A method and device for evaluating the efficacy of auricular vagus nerve stimulation for insomnia

Abstract

The application provides an auricular vagus nerve stimulation insomnia treatment effect evaluation method and device, the method comprising: obtaining the treatment effect grade of the auricular vagus nerve stimulation treatment according to the data and the change rate of a plurality of insomnia patients before and after the treatment, and according to the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score; obtaining a plurality of heart rate data change rates related to the treatment effect grade from the heart rate variability data change rate through multiple linear regression analysis; training a random forest model according to the sleep quality change rate of the plurality of insomnia patients, the plurality of heart rate data change rates, and the corresponding treatment effect score to obtain an auricular vagus nerve stimulation insomnia treatment effect evaluation model; and obtaining the auricular vagus nerve stimulation insomnia treatment effect score of a target patient through the auricular vagus nerve stimulation insomnia treatment effect evaluation model. The application improves the objectivity, quantification, and accuracy of the treatment effect evaluation.

Description

Technical Field

[0001] This application relates to the technical field of insomnia treatment efficacy evaluation, specifically to a method and device for evaluating the efficacy of vagus nerve stimulation for insomnia treatment. Background Technology

[0002] Pisciatic vagus nerve stimulation (taVNS) is a novel non-invasive neuromodulation technique for treating insomnia, and it has been preliminarily applied in clinical practice. However, the industry currently lacks an objective quantitative evaluation model for the efficacy of taVNS in treating insomnia. While some existing taVNS devices integrate HRV acquisition modules to obtain HRV indicators such as SDNN, RMSSD, and pNN50, and select personalized stimulation frequencies based on these indicators, they only collect HRV indicators or apply them in a single dimension. They cannot quantitatively correlate HRV indicators with the degree of insomnia improvement, leading to reliance on subjective scales (such as the Pittsburgh Sleep Quality Index) for evaluating the efficacy of taVNS in treating insomnia. This lack of objective, quantitative, and practical evaluation criteria makes it difficult to support a closed-loop control system for taVNS in treating insomnia and to provide accurate feedback for adjusting stimulation parameters and optimizing treatment plans. Summary of the Invention

[0003] The purpose of this application is to overcome the shortcomings and deficiencies in the prior art and to provide a method and device for evaluating the efficacy of vagus nerve stimulation for insomnia.

[0004] The first aspect of this application provides a method for evaluating the efficacy of vagus nerve stimulation for insomnia, including: We collected first heart rate variability data, first sleep quality data, and first Pittsburgh sleep quality scores corresponding to the first sleep quality data from multiple insomnia patients before treatment. The second heart rate variability data, second sleep quality data, and the second Pittsburgh sleep quality score corresponding to the second sleep quality data were collected from the insomnia patients after each percutaneous vagus nerve stimulation treatment. Based on the first sleep quality data and the second sleep quality data, obtain the sleep quality change rate; based on the first heart rate variability data and the second heart rate variability data, obtain the heart rate variability data change rate; The efficacy level of percutaneous vagus nerve stimulation therapy was determined based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score. Through multiple linear regression analysis, several heart rate data change rates related to the therapeutic effect level were obtained from the heart rate variability data change rate. Based on the rate of change in sleep quality of the multiple insomnia patients, the rate of change in several heart rate data, and the corresponding efficacy scores, a random forest model was trained to obtain an evaluation model for the efficacy of vagus nerve stimulation for insomnia. The actual sleep quality change rate and several actual heart rate data change rates of the target patients after percutaneous vagus nerve stimulation treatment were input into the vagus nerve stimulation insomnia efficacy evaluation model to obtain the vagus nerve stimulation insomnia efficacy score of the target patients.

[0005] As one implementation method, the step of determining the efficacy level of percutaneous vagus nerve stimulation therapy based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score includes: Based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score, obtain the difference in sleep quality scores before and after treatment; The sleep quality reduction rate is obtained by comparing the difference in sleep quality scores with the first Pittsburgh sleep quality score. Based on the preset correspondence between the quality reduction rate and the therapeutic effect level, the therapeutic effect level corresponding to the sleep quality reduction rate is obtained.

[0006] As one implementation method, the steps of training a random forest model based on the sleep quality change rate of the multiple insomnia patients, the change rate of several heart rate data, and the corresponding efficacy scores to obtain an evaluation model for the efficacy of vagus nerve stimulation for insomnia include: The sample set is constructed by taking the rate of change in sleep quality and the rate of change in several heart rate data of the multiple insomnia patients as inputs and the efficacy score as output. The random forest model is trained based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation in insomnia.

[0007] As one implementation method, the step of training the random forest model based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation for insomnia includes: The sample set is divided into a training set and a test set; The random forest model is trained based on the training set to obtain a candidate insomnia efficacy evaluation model. The candidate insomnia efficacy evaluation model was validated and tested using the test set to obtain the insomnia efficacy evaluation model that passed the test via auricular vagus nerve stimulation.

