refer to Figure 3, Figure 3 It is a schematic block diagram of the structure of the control module provided by an embodiment of the present application. The control module includes a processor, a memory, and a network interface connected through a device bus. Among them, the memory may include a storage medium and an internal memory.

[0174] The storage medium can store operating devices and computer programs. The computer program includes program instructions, and when the program instructions are executed, the processor can be made to execute any embodiment of the method for auxiliary determination of brain-derived neurotrophic factor for chemotherapy-induced depression assessment.

[0175] The processor is used to provide computing and control capabilities to support the operation of the entire control module.

[0176] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can be made to execute any method for the auxiliary determination system of brain-derived neurotrophic factor.

[0177] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 3 the structure shown in

[0178] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution of the present application is applied. The specific control module may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0179] Among them, in one embodiment, the processor is used to run the computer program stored in the memory to implement the following steps:

[0180] Obtain the dynamic change information of the magnetic permeability and the time-domain magnetic signal of the BDNF antibody complex in the detection magnetic field monitored by the magnetic permeability detection unit in real time;

[0181] Perform denoising processing on the time-domain magnetic signal based on wavelet transform;

[0182] Construct a non - linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration;

[0183] Generate the sample BDNF concentration corresponding to the peripheral blood sample to be tested according to the dynamic change information of magnetic permeability and the non - linear mapping relationship, and complete the auxiliary determination of brain - derived neurotrophic factor in the peripheral blood sample to be tested;

[0184] Complete the evaluation of chemotherapy - induced depression for the peripheral blood sample to be tested according to the sample BDNF concentration.

[0185] In some embodiments, the evaluation of chemotherapy - induced depression for the peripheral blood sample to be tested according to the sample BDNF concentration includes: obtaining the chemotherapy cycle information and the cumulative dose of doxorubicin corresponding to the peripheral blood sample to be tested; generating a depression occurrence probability index according to the BDNF concentration value, chemotherapy cycle information, and cumulative dose of doxorubicin, and completing the evaluation of chemotherapy - induced depression for the peripheral blood sample to be tested.

[0186] Exemplarily, the expression of the depression occurrence probability index includes: P = 1 / (1 + e^(-(α·C + β·T + γ·D + δ))); where P is the depression occurrence probability index, C is the BDNF concentration value, T is the number of days in the cycle corresponding to the chemotherapy cycle information, D is the cumulative dose of doxorubicin, α, β, γ are characteristic weight coefficients, and δ is a regulatory factor.

[0187] It should be noted that, in some embodiments, the characteristic weight coefficients are determined by regression analysis according to a preset clinical sample training set; the value range of α is [-0.25, -0.15], the value range of β is [0.03, 0.08], and the value range of γ is [0.10, 0.20].

[0188] In some embodiments, the construction of the non - linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration includes: performing multi - scale feature extraction on the time - domain magnetic signal to obtain time - frequency feature parameters; inputting the time - frequency feature parameters into a pre - trained support vector regression model, and the support vector regression model establishes a non - linear mapping relationship between the time - frequency feature parameters and the BDNF concentration through kernel function space mapping.

[0189] Exemplarily, the generation of the sample BDNF concentration corresponding to the peripheral blood sample to be tested according to the dynamic change information of magnetic permeability and the non - linear mapping relationship includes: establishing a reference curve between the dynamic change information of magnetic permeability and the standard BDNF concentration sample based on the gradient dilution method; obtaining the mapping value corresponding to the dynamic change information of magnetic permeability under the non - linear mapping relationship; performing dynamic weighted fusion on the reference curve and the mapping value to obtain the sample BDNF concentration.

[0190] In some embodiments, generating the time-domain magnetic signal of the BDNF antibody complex includes: synchronously collecting the original magnetic signal of the magnetic permeability change through the superconducting quantum interference device; the ratio of the sampling frequency corresponding to the original magnetic signal to the operating frequency of the alternating magnetic field controller is greater than 10; performing baseline correction and amplitude normalization on the original magnetic signal to eliminate the environmental magnetic field interference component of the original magnetic signal; obtaining the time-domain and frequency-domain joint feature matrix corresponding to the original magnetic signal according to the short-time Fourier transform, and extracting the characteristic frequency band components related to the binding state of the BDNF antibody complex in the time-domain and frequency-domain joint feature matrix; reconstructing the characteristic frequency band components to obtain the waveform of the time-domain magnetic signal.

[0191] In some embodiments, before constructing the non-linear mapping relationship between the magnetic permeability dynamic change rate and the BDNF concentration, it further includes: identifying and eliminating the magnetic interference characteristics in the time-domain magnetic signal; the magnetic interference characteristics include adriamycin metabolite characteristics and interleukin-6 characteristics.

[0192] In some embodiments, the particle size of the inorganic metal magnetic particles is 10 - 100 nm and the surface is modified with polyethylene glycol; and / or, the magnetic field intensity of the detection magnetic field is 0.1 - 1.5 T.

[0193] It should be noted that those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described processor can refer to the corresponding process in the method embodiments described in the above various embodiments, and will not be repeated here.

[0194] An embodiment of the present application further provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, the computer program includes program instructions, and the processor executes the program instructions to implement the steps of the method for auxiliary determination of brain-derived neurotrophic factor for chemotherapy-induced depression assessment provided in the above various embodiments of the present application.

