Method for evaluating curative effect of depressive disorder treatment based on heart rate variability circadian rhythm

Abstract

The invention discloses a method for evaluating the curative effect of depressive disorder treatment based on heart rate variability circadian rhythm, and belongs to the technical field of mental disease treatment evaluation, and the method comprises the following steps: carrying out 24-hour continuous electrocardiogram monitoring on a patient to obtain HRV data of the corresponding patient, and preprocessing the HRV data; dividing the HRV data according to a preset unit time length to obtain HRV unit data of a corresponding unit time period, integrating the HRV unit data according to a corresponding patient to obtain patient analysis data of the patient, and determining circadian rhythm parameter data according to the patient analysis data; establishing a treatment monitoring model, performing data acquisition on a target patient to obtain target analysis data, and analyzing the target analysis data through the treatment monitoring model to obtain a treatment effect of the target patient; the method is not limited to treatment evaluation of depressive disorder, and can be applied to evaluation of other clinical scenes and disease treatment effects requiring continuous monitoring of heart rate variability circadian rhythm parameters.

Description

Technical Field

[0001] The present invention belongs to the technical field of mental illness treatment evaluation, and specifically is a method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability. Background Art

[0002] Depressive disorder is a common mental illness and has become a major challenge to global public health. There are many ways to treat depression, including medication, psychotherapy, and physical therapy. However, the current evaluation of treatment efficacy still mainly relies on changes in clinical symptoms and lacks objective and quantitative biological indicators. This evaluation method is often delayed and inaccurate, especially in the early stages of treatment, when symptoms may improve slowly and the timeliness of treatment adjustments is insufficient. Therefore, there is an urgent need for a technology that can evaluate treatment effects in real time, objectively, and dynamically.

[0003] In recent years, heart rate variability (HRV), as an important biomarker of autonomic nervous system (ANS) function, has been widely used in the study of various diseases. HRV reveals the balance between sympathetic and parasympathetic nerves by reflecting the fluctuations in the time intervals between heart beats. Low HRV levels are usually associated with autonomic nervous system dysfunction, and HRV is significantly correlated with the severity of depression, mood swings, etc. Many studies have shown that HRV in patients with depression is significantly lower than that in healthy individuals, further proving the potential of HRV as a physiological marker of depression.

[0004] However, changes in HRV are not only closely related to emotional state, but also affected by circadian rhythm. Circadian rhythm regulates multiple physiological functions including sleep, body temperature, hormone secretion, etc., and has a profound impact on psychological states such as emotions and cognition. Patients with depression often have circadian rhythm disorders, such as sleep disorders, early awakening, mood swings and other symptoms. These circadian rhythm abnormalities may aggravate the clinical manifestations of depression and further affect the effect of treatment. Therefore, the treatment of depression requires not only attention to HRV, but also a comprehensive assessment combined with changes in circadian rhythm.

[0005] Although existing studies have explored the application of HRV in depressive disorders, most of these studies focus on single HRV measurements or circadian rhythm assessments in a single period of time, lacking dynamic monitoring and comprehensive analysis of HRV and circadian rhythm changes during treatment. In addition, existing treatment effect evaluation methods mainly rely on patients' subjective feedback, which cannot fully reflect changes in physiological status during treatment. Most existing technologies rely on traditional medical equipment and lack convenient out-of-hospital monitoring methods. Therefore, there is currently a lack of a method that can monitor and quantitatively evaluate HRV and circadian rhythm changes in real time during treatment, and combine it with treatment effect judgment.

[0006] Some existing technologies assess circadian rhythms by monitoring sleep, body temperature or hormone levels, but these technologies have limitations. For example, traditional sleep monitoring methods cannot reflect the fluctuations of circadian rhythms in real time and continuously, and monitoring of hormone levels requires invasive procedures (such as blood sampling), which is not convenient in clinical applications.

[0007] Based on this, the present invention provides a method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability, aiming to provide an objective, real-time, and quantitative means of monitoring the therapeutic effect, provide clinicians with accurate treatment feedback, and promote the optimization and adjustment of personalized treatment plans. Summary of the invention

[0008] In order to solve the problems existing in the above scheme, the present invention provides a method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability. By combining the analysis of heart rate variability and circadian rhythm, a dynamic quantitative evaluation of the physiological state of patients with depressive disorders is achieved. In order to improve the reliability and feasibility of the data, the invention introduces a data correction module and a list of reserve equipment, and uses a machine learning algorithm to correct the measurement data of non-standard equipment, thereby reducing the impact of equipment errors on the results. The corrected analysis data generated by comparison with standard equipment greatly improves the compatibility between devices and the accuracy of the data.