[0008] In one implementation, the rate of change of the several heart rate data includes the rate of change of the SDNN index, the rate of change of the RMSSD index, and the rate of change of the pNN50 index.

[0009] As one implementation method, the sleep quality change rate includes the sleep latency change rate, the total sleep time change rate, the sleep efficiency change rate, and the number of awakenings change rate.

[0010] A second aspect of this application provides a device for evaluating the efficacy of vagus nerve stimulation for insomnia, comprising: The pre-treatment data acquisition module is used to collect the first heart rate variability data, the first sleep quality data, and the first Pittsburgh sleep quality score corresponding to the first sleep quality data of multiple insomnia patients before treatment. The post-treatment data acquisition module is used to collect the second heart rate variability data, the second sleep quality data, and the second Pittsburgh sleep quality score corresponding to the second sleep quality data after each percutaneous vagus nerve stimulation treatment for the insomnia patients. The data change rate acquisition module is used to acquire the sleep quality change rate based on the first sleep quality data and the second sleep quality data; and to acquire the heart rate variability data change rate based on the first heart rate variability data and the second heart rate variability data. The efficacy level acquisition module is used to obtain the efficacy level of percutaneous vagus nerve stimulation therapy based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score. The heart rate data change rate acquisition module is used to obtain several heart rate data change rates related to the efficacy level from the heart rate variability data change rate through multiple linear regression analysis. The insomnia efficacy evaluation model acquisition module is used to train a random forest model based on the sleep quality change rate, the heart rate data change rate, and the corresponding efficacy score of the multiple insomnia patients to obtain the vagus nerve stimulation insomnia efficacy evaluation model. The insomnia efficacy scoring module is used to input the actual sleep quality change rate and the change rate of several actual heart rate data after percutaneous vagus nerve stimulation treatment into the vagus nerve stimulation insomnia efficacy evaluation model to obtain the vagus nerve stimulation insomnia efficacy score of the target patient.

[0011] In one implementation, the efficacy level acquisition module is used to perform the following steps: Based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score, obtain the difference in sleep quality scores before and after treatment; The sleep quality reduction rate is obtained by comparing the difference in sleep quality scores with the first Pittsburgh sleep quality score. Based on the preset correspondence between the quality reduction rate and the therapeutic effect level, the therapeutic effect level corresponding to the sleep quality reduction rate is obtained.

[0012] As one implementation method, the insomnia treatment efficacy assessment model acquisition module is used to perform the following steps: Based on the first and second heart rate variability data corresponding to the aforementioned target heart rate variability indicators, the rate of change of several indicator data is obtained. The sample set is constructed by taking the rate of change in sleep quality and the rate of change in several indicators of the multiple insomnia patients as inputs and the efficacy score as output. The random forest model is trained based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation in insomnia.

[0013] As one implementation method, the step of training the random forest model based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation for insomnia includes: The sample set is divided into a training set and a test set; The random forest model is trained based on the training set to obtain a candidate insomnia efficacy evaluation model. The candidate insomnia efficacy evaluation model was validated and tested using the test set to obtain the insomnia efficacy evaluation model that passed the test via auricular vagus nerve stimulation.

[0014] Compared to related technologies, this application is the first to construct a quantitative evaluation model for the efficacy of taVNS (transcutaneous auricular vagus nerve stimulation) in treating insomnia based on HRV (heart rate variability) data. This model quantitatively correlates HRV indicators with the degree of insomnia improvement, solving the problem of existing technologies relying on subjective scales for efficacy evaluation and improving the objectivity, quantification, and accuracy of efficacy assessment. Furthermore, the HRV data used in the sample set is selected through multiple linear regression to identify indicators with high correlation to efficacy levels, effectively improving the model's evaluation accuracy and robustness. This model is applicable to patients with different insomnia subtypes. Moreover, the taVNS insomnia efficacy score output by the trained taVNS insomnia treatment closed-loop control system can be directly used as feedback for the system, achieving seamless integration of efficacy evaluation and closed-loop control. This provides an executable reference standard for subsequent dynamic adjustment of stimulation parameters and personalized optimization of treatment plans.

[0015] To provide a clearer understanding of this application, the specific embodiments of this application will be described below in conjunction with the accompanying drawings. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a method for evaluating the efficacy of auricular vagus nerve stimulation for insomnia according to one embodiment of this application.

[0017] Figure 2 This is a flowchart of step S4 of a method for evaluating the efficacy of auricular vagus nerve stimulation for insomnia according to an embodiment of this application.

[0018] Figure 3 This is a schematic diagram of the module connections of an auricular vagus nerve stimulation insomnia efficacy assessment device according to an embodiment of this application.