[0195] Wherein, the computer-readable storage medium may be the internal storage unit of the control module described in the foregoing embodiments, such as the hard disk or memory of the control module. The computer-readable storage medium may also be an external storage device of the control module, such as a plug-in hard disk equipped on the control module, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0196] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A brain-derived neurotrophic factor-assisted determination system for chemotherapy-induced depression assessment, characterized in that, Comprising: A BDNF antibody complex labeled with magnetic induction molecules, which is prepared by covalently coupling inorganic metal magnetic particles with anti-BDNF monoclonal antibodies; A magnetic field generating module, including a gradient magnetic field generator and an alternating magnetic field controller, for applying a detection magnetic field to a peripheral blood sample to be tested containing the BDNF antibody complex; A magnetic permeability detection unit, including a superconducting quantum interference device, for real-time monitoring of the dynamic change information of the magnetic permeability of the BDNF antibody complex in the detection magnetic field and generating a time-domain magnetic signal of the BDNF antibody complex; A control module, which performs denoising processing on the time-domain magnetic signal based on wavelet transform; The control module constructs a non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration; according to the magnetic permeability dynamic change information and the non-linear mapping relationship, it generates the sample BDNF concentration corresponding to the peripheral blood sample to be tested, and completes the auxiliary determination of brain-derived neurotrophic factor in the peripheral blood sample to be tested; The control module completes the evaluation of chemotherapy-induced depression for the peripheral blood sample to be tested according to the sample BDNF concentration.

2. The system according to claim 1, wherein The evaluation of chemotherapy-induced depression for the peripheral blood sample to be tested according to the sample BDNF concentration includes: Obtaining the chemotherapy cycle information and the cumulative dose of doxorubicin corresponding to the peripheral blood sample to be tested; Generating a depression occurrence probability index according to the BDNF concentration value, chemotherapy cycle information, and cumulative dose of doxorubicin, and completing the evaluation of chemotherapy-induced depression for the peripheral blood sample to be tested.

3. The system according to claim 2, wherein The expression formula of the depression occurrence probability index includes: P = 1 / (1 + e^(-(α·C + β·T + γ·D + δ))); Wherein, P is the depression occurrence probability index, C is the BDNF concentration value, T is the number of days in the cycle corresponding to the chemotherapy cycle information, D is the cumulative dose of doxorubicin, α, β, γ are characteristic weight coefficients, and δ is a regulatory factor.

4. The system according to claim 3, wherein The characteristic weight coefficients are determined by regression analysis according to a preset clinical sample training set; the value range of α is [-0.25, -0.15], the value range of β is [0.03, 0.08], and the value range of γ is [0.10, 0.20].

5. The system according to claim 1, characterized in that, The construction of the non-linear mapping relationship between the dynamic change rate of magnetic permeability and the BDNF concentration includes: Performing multi-scale feature extraction on the time-domain magnetic signal to obtain time-frequency feature parameters; Inputting the time-frequency feature parameters into a pre-trained support vector regression model, and the support vector regression model establishes a non-linear mapping relationship between the time-frequency feature parameters and the BDNF concentration through kernel function space mapping.

6. The system according to claim 5, wherein The generation of the sample BDNF concentration corresponding to the peripheral blood sample to be tested according to the magnetic permeability dynamic change information and the non-linear mapping relationship includes: Establishing a reference curve between the magnetic permeability dynamic change information and the standard BDNF concentration sample based on the gradient dilution method; Obtaining the mapping value corresponding to the magnetic permeability dynamic change information under the non-linear mapping relationship; Performing dynamic weighted fusion on the reference curve and the mapping value to obtain the sample BDNF concentration.

7. The system according to claim 1, characterized in that, The generation of the time-domain magnetic signal of the BDNF antibody complex includes: Synchronously collecting the original magnetic signal of the magnetic permeability change through the superconducting quantum interference device; the ratio of the sampling frequency corresponding to the original magnetic signal to the operating frequency of the alternating magnetic field controller is greater than 10; Performing baseline correction and amplitude normalization processing on the original magnetic signal to eliminate the environmental magnetic field interference component of the original magnetic signal; Obtaining the time-frequency domain joint feature matrix corresponding to the original magnetic signal according to the short-time Fourier transform, and extracting the characteristic frequency band components related to the binding state of the BDNF antibody complex in the time-frequency domain joint feature matrix; Reconstructing the characteristic frequency band components to obtain the waveform of the time-domain magnetic signal.

8. The system according to claim 1, wherein Before constructing the non-linear mapping relationship between the magnetic permeability dynamic change rate and the BDNF concentration, it further includes: Identifying and eliminating the magnetic interference characteristics in the time-domain magnetic signal; The magnetic interference characteristics include adriamycin metabolite characteristics and interleukin-6 characteristics.

9. The system according to claim 1, wherein The particle size of the inorganic metal magnetic particles is 10-100 nm and the surface is modified with polyethylene glycol; and / or, The magnetic field intensity of the detected magnetic field is 0.1-1.5 T.

10. A method for auxiliary determination of brain-derived neurotrophic factor for chemotherapy-induced depression assessment, characterized in that, Applied to the control module of the system according to any one of claims 1-9, the method includes: Obtaining the magnetic permeability dynamic change information and the time-domain magnetic signal of the BDNF antibody complex in the detected magnetic field monitored by the magnetic permeability detection unit in real time; Performing denoising processing on the time-domain magnetic signal based on wavelet transform; Constructing a non-linear mapping relationship between the magnetic permeability dynamic change rate and the BDNF concentration; Generating the sample BDNF concentration corresponding to the peripheral blood sample to be tested according to the magnetic permeability dynamic change information and the non-linear mapping relationship, and completing the auxiliary determination of brain-derived neurotrophic factor in the peripheral blood sample to be tested; Completing the chemotherapy-induced depression assessment of the peripheral blood sample to be tested according to the sample BDNF concentration.

Images