[0009] The present invention can evaluate the treatment effect of depression disorders in real time, objectively and quantitatively, and can be combined with smart wearable devices to support dynamic monitoring of the treatment effect outside the hospital. This innovation enhances the patient's participation in treatment and the real-time nature of the data, while providing clinicians with accurate treatment feedback, which helps to optimize and adjust personalized treatment plans, thereby improving the scientificity and accuracy of the treatment effect.

[0010] The purpose of the present invention can be achieved through the following technical solutions: Methods for evaluating the efficacy of treatment for depressive disorders based on the circadian rhythm of heart rate variability include: Step 1: Perform 24-hour continuous ECG monitoring on the patient to obtain HRV data of the corresponding patient, wherein the HRV data is ECG data; and pre-process the HRV data; Furthermore, the method of performing 24-hour continuous ECG monitoring on the patient is as follows: A dynamic electrocardiogram device or a wearable electrocardiogram monitoring device is used to perform 24-hour continuous electrocardiogram monitoring on the patient to obtain HRV initial data, and artifacts and noise data are removed from the HRV initial data to obtain HRV data.

[0011] Furthermore, the method for preprocessing HRV data includes: Define an RR interval, where the RR interval is the time difference between two adjacent heartbeats; perform feature recognition on the HRV data according to the RR interval definition to obtain a corresponding RR interval; Calculate the HRV index using time domain analysis and frequency domain analysis, wherein the HRV index includes a time domain index and a frequency domain index; The time domain indicators include but are not limited to standard deviation, average RR interval and PNN50; the average RR interval is the root mean square of the difference between consecutive RR intervals; PNN50 is the proportion of adjacent RR interval differences exceeding 50ms; Frequency domain indicators include but are not limited to extremely low frequency, low frequency, high frequency and LF / HF ratio; extremely low frequency is 0.003~0.04Hz; low frequency is 0.04~0.15Hz; high frequency is 0.15~0.4Hz; in the LF / HF ratio, LF is low frequency and HF is high frequency.

[0012] Step 2: Set a unit duration, divide 24 hours according to the unit duration to form K unit time periods, where K is an integer; divide the HRV data according to the unit time periods to obtain HRV unit data corresponding to the unit time periods, integrate the HRV unit data according to the corresponding patients to obtain the patient analysis data of the patients, and determine the circadian rhythm parameter data according to the patient analysis data, wherein the circadian rhythm parameter data includes HRV representative value, HRV fluctuation representative amplitude, HRV representative peak value and preset confidence interval; Furthermore, the unit duration is 5 minutes or other feasible time periods.

[0013] Further, K = (24 × 60) ÷ dy; Where: dy is the unit duration, and dy≠0.

[0014] Furthermore, the preset confidence interval is a 95% confidence interval.

[0015] Further, the method for determining circadian rhythm parameter data based on patient analysis data includes: Identify each HRV unit data in the patient analysis data, analyze the HRV unit data, and obtain the HRV value of the unit time period; The HRV value of each unit period is fitted using a periodic fitting function that meets the fitting requirements to determine the M value of the corresponding patient. i , A i and θ i ; i represents the corresponding patient, i=1, 2, ..., n, n is the number of patients; M i is the average daily HRV value of the corresponding patient; A i is the fluctuation amplitude of the corresponding patient; θ iis the peak time of the HRV value of the corresponding patient; According to the obtained M i , A i and θ i Integrated into circadian rhythm parameter data.

[0016] Furthermore, if the periodic fitting function is a cosine curve, the HRV value of each unit period is fitted according to the cosine curve to obtain the cosine function of the corresponding patient. The cosine function is: ; Where: HRV i (t) represents the HRV value of the corresponding patient at time t, i represents the corresponding patient, i=1, 2, ..., n, n is the number of patients; 1 (t) represents the HRV value of the patient labeled 1 at time t; M i is the average daily HRV value of the corresponding patient; A i is the amplitude of HRV fluctuation; θ i is the peak time (time delay) of the HRV value of the corresponding patient; T is the periodic time, usually 24 hours; Identify M in the cosine function i , A i and θ i , integrated into the unit rhythm data of the corresponding patients; each unit rhythm data is analyzed to obtain circadian rhythm parameter data.