[0019] 100. Auricular vagus nerve stimulation insomnia efficacy assessment device; 101. Pre-treatment data acquisition module; 102. Post-treatment data acquisition module; 103. Data change rate acquisition module; 104. Efficacy level acquisition module; 105. Heart rate data change rate acquisition module; 106. Insomnia efficacy assessment model acquisition module; 107. Insomnia efficacy scoring module. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0021] It should be understood that the described embodiments are merely some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of the embodiments of this application.

[0022] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances. The singular forms "a," "the," and "the" used in this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. The word "if" as used herein can be interpreted as "when," "when," or "in response to determination."

[0023] Furthermore, in the description of this application, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0024] Please see Figure 1 This is a flowchart of the method for evaluating the efficacy of auricular vagus nerve stimulation for insomnia according to the first embodiment of this application. The method includes: S1: Collect the first heart rate variability data, the first sleep quality data, and the first Pittsburgh sleep quality score corresponding to the first sleep quality data of multiple insomnia patients before treatment; S2: Collect the second heart rate variability data, second sleep quality data, and the second Pittsburgh sleep quality score corresponding to the second sleep quality data after each percutaneous vagus nerve stimulation treatment for the insomnia patients; In step S2, percutaneous vagus nerve stimulation (taVNS) therapy will be performed on insomnia patients according to a preset duration, such as a 4-week taVNS treatment for all patients.

[0025] The first and second heart rate variability (HRV) data can be HRV data collected by the ECG acquisition module. Heart rate variability (HRV) refers to the minute fluctuations in the heartbeat interval, reflecting the strength of the heart's autonomic regulatory ability. It is jointly regulated by the autonomic nervous system (sympathetic and parasympathetic nervous systems). A higher HRV value generally indicates a stronger ability of the body to adapt to environmental changes, while a lower HRV value may indicate stress, fatigue, or disease risk. Both the first and second HRV data are the average of signal data collected by the ECG acquisition module within a preset time period. The preset time period corresponding to the first HRV data is greater than or equal to the preset time period corresponding to the second HRV data.

[0026] The first and second sleep quality data can be collected using sleep monitoring devices.

[0027] The first Pittsburgh sleep quality score was obtained based on the first sleep quality data before treatment and the standardized PSQI scale. The second Pittsburgh sleep quality score was obtained based on the second sleep quality data after treatment and the same version of the PSQI scale. The PSQI scale is the Pittsburgh Sleep Quality Index, a general scale for insomnia assessment. It includes seven dimensions: sleep quality, sleep onset time, sleep duration, sleep efficiency, sleep disturbances, hypnotics, and daytime dysfunction. Each dimension is scored from 0 to 3 points according to severity, with a total score ranging from 0 to 21 points. A higher score indicates worse sleep quality.

[0028] S3: Obtain the sleep quality change rate based on the first sleep quality data and the second sleep quality data; obtain the heart rate variability change rate based on the first heart rate variability data and the second heart rate variability data. The sleep quality change rate includes the sleep latency change rate, total sleep time change rate, sleep efficiency change rate, and awakening frequency change rate.

[0029] S4: The efficacy level of percutaneous vagus nerve stimulation therapy is obtained based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score; Please see Figure 2 Step S4 includes: S41: Based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score, obtain the difference in sleep quality scores before and after treatment; Calculate the PSQI score reduction (sleep quality score difference) for each patient before and after treatment: ; in, A poor sleep quality score indicates... The first Pittsburgh sleep quality score, Second Pittsburgh Sleep Quality Score.

[0030] S42: The sleep quality reduction rate is obtained based on the ratio of the sleep quality score difference to the first Pittsburgh sleep quality score; The sleep quality deduction rate is obtained using the following formula:

[0031] in, A poor sleep quality score indicates... The first Pittsburgh sleep quality score.

[0032] S43: Based on the preset correspondence between the sleep quality reduction rate and the therapeutic effect level, obtain the therapeutic effect level corresponding to the sleep quality reduction rate.

[0033] Based on the calculated sleep quality score reduction rate (PSQI reduction rate), it is mapped to a therapeutic effect level according to a preset standard and used as a label variable for model training: Complete recovery: PSQI score reduction rate ≥75%; Effective: 50% ≤ PSQI score reduction rate < 75%; Effective: 25% ≤ PSQI deduction rate < 50%; Invalid: PSQI deduction rate < 25% (including cases where ΔS ≤ 0).

[0034] Calculation example: A patient's baseline PSQI total score was 16 before treatment and 4 after treatment. Then ΔS = 16 - 4 = 12 points, PSQI reduction rate = (12 / 16) × 100% = 75%, and its efficacy level corresponds to the cure level.

[0035] S5: Through multiple linear regression analysis, obtain several heart rate data change rates related to the efficacy level from the heart rate variability data change rate; Among them, the rate of change of several heart rate data items includes indicators whose correlation coefficients are all greater than 0.6, such as the rate of change of SDNN indicator, the rate of change of RMSSD indicator, and the rate of change of pNN50 indicator.

