A reproductive function state evaluation system based on multi-modal physiological data

Abstract

The present application relates to the technical field of reproductive function state evaluation, and particularly relates to a reproductive function state evaluation system based on multi-modal physiological data. The system comprises: a data acquisition module for acquiring blood glucose, heart rate, acceleration data and follicle diameter; a data analysis module for dividing sleep and wake-up periods, calculating blood glucose deficiency degree in the sleep period, and determining the correlation of blood glucose and heart rate reverse linkage events in the wake-up period to determine the synchronization degree of nerve-metabolic regulation stiffness; a physiological resistance index acquisition module for calculating the physiological resistance index according to the blood glucose deficiency degree, the reverse linkage frequency gained by the synchronization degree, and the follicle diameter susceptibility weight; and a data processing module for obtaining the evaluation result in combination with the follicle growth condition and the physiological resistance index. The present application quantifies the nerve-metabolic stiffness and the environmental resistance, solves the problem that it is difficult to distinguish between insufficient drug dosage and excessive body environmental resistance, and effectively improves the accuracy of reproductive function state evaluation.

Description

Technical Field

[0001] This invention relates to the field of reproductive function status assessment technology, and specifically to a reproductive function status assessment system based on multimodal physiological data. Background Technology

[0002] Polycystic ovary syndrome (PCOS) is a leading cause of ovulation disorders in women of reproductive age. One of its clinical features is the unexpected growth arrest or atresia of the dominant follicle in the late stages of development, leading to failure of ovulation induction treatment. Modern reproductive physiology research indicates that PCOS patients often have specific pathological mechanisms: on the one hand, the lack of nocturnal energy metabolism homeostasis (such as hypoglycemia) can induce a rebound of stress hormones, inhibiting the luteinizing hormone pulse; on the other hand, the sympathetic nervous system's response to metabolic fluctuations exhibits pathological rigidity, leading to excessive vasoconstriction of the ovaries and blocking blood perfusion. These microscopic physiological resistances can form a strong resistance against the effects of drugs.

[0003] Current clinical monitoring methods mainly rely on transvaginal ultrasound and serum hormone testing. However, ultrasound examination has a time lag, reflecting the final morphological results