[0017] Step 3: Establishing a treatment monitoring model, wherein the treatment monitoring model is used to evaluate and predict the treatment effect of a target patient; the target patient is a patient with depression disorder who needs treatment evaluation; Step 4: Collect data on the target patient to obtain target analysis data, analyze the target analysis data through the treatment monitoring model, and obtain the current treatment effect and predicted treatment effect of the target patient.

[0018] Furthermore, the method for collecting data from the target patient includes: Determine a control time, obtain historical HRV data and historical circadian rhythm parameter data of the target patient according to the control time, and integrate the obtained historical HRV data and historical circadian rhythm parameter data into benchmark control data; Collecting HRV data of a target patient to obtain target HRV data, preprocessing the target HRV data, determining circadian rhythm parameter data of the target patient according to the preprocessed target HRV data, and marking the target circadian rhythm parameter data; integrating the target circadian rhythm parameter data and the target HRV data into target collected data; Integrate target acquisition data and benchmark control data into target analysis data.

[0019] Furthermore, the method for collecting HRV data of the target patient includes: Set up correction module and user collection module; The user acquisition module is used to collect data from the target patient and display a preset list of reserve devices to the target patient. When the target patient needs to be evaluated for treatment effect, data is collected through the reserve devices in the reserve device list to obtain user HRV data, and the user HRV data is sent to the correction module; The correction module is used to correct the received user HRV data to obtain the target HRV data of the target patient.

[0020] Furthermore, the method for correcting the user's HRV data includes: The platform sets a list of reserve equipment, which is used to count the reserve equipment that meets the HRV data collection requirements; Performing verification tests on the reserve equipment in the reserve equipment list to obtain corrected analysis data of the reserve equipment, wherein the corrected analysis data includes HRV simulation data and HRV standard data; Establishing a correction model of the storage device according to the correction analysis data, wherein the correction module is used to correct the user HRV data collected by the storage device; The storage device corresponding to the received user HRV data is identified, and the user HRV data is corrected by a correction model corresponding to the storage device to obtain target HRV data.

[0021] Furthermore, the target analysis data also includes additional physiological function circadian rhythm change data related to treatment, and the additional physiological function circadian rhythm change data includes body temperature, skin conductance, and exercise volume, among which HRV circadian rhythm parameters are the core analysis indicators.

[0022] Compared with the prior art, the present invention has the following beneficial effects: The present invention realizes an objective, real-time and quantitative means of monitoring treatment effects through a dynamic evaluation method combining HRV and circadian rhythm characteristics, provides accurate treatment feedback for clinicians, and promotes the optimization and adjustment of personalized treatment plans; the circadian rhythm characteristics of heart rate variability (HRV) are applied to the evaluation of the therapeutic efficacy of depressive disorders, filling the technical gap in this field. In an outpatient environment, the target patient can wear a wearable device to continuously collect HRV, and correct the data collected by the wearable device through a set correction module to ensure that the measured data is close to the standard equipment data, thereby achieving flexible and convenient efficacy evaluation. Through the above technical solution, the present invention provides clinicians with a convenient, reliable, dynamic and quantitative treatment evaluation tool, which can not only realize the dynamic adjustment of individualized treatment plans, but also facilitate remote monitoring and evaluation in non-medical environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] like Figure 1 As shown, a method for evaluating the efficacy of treatment for depressive disorders based on the circadian rhythm of heart rate variability includes: Step 1: Perform 24-hour continuous ECG monitoring on the patient to obtain the HRV data of the corresponding patient, where the HRV data is the ECG data; pre-process the obtained HRV data; In one embodiment, the method for performing 24-hour continuous ECG monitoring on a patient is: A dynamic electrocardiogram device or a wearable electrocardiogram monitoring device is used to continuously monitor the patient's electrocardiogram for 24 hours to obtain the initial HRV data. The patient wears the device during normal daily activities and avoids strenuous exercise. The obtained initial HRV data is removed from artifacts and noise data to obtain HRV data; the artifact and noise data can be processed based on existing methods, such as inspection by experts.