[0036] The SDNN (Standard Deviation of Normal-to-Normal Intervals) index is a core time-domain indicator in heart rate variability (HRV) analysis, used to assess the balance and adaptability of the autonomic nervous system in regulating the heart.

[0037] The RMSSD (root mean square of the difference between adjacent normal heartbeats) index is one of the core indicators of heart rate variability (HRV), mainly reflecting the activity of the parasympathetic nervous system (vagus nerve). The higher the value, the stronger the parasympathetic regulation ability in the autonomic nervous system, and the more flexible the short-term fluctuations in heart rhythm. It is usually associated with a good recovery state, relaxed mood, and cardiopulmonary adaptation.

[0038] The pNN50 index is an important time-domain indicator of heart rate variability (HRV), primarily reflecting the short-term regulatory capacity of the parasympathetic nervous system (vagus nerve). An elevated value usually indicates a relaxed and well-recovered state of mind and body, while a low value may suggest autonomic nervous system dysfunction or potential health risks.

[0039] S6: Based on the sleep quality change rate of the multiple insomnia patients, the change rate of several heart rate data, and the corresponding efficacy scores, train a random forest model to obtain an auricular vagus nerve stimulation insomnia efficacy evaluation model. S7: Input the actual sleep quality change rate and several actual heart rate data change rates of the target patient after percutaneous vagus nerve stimulation treatment into the vagus nerve stimulation insomnia efficacy evaluation model to obtain the vagus nerve stimulation insomnia efficacy score of the target patient.

[0040] Taking one patient with sleep maintenance disorder as an example, before treatment, the baseline SDNN was 85ms, RMSSD was 22ms, pNN50 was 5%, sleep latency was 45min, total sleep time was 4h, and sleep efficiency was 60%. After 4 weeks of taVNS treatment, the SDNN was 102ms, RMSSD was 30ms, pNN50 was 8%, sleep latency was 30min, total sleep time was 6h, and sleep efficiency was 85%.

[0041] The change rates of various indicators were calculated: SDNN change rate was 20%, RMSSD change rate was 36.4%, pNN50 change rate was 60%, sleep latency change rate was 33.3%, total sleep time change rate was 50%, sleep efficiency change rate was 41.7%, and number of awakenings change rate was -60% (reduction in the number of awakenings). These change rates were substituted into the auricular vagus nerve stimulation insomnia efficacy evaluation model, and the auricular vagus nerve stimulation insomnia efficacy score for this patient was calculated to be 78 points. The corresponding efficacy level can also be obtained based on the efficacy score. Then, the insomnia patient's insomnia type, auricular vagus nerve stimulation insomnia efficacy score, efficacy level, and change data of each core indicator can be output to the taVNS closed-loop control system. The system fine-tunes the stimulation parameters (appropriately reducing the stimulation amplitude and lengthening the pulse width) based on the feedback results to further optimize the treatment effect.

[0042] The core of the taVNS closed-loop control system is the linkage logic of "therapeutic effect assessment results - core indicator change trends - dynamic adjustment of stimulation parameters". The system has a built-in taVNS stimulation parameter base library (including four core adjustable parameters: amplitude, pulse width, frequency, and stimulation duration). Based on the change rate of HRV core indicators (SDNN, RMSSD, pNN50) and the change rate of sleep quality core indicators, as well as their change trends, and combined with the insomnia improvement efficacy score / level, it formulates graded and dimensional parameter adjustment rules. The adjustment process is a closed-loop process of real-time acquisition - data input - rule matching - parameter output - stimulation execution. The specific operation process is as follows: (a) Data input and threshold setting before adjustment The efficacy evaluation model standardizes and outputs the insomnia improvement efficacy score (0-100 points), efficacy level (cured / significantly effective / effective / ineffective), HRV core indicator change rate (SDNN%, RMSSD%, pNN50%), and sleep quality core indicator change rate (sleep latency%, total sleep time, sleep efficiency, number of awakenings%) to the taVNS closed-loop control system. The system preset thresholds for the rate of change of indicators and the threshold for efficacy scores as the basis for parameter adjustment (the thresholds were optimized based on clinical data from 120 validation samples and can be fine-tuned according to different insomnia subtypes). The results are shown in the table below:

[0043] (II) Core Adjustment Rules and Implementation Process The baseline values ​​for taVNS stimulation parameters are: amplitude 0.5-2.0 mA, pulse width 100-500 μs, frequency 10-30 Hz, and single stimulation duration 20-40 min (preset baseline values ​​according to insomnia type: frequency 20-30 Hz for difficulty falling asleep, pulse width 300-500 μs for sleep maintenance disorder, single stimulation duration 30-40 min for early awakening, and comprehensive baseline values ​​for mixed types). The system employs a four-level adjustment strategy of "maintenance-fine-tuning-optimization-re-adjustment" based on the therapeutic effect level from high to low. The adjustment range is matched to the specific values ​​of the core indicator change rate, and the single-step adjustment range does not exceed 20% of the baseline value to avoid physiological discomfort caused by parameter mutations. The specific strategy is as follows: 1. Recovery Level (score ≥ 85 points): Maintain current parameters and monitor dynamically. Judgment criteria: The efficacy score is ≥85 points, and all HRV core indicators and sleep quality core indicators have reached the positive change threshold; Adjustment procedure: Keep the current stimulation parameters (amplitude, pulse width, frequency, stimulation duration) unchanged, and adjust the taVNS stimulation frequency from once a day to once every other day to enter the consolidation treatment phase; Monitoring requirements: Continue to collect patient HRV and sleep quality indicators. If the indicators remain positive for two consecutive weeks, gradually reduce the stimulation amplitude (0.2 mA each time) until the minimum effective amplitude is reached.

[0044] 2. Significant Effect Level (70-84 points): Fine-tune parameters to enhance the improvement effect. Judgment criteria: efficacy score of 70-84, all core HRV indicators reaching the positive change threshold, and 1-2 sleep quality indicators not reaching the positive change threshold (such as sleep latency shortening by less than 20% or the number of awakenings decreasing by less than 30%). Adjustment procedure: Based on sleep quality indicators that have not reached the threshold, fine-tune a single parameter (adjustment range 5%-10% of the base value), specific matching relationship: Insufficient improvement in sleep latency: Appropriately increase the stimulation frequency (+5Hz) and shorten the duration of a single stimulation (-5min). Insufficient improvement in the number of awakenings: Appropriately increase the pulse width (+50μs) while maintaining the amplitude; Insufficient improvement in total sleep time / sleep efficiency: Appropriately increase amplitude (+0.2mA) and decrease frequency (-5Hz); Example: For a patient with sleep maintenance disorder (efficacy score 78, significant effect), the number of awakenings has reached the positive threshold, and the improvement in sleep latency is close to the threshold. Therefore, the stimulation amplitude is reduced (-0.2mA) and the pulse width is increased (+50μs).

[0045] 3. Effectiveness Level (50-69 points): Multi-parameter optimization, targeted improvement of core indicators. Judgment criteria: efficacy score of 50-69 points, 1-2 core HRV indicators reaching the positive change threshold, and 2 or more sleep quality indicators failing to reach the positive change threshold; Adjustment procedure: First, identify the core HRV indicators that have not reached the threshold (HRV indicators are the core physiological feedback of neural regulation effects). Prioritize adjusting parameters to improve HRV indicators, and then optimize by matching sleep quality indicators. The adjustment range is 10%-15% of the base value. Specific matching details are as follows: Insufficient SDNN rate of change: Increase stimulus amplitude (+0.3mA) and prolong single stimulus duration (+5min). Insufficient RMSSD / pNN50 change rate: Increase pulse width (+100μs), increase frequency (+5Hz). Multiple indicators are insufficient: Adjustment is made using a combination of "amplitude + pulse width", while frequency and duration remain at their base values; Implementation requirements: After optimization, continue treatment for 1 week, re-collect indicators and calculate the rate of change. If the HRV indicator reaches the positive threshold, then adjust the sleep-related parameters separately.

[0046] 4. Ineffective level (<50 points): Readjust baseline parameters and change the stimulus regimen. Judgment criteria: efficacy score <50 points, one or more HRV core indicators showing negative changes, or three or more sleep quality indicators showing negative changes; Adjustment operation: Immediately suspend the current stimulation protocol, re-collect the patient's baseline HRV and sleep quality indicators, and rule out ineffectiveness due to the patient's physiological state or device wearing issues; If external factors are excluded, reset the basic stimulation parameters (adjust by 15%-20% of the base value) and change the core adjustment dimensions according to the insomnia type: focus on frequency + pulse width for difficulty falling asleep, focus on amplitude + duration for sleep maintenance disorder, and make small adjustments to all parameters for early awakening / mixed type. Three days after the new regimen is implemented, the first set of indicators will be collected for an initial evaluation of efficacy. If the HRV indicator shows a positive change, the regimen will continue; if it still shows a negative change, the patient's suitability for taVNS treatment will be reassessed.

[0047] (III) Feedback and Iteration after Adjustment After the stimulation parameters are adjusted, the taVNS device performs stimulation according to the new parameters, and the system collects dynamic HRV indicators and sleep quality indicators in real time within 24 hours after treatment. The collected data is summarized weekly, the rate of change of indicators is calculated and substituted into the efficacy evaluation model to obtain the insomnia improvement efficacy score and grade again; Based on the new efficacy evaluation results, the system re-matches the above four-level adjustment strategy to achieve continuous iteration of "parameter adjustment - efficacy evaluation - readjustment" until the patient reaches the cure / significant effect level and enters the consolidation treatment stage.