[0027] In one embodiment, 24-hour continuous ECG monitoring of the patient can be implemented based on other existing medical equipment to obtain HRV data.

[0028] In one embodiment, the method for preprocessing the obtained HRV data is: processing the 24-hour HRV data according to an existing standard HRV analysis method.

[0029] In one embodiment, the method of preprocessing the obtained HRV data includes: Define the RR interval, which is the time difference between two adjacent heartbeats; perform feature recognition on HRV data according to the definition of the RR interval to obtain the corresponding RR interval; Use time domain analysis and frequency domain analysis to calculate HRV indicators, which include time domain indicators and frequency domain indicators; Time domain indicators include standard deviation, mean RR interval and PNN50; standard deviation (SDNN) is the standard deviation of all normal heartbeat intervals; mean RR interval (RMSSD): the root mean square of the difference between consecutive RR intervals; PNN50 is the proportion of adjacent RR interval differences exceeding 50ms.

[0030] Frequency domain indicators include very low frequency, low frequency, high frequency and LF / HF ratio; very low frequency (VLF, 0.003-0.04Hz), low frequency (LF, 0.04-0.15Hz), high frequency (HF, 0.15-0.4Hz); LF / HF ratio is used to evaluate the balance between sympathetic and parasympathetic nerves.

[0031] Step 2: Set the unit duration, such as 5 minutes, or other feasible time periods, that is, time periods that meet the preset requirements; divide 24 hours according to the unit duration to form K unit time periods, where K is an integer, K=(24×60) / dy, in minutes, and dy is the unit duration; divide the HRV data according to each unit time period, obtain the HRV unit data corresponding to each unit time period, integrate each HRV unit data into the patient analysis data of the patient, and determine the circadian rhythm parameter data based on the patient analysis data of each patient. The circadian rhythm parameter data includes the HRV representative value, the HRV fluctuation representative amplitude, the HRV representative peak value and the preset confidence interval; the preset confidence interval is generally a 95% confidence interval.

[0032] In one embodiment, the circadian rhythm parameter data is determined based on the patient analysis data of each patient, and the data can be processed based on the existing circadian rhythm analysis method to obtain the corresponding circadian rhythm parameter data.

[0033] In one embodiment, a method for determining circadian rhythm parameter data based on patient analysis data of each patient includes: Identify each HRV unit data in the patient analysis data, analyze the HRV unit data using mathematical processing methods such as mean, obtain the HRV value corresponding to the HRV unit data, and then determine the HRV value of the unit time period; Use a cosine curve or other periodic fitting function to fit the HRV value of each unit period to determine the M value of the corresponding patient. i , A i and θ i ; i represents the corresponding patient, i=1, 2, ..., n, n is the number of patients; M i is the average daily HRV value of the corresponding patient; A i is the fluctuation amplitude of the corresponding patient; θ i is the peak time of the HRV value of the corresponding patient; The obtained M i , A i and θ i and its statistical intervals are integrated into circadian rhythm parameter data.

[0034] Exemplarily, a cosine curve is used to fit the HRV value of each unit period: The cosine function of the corresponding patient is obtained, and the cosine function is: ; Where: HRV i (t) represents the HRV value of the corresponding patient at time t, i represents the corresponding patient, i=1, 2, ..., n, n is the number of patients; 1 (t) represents the HRV value of the patient labeled 1 at time t; M i is the average daily HRV value of the corresponding patient; A i is the amplitude of HRV fluctuation; θ i is the peak time (time delay) of the HRV value of the corresponding patient; T is the periodic time, usually 24 hours; Identify M in the cosine function i , A i and θ i , integrated into the unit rhythm data of the corresponding patients; each unit rhythm data is analyzed to obtain circadian rhythm parameter data.

[0035] To analyze the rhythm data of each unit, random effects meta-analysis can be used to estimate the mean and 95% confidence interval of the overall M, A, and θ as the representative value of HRV, the representative amplitude of HRV fluctuation, and the representative peak value of HRV; other existing technologies can also be used to determine the circadian rhythm parameter data.