[0048] (iv) Subtype adaptation adjustment and supplementation For patients with different types of insomnia, the system adapts the parameter adjustment priority based on the above general adjustment rules: Difficulty falling asleep: Frequency > Pulse width > Amplitude > Duration; Sleep maintenance disorder type: pulse width > amplitude > duration > frequency; Early awakening type: Duration > Pulse width > Amplitude > Frequency; Hybrid type: Amplitude > Pulse Width > Frequency > Duration.

[0049] It should be noted that, to improve data accuracy, this embodiment employs the 3σ criterion to remove outliers from HRV (heart rate variability) and sleep quality data, uses moving averages for data smoothing, and employs linear interpolation to fill in missing values, ensuring data validity. The execution steps include: (a) 3σ criterion for outlier removal The HRV index datasets (SDNN, RMSSD, pNN50) and sleep quality index datasets (sleep latency, total sleep time, sleep efficiency, and number of awakenings) were grouped by individual index, and the mean μ and standard deviation σ of each group were calculated. An outlier threshold was set: data values ​​exceeding the range [μ-3σ, μ+3σ] were considered outliers. All index data of all samples were validated row by row, outliers were removed, and the corresponding data positions were marked for subsequent missing value completion. After outlier removal, the effective data ratio of the single index dataset must be ≥95%. If it is lower than this ratio, the sample data collection process is re-verified to exclude batch anomalies caused by collection equipment failure.

[0050] (ii) Moving average method for data smoothing For the time-series HRV data after removing outliers, a simple moving average method with a 5-point sliding window was used for smoothing. The sleep quality index was a periodic statistical value (daily / weekly), which was processed using a 3-point sliding window. Sliding window calculation rules: For the nth data point in the time series data, its smoothing value = (n-2th data point + n-1th data point + nth data point + n+1th data point + n+2th data point) / 5 (5-point window). The first and last data points are supplemented with missing values ​​in the window using the first and last extension method. The core purpose of data smoothing is to eliminate random errors caused by physiological fluctuations and equipment noise during the data collection process, and to ensure the temporal stability of the indicator data.

[0051] (iii) Linear interpolation method to complete missing values The missing locations marked after outlier removal, as well as naturally missing values ​​caused by equipment offline or signal interruption during the data collection process, are filled in. Only cases with ≤3 consecutive missing data points are processed. If more than 3 consecutive missing data points are found, all data for the corresponding time period of the sample are removed. Linear interpolation calculation rules: Let the location of the missing value be... The nearest valid data point before and after it is (numerical value) ), (numerical value) (), then missing values ; After missing values ​​are filled in, all indicators for all samples are free of null values, completing the entire preprocessing process and outputting a standardized dataset for subsequent indicator change rate calculation and model training.

[0052] In a feasible embodiment, S6: the step of training a random forest model based on the sleep quality change rate of the multiple insomnia patients, the change rate of several heart rate data, and the corresponding efficacy scores to obtain an ear vagus nerve stimulation insomnia efficacy evaluation model includes: S61: Using the sleep quality change rate and the heart rate change rate of the multiple insomnia patients as inputs and the efficacy score as output, construct a sample set; S62: Train the random forest model based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation for insomnia.

[0053] In a feasible embodiment, S62: the step of training the random forest model based on the sample set to obtain the vagus nerve stimulation insomnia efficacy evaluation model includes: S621: Divide the sample set into a training set and a test set; wherein the ratio of the training set to the test set is 7:3.

[0054] S622: Train the random forest model based on the training set to obtain a candidate insomnia efficacy evaluation model; S623: Validate the candidate insomnia efficacy evaluation model according to the test set to obtain the ear vagus nerve stimulation insomnia efficacy evaluation model that passes the test.

[0055] Compared to related technologies, this application is the first to construct a quantitative evaluation model for the efficacy of taVNS (transcutaneous auricular vagus nerve stimulation) in treating insomnia based on HRV (heart rate variability) data. This model quantitatively correlates HRV indicators with the degree of insomnia improvement, solving the problem of existing technologies relying on subjective scales for efficacy evaluation and improving the objectivity, quantification, and accuracy of efficacy assessment. Furthermore, the HRV data used in the sample set is selected through multiple linear regression to identify indicators with high correlation to efficacy levels, effectively improving the model's evaluation accuracy and robustness. This model is applicable to patients with different insomnia subtypes. Moreover, the taVNS insomnia efficacy score output by the trained taVNS insomnia treatment closed-loop control system can be directly used as feedback for the system, achieving seamless integration of efficacy evaluation and closed-loop control. This provides an executable reference standard for subsequent dynamic adjustment of stimulation parameters and personalized optimization of treatment plans.

[0056] Please see Figure 3 The second embodiment of this application provides a device 100 for evaluating the efficacy of auricular vagus nerve stimulation for insomnia, comprising: The pre-treatment data acquisition module 101 is used to collect the first heart rate variability data, the first sleep quality data, and the first Pittsburgh sleep quality score corresponding to the first sleep quality data of multiple insomnia patients before treatment. The post-treatment data acquisition module 102 is used to collect the second heart rate variability data, the second sleep quality data, and the second Pittsburgh sleep quality score corresponding to the second sleep quality data after each percutaneous vagus nerve stimulation treatment for the insomnia patient. The data change rate acquisition module 103 is used to acquire the sleep quality change rate based on the first sleep quality data and the second sleep quality data; and to acquire the heart rate variability data change rate based on the first heart rate variability data and the second heart rate variability data. The efficacy level acquisition module 104 is used to obtain the efficacy level of percutaneous vagus nerve stimulation therapy based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score. The heart rate data change rate acquisition module 105 is used to acquire several heart rate data change rates related to the therapeutic effect level from the heart rate variability data change rate through multiple linear regression analysis. The insomnia efficacy assessment model acquisition module 106 is used to train a random forest model based on the sleep quality change rate of the multiple insomnia patients, the change rate of several heart rate data, and the corresponding efficacy scores to obtain the auricular vagus nerve stimulation insomnia efficacy assessment model. The insomnia efficacy scoring module 107 is used to input the actual sleep quality change rate and the change rate of several actual heart rate data after the target patient undergoes percutaneous vagus nerve stimulation treatment into the vagus nerve stimulation insomnia efficacy evaluation model to obtain the vagus nerve stimulation insomnia efficacy score of the target patient.

[0057] In one feasible embodiment, the efficacy level acquisition module 104 is used to perform the following steps: Based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score, obtain the difference in sleep quality scores before and after treatment; The sleep quality reduction rate is obtained by comparing the difference in sleep quality scores with the first Pittsburgh sleep quality score. Based on the preset correspondence between the quality reduction rate and the therapeutic effect level, the therapeutic effect level corresponding to the sleep quality reduction rate is obtained.

[0058] In one feasible embodiment, the insomnia treatment efficacy assessment model acquisition module 106 is used to perform the following steps: Based on the first and second heart rate variability data corresponding to the aforementioned target heart rate variability indicators, the rate of change of several indicator data is obtained. The sample set is constructed by taking the rate of change in sleep quality and the rate of change in several indicators of the multiple insomnia patients as inputs and the efficacy score as output. The random forest model is trained based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation in insomnia.

[0059] In one feasible embodiment, the step of training the random forest model based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation for insomnia includes: The sample set is divided into a training set and a test set; The random forest model is trained based on the training set to obtain a candidate insomnia efficacy evaluation model. The candidate insomnia efficacy evaluation model was validated and tested using the test set to obtain the insomnia efficacy evaluation model that passed the test via auricular vagus nerve stimulation.

[0060] It should be noted that the vagus nerve stimulation insomnia efficacy assessment device provided in the second embodiment of this application is only illustrated by the above-described division of functional modules when performing the vagus nerve stimulation insomnia efficacy assessment method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the vagus nerve stimulation insomnia efficacy assessment device provided in the second embodiment of this application and the vagus nerve stimulation insomnia efficacy assessment method of the first embodiment of this application belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.

[0061] The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0062] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function selected in one or more boxes.

[0064] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function selected in one or more boxes.

[0065] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0066] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0067] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0068] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0069] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for evaluating the therapeutic effect of vagus nerve stimulation on insomnia, characterized in that, include: We collected first heart rate variability data, first sleep quality data, and first Pittsburgh sleep quality scores corresponding to the first sleep quality data from multiple insomnia patients before treatment. The second heart rate variability data, second sleep quality data, and the second Pittsburgh sleep quality score corresponding to the second sleep quality data were collected from the insomnia patients after each percutaneous vagus nerve stimulation treatment. Based on the first sleep quality data and the second sleep quality data, obtain the sleep quality change rate; based on the first heart rate variability data and the second heart rate variability data, obtain the heart rate variability data change rate; The efficacy level of percutaneous vagus nerve stimulation therapy was determined based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score. Through multiple linear regression analysis, several heart rate data change rates related to the therapeutic effect level were obtained from the heart rate variability data change rate. Based on the rate of change in sleep quality of the multiple insomnia patients, the rate of change in several heart rate data, and the corresponding efficacy scores, a random forest model was trained to obtain an evaluation model for the efficacy of vagus nerve stimulation for insomnia. The actual sleep quality change rate and several actual heart rate data change rates of the target patients after percutaneous vagus nerve stimulation treatment were input into the vagus nerve stimulation insomnia efficacy evaluation model to obtain the vagus nerve stimulation insomnia efficacy score of the target patients.

2. The method for evaluating the efficacy of vagus nerve stimulation for insomnia according to claim 1, characterized in that, The steps for determining the efficacy level of percutaneous vagus nerve stimulation therapy based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score include: Based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score, obtain the difference in sleep quality scores before and after treatment; The sleep quality reduction rate is obtained by comparing the difference in sleep quality scores with the first Pittsburgh sleep quality score. Based on the preset correspondence between the quality reduction rate and the therapeutic effect level, the therapeutic effect level corresponding to the sleep quality reduction rate is obtained.