[0036] Step 3: Establish a treatment monitoring model. The treatment monitoring model can use a variety of machine learning, statistical analysis or intelligent prediction methods. The model is trained with historical patient data to enable it to evaluate the current treatment effect and predict the subsequent treatment effect based on the corresponding HRV and circadian rhythm changes. Model types are not limited to decision trees, random forests, support vector machines, neural networks or other algorithms.

[0037] The treatment monitoring model is used to process circadian rhythm parameter data and HRV data, predict and evaluate the treatment effect of the target patient; that is, the treatment monitoring model evaluates the current treatment effect based on the circadian rhythm parameter data and HRV data, and then provides real-time feedback by analyzing the short-term fluctuations, trend changes and phased improvements of the HRV circadian rhythm parameters to predict the subsequent treatment effect; this is equivalent to the treatment monitoring model having two output results, one is to evaluate the current treatment effect, and the other is to estimate the treatment effect. It is equivalent to comparing the data before and after to evaluate the current quality effect, and combining the prediction method to infer the subsequent treatment effect; that is, using the HRV and circadian rhythm change data before and after treatment or the subsequent prediction for evaluation or predictive analysis.

[0038] The target patients are patients with depressive disorders who need treatment evaluation, which is different from the patients in steps one and two above. The patients in the above steps are analyzed as source materials.

[0039] It can also be composed of two intelligent models.

[0040] In one embodiment, the process of establishing the treatment monitoring model is: Model selection and training: Gradient boosting machine (GBM) is a tree-based ensemble learning method that builds a decision tree through multiple iterative learning and weights it with the results of the previous learning to improve the prediction accuracy of the model.

[0041] The steps in the training process include: Data splitting: The collected HRV data and circadian rhythm parameter data are divided into training set and test set (for example, 80% of the data is used for training and 20% for testing).

[0042] Feature selection: Select HRV indicators related to treatment efficacy (such as SDNN, RMSSD, LF, HF, etc.), as well as circadian rhythm parameters (such as M, A, θ).

[0043] GBM model training: In GBM, the model builds a series of decision trees through continuous training and iteration, and each tree is a fit of the residual part of the previous tree.

[0044] The specific training process formula is as follows: ; Hyperparameter tuning: Use grid search or random search to tune hyperparameters (such as tree depth, learning rate, number of iterations, etc.) to improve model performance.

[0045] Model evaluation and validation: The performance of the model is evaluated by indicators such as accuracy, precision, recall, F1 score, and area under the ROC curve (AUC).

[0046] Cross-validation techniques are used to further verify the generalization ability of the model.

[0047] SHAP value analysis: The SHAP (SHapley Additive exPlanation) value was used to rank the importance of the features of the GBM model, and the most important HRV features and circadian rhythm parameters for predicting the treatment effect of depressive disorders were identified.

[0048] In other embodiments, a treatment monitoring model may also be established based on existing intelligent technologies.

[0049] Step 4: Collect data on the target patient, including continuously collecting HRV data through a dynamic electrocardiogram device or a wearable device again, and preprocessing and parameter analysis of the data to obtain target analysis data, and analyzing the target analysis data through a treatment monitoring model to obtain the current treatment effect and predicted treatment effect of the target patient.

[0050] In one implementation, a method for collecting data from a target patient includes: Determine the control time, which is the time when historical data collection is performed, that is, the target patient at what time is used for comparison, as a benchmark for effect evaluation, such as the time before treatment, which is set by the target patient or doctor; obtain the target patient's historical HRV data and historical circadian rhythm parameter data according to the control time, and integrate them into the benchmark control data; Collect HRV data of the current target patient, obtain HRV data, mark it as target HRV data, preprocess the target HRV data, determine the circadian rhythm parameter data of the target patient according to the preprocessed target HRV data, and mark it as target circadian rhythm parameter data; integrate the target circadian rhythm parameter data and the target HRV data into target collection data; Integrate target acquisition data and benchmark control data into target analysis data.

[0051] In one embodiment, in actual application, the target patient has a need to understand the treatment effect in real time, but because it is necessary to go to the hospital for monitoring and evaluation, the flexibility is poor, so the target patient has a need for treatment evaluation outside the hospital; therefore, in this embodiment, the method for collecting HRV data for the current target patient is different from the collection method in step one, and the method for collecting HRV data for the current target patient also includes: Set up a correction module and a user collection module; generally, the correction module is set in the corresponding system of the corresponding hospital, and the user collection module is set at the user, but the correction module can also be set at the user.