3. The method for evaluating the efficacy of vagus nerve stimulation for insomnia according to claim 1, characterized in that, The steps for obtaining the vagus nerve stimulation insomnia efficacy assessment model by training a random forest model based on the sleep quality change rate, the heart rate change rate, and the corresponding efficacy scores of the multiple insomnia patients include: The sample set is constructed by taking the rate of change in sleep quality and the rate of change in several heart rate data of the multiple insomnia patients as inputs and the efficacy score as output. The random forest model is trained based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation in insomnia.

4. The method for evaluating the therapeutic effect of vagus nerve stimulation on insomnia according to claim 3, characterized in that, The steps for training the random forest model based on the sample set to obtain the vagus nerve stimulation insomnia efficacy evaluation model include: The sample set is divided into a training set and a test set; The random forest model is trained based on the training set to obtain a candidate insomnia efficacy evaluation model. The candidate insomnia efficacy evaluation model was validated and tested using the test set to obtain the insomnia efficacy evaluation model that passed the test via auricular vagus nerve stimulation.

5. The method for evaluating the efficacy of auricular vagus nerve stimulation for insomnia according to any one of claims 1-4, characterized in that, The rate of change of the aforementioned heart rate data includes the rate of change of the SDNN index, the rate of change of the RMSSD index, and the rate of change of the pNN50 index.

6. The method for evaluating the efficacy of auricular vagus nerve stimulation for insomnia according to any one of claims 1-4, characterized in that, The sleep quality change rate includes the sleep latency change rate, total sleep time change rate, sleep efficiency change rate, and number of awakenings change rate.

7. A device for evaluating the therapeutic effect of vagus nerve stimulation on insomnia, characterized in that, include: The pre-treatment data acquisition module is used to collect the first heart rate variability data, the first sleep quality data, and the first Pittsburgh sleep quality score corresponding to the first sleep quality data of multiple insomnia patients before treatment. The post-treatment data acquisition module is used to collect the second heart rate variability data, the second sleep quality data, and the second Pittsburgh sleep quality score corresponding to the second sleep quality data after each percutaneous vagus nerve stimulation treatment for the insomnia patients. The data change rate acquisition module is used to acquire the sleep quality change rate based on the first sleep quality data and the second sleep quality data; and to acquire the heart rate variability data change rate based on the first heart rate variability data and the second heart rate variability data. The efficacy level acquisition module is used to obtain the efficacy level of percutaneous vagus nerve stimulation therapy based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score. The heart rate data change rate acquisition module is used to obtain several heart rate data change rates related to the efficacy level from the heart rate variability data change rate through multiple linear regression analysis. The insomnia efficacy evaluation model acquisition module is used to train a random forest model based on the sleep quality change rate, the heart rate data change rate, and the corresponding efficacy score of the multiple insomnia patients to obtain the vagus nerve stimulation insomnia efficacy evaluation model. The insomnia efficacy scoring module is used to input the actual sleep quality change rate and the change rate of several actual heart rate data after percutaneous vagus nerve stimulation treatment into the vagus nerve stimulation insomnia efficacy evaluation model to obtain the vagus nerve stimulation insomnia efficacy score of the target patient.

8. The device for evaluating the efficacy of vagus nerve stimulation for insomnia according to claim 7, characterized in that, The efficacy level acquisition module is used to perform the following steps: Based on the first Pittsburgh sleep quality score and the second Pittsburgh sleep quality score, obtain the difference in sleep quality scores before and after treatment; The sleep quality reduction rate is obtained by comparing the difference in sleep quality scores with the first Pittsburgh sleep quality score. Based on the preset correspondence between the quality reduction rate and the therapeutic effect level, the therapeutic effect level corresponding to the sleep quality reduction rate is obtained.

9. The device for evaluating the efficacy of vagus nerve stimulation for insomnia according to claim 7, characterized in that, The insomnia treatment efficacy assessment model acquisition module is used to perform the following steps: Based on the first and second heart rate variability data corresponding to the aforementioned target heart rate variability indicators, the rate of change of several indicator data is obtained. The sample set is constructed by taking the rate of change in sleep quality and the rate of change in several indicators of the multiple insomnia patients as inputs and the efficacy score as output. The random forest model is trained based on the sample set to obtain an evaluation model for the efficacy of vagus nerve stimulation in insomnia.

10. The device for evaluating the efficacy of vagus nerve stimulation for insomnia according to claim 9, characterized in that, The steps for training the random forest model based on the sample set to obtain the vagus nerve stimulation insomnia efficacy evaluation model include: The sample set is divided into a training set and a test set; The random forest model is trained based on the training set to obtain a candidate insomnia efficacy evaluation model. The candidate insomnia efficacy evaluation model was validated and tested using the test set to obtain the insomnia efficacy evaluation model that passed the test via auricular vagus nerve stimulation.

Images