[0052] The user acquisition module is used to collect user HRV data of the target patient, and display a preset list of reserve devices to the user. When the user needs to evaluate the treatment effect, data is collected through the reserve devices in the reserve device list to obtain the user's HRV data, and the user's HRV data is sent to the correction module; The correction module is used to correct the received user HRV data to obtain the target HRV data of the target patient.

[0053] In one embodiment, the method for correcting the user's HRV data includes: The platform sets up a list of reserve devices, which is used to count the ECG collection devices that meet the HRV data collection requirements and are marked as reserve devices. Generally, the platform sets it up directly, such as setting mobile smart devices of major well-known brands as reserve devices, such as the currently common smart watches and heart rate belts of major brands with monitoring functions. Perform verification tests on each reserve device in the reserve device list to obtain revised analysis data for each reserve device, that is, use the reserve devices to collect data on patients respectively, obtain HRV data collected by the reserve devices during the simulation process, mark it as HRV simulation data, and use standard medical equipment to collect data at the same time to form collected data with a control effect, mark it as HRV standard data, and integrate multiple groups of HRV simulation data and HRV standard data into revised analysis data; According to the correction analysis data, a correction model for the corresponding reserve equipment is established. The correction model is established based on existing correction technologies, such as the common ones based on machine learning or deep learning algorithms. For example, machine learning or deep learning algorithms are used to train the model with HRV standard data as labels (true values) and HRV simulation data as input features. The goal is to enable the model to learn the mapping relationship between the two, so that the real HRV data collected by the reserve equipment can be stored. The model is verified using a validation data set to evaluate the model's predictive performance and accuracy. The model is optimized based on the validation results, such as adjusting model parameters, adding features, etc., to improve the model's predictive performance.

[0054] The storage device corresponding to the received user HRV data is identified, and the user HRV data is corrected by a correction model corresponding to the storage device to obtain target HRV data.

[0055] In one embodiment, the method of the present invention is applicable to the evaluation of therapeutic efficacy of other diseases or treatment states including but not limited to depressive disorders, wherein the disease or treatment state obtains an objective therapeutic efficacy evaluation through the HRV circadian rhythm parameter analysis.

[0056] In one embodiment, by monitoring the patient's circadian rhythm changes in physiological functions, while monitoring the patient's HRV circadian rhythm parameters, other physiological function circadian rhythm change data related to treatment can be obtained, and the other physiological function circadian rhythm change data include circadian rhythm characteristics of body temperature, skin conductance and exercise volume, etc.; the HRV circadian rhythm parameters are fused and analyzed with the other physiological function circadian rhythm change data to comprehensively evaluate the treatment effect on patients with depressive disorders, wherein the HRV circadian rhythm parameters are the core analysis indicators; the method can also be used for other neuropsychiatric diseases accompanied by autonomic dysfunction and circadian rhythm abnormalities, including but not limited to depressive disorders, anxiety disorders, insomnia, etc.

[0057] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0058] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability, characterized in that: Methods include: Step 1: Perform 24-hour continuous ECG monitoring on the patient to obtain HRV data of the corresponding patient, wherein the HRV data is ECG data; Preprocessing the HRV data; Step 2: Set a unit duration, divide 24 hours according to the unit duration to form K unit time periods, where K is an integer; divide the HRV data according to the unit time periods to obtain HRV unit data corresponding to the unit time periods, integrate the HRV unit data according to the corresponding patients to obtain the patient analysis data of the patients, and determine the circadian rhythm parameter data according to the patient analysis data, wherein the circadian rhythm parameter data includes HRV representative value, HRV fluctuation representative amplitude, HRV representative peak value and preset confidence interval; Step 3: Establishing a treatment monitoring model, wherein the treatment monitoring model is used to evaluate and predict the treatment effect of a target patient; the target patient is a patient with depression disorder who needs treatment evaluation; Step 4: Collect data on the target patient to obtain target analysis data, analyze the target analysis data through the treatment monitoring model, and obtain the current treatment effect and predicted treatment effect of the target patient.

2. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to claim 1, characterized in that: The method of conducting 24-hour continuous ECG monitoring on patients is: A dynamic electrocardiogram device or a wearable electrocardiogram monitoring device is used to perform 24-hour continuous electrocardiogram monitoring on the patient to obtain HRV initial data, and artifacts and noise data are removed from the HRV initial data to obtain HRV data.

3. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to claim 1, characterized in that: Methods for preprocessing HRV data include: Define an RR interval, where the RR interval is the time difference between two adjacent heartbeats; perform feature recognition on the HRV data according to the RR interval definition to obtain a corresponding RR interval; Calculate the HRV index using time domain analysis and frequency domain analysis, wherein the HRV index includes a time domain index and a frequency domain index; The time domain indicators include but are not limited to standard deviation, average RR interval and PNN50; the average RR interval is the root mean square of the difference between consecutive RR intervals; PNN50 is the proportion of adjacent RR interval differences exceeding 50ms; Frequency domain indicators include but are not limited to extremely low frequency, low frequency, high frequency and LF / HF ratio; extremely low frequency is 0.003~0.04Hz; low frequency is 0.04~0.15Hz; high frequency is 0.15~0.4Hz; in the LF / HF ratio, LF is low frequency and HF is high frequency.

4. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to claim 1, characterized in that: K = (24 × 60) ÷ dy; Where: dy is the unit duration, and dy≠0.

5. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to claim 1, characterized in that: The method for determining circadian rhythm parameter data based on patient analysis data includes: Identify each HRV unit data in the patient analysis data, analyze the HRV unit data, and obtain the HRV value of the unit time period; The HRV value of each unit period is fitted using a periodic fitting function that meets the fitting requirements to determine the M value of the corresponding patient. i , A i and θ i , i represents the corresponding patient, i=1, 2, ..., n, n is the number of patients; M i is the average daily HRV value of the corresponding patient; A i is the fluctuation amplitude of the corresponding patient; θ i is the peak time of the HRV value of the corresponding patient; According to the obtained M i , A i and θ i Integrated into circadian rhythm parameter data.

6. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to claim 1, characterized in that: Methods for collecting data from target patients include: Determine a control time, obtain historical HRV data and historical circadian rhythm parameter data of the target patient according to the control time, and integrate the obtained historical HRV data and historical circadian rhythm parameter data into benchmark control data; Collecting HRV data of a target patient to obtain target HRV data, preprocessing the target HRV data, determining circadian rhythm parameter data of the target patient according to the preprocessed target HRV data, and marking the target circadian rhythm parameter data; integrating the target circadian rhythm parameter data and the target HRV data into target collected data; Integrate target acquisition data and benchmark control data into target analysis data.

7. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to claim 6, characterized in that: The target analysis data also includes additional physiological function circadian rhythm change data related to treatment, and the additional physiological function circadian rhythm change data includes body temperature, skin conductance, and exercise volume.

8. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to claim 6, characterized in that: Methods for collecting HRV data from target patients include: Set up correction module and user collection module; The user acquisition module is used to collect data from the target patient and display a preset list of reserve devices to the target patient. When the target patient needs to be evaluated for treatment effect, data is collected through the reserve devices in the reserve device list to obtain user HRV data, and the user HRV data is sent to the correction module; The correction module is used to correct the received user HRV data to obtain the target HRV data of the target patient.

9. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to claim 8, characterized in that: Methods for correcting user HRV data include: The platform sets a list of reserve equipment, which is used to count the reserve equipment that meets the HRV data collection requirements; Performing verification tests on the reserve equipment in the reserve equipment list to obtain corrected analysis data of the reserve equipment, wherein the corrected analysis data includes HRV simulation data and HRV standard data; Establishing a correction model of the storage device according to the correction analysis data, wherein the correction module is used to correct the user HRV data collected by the storage device; The storage device corresponding to the received user HRV data is identified, and the user HRV data is corrected by a correction model corresponding to the storage device to obtain target HRV data.

10. The method for evaluating the therapeutic efficacy of depressive disorders based on the circadian rhythm of heart rate variability according to any one of claims 1 to 9, characterized in that: The method is applicable to the evaluation of therapeutic efficacy in other diseases or treatment states including but not limited to depressive disorders, wherein the efficacy of the disease or treatment state is evaluated by analyzing the HRV circadian rhythm parameters.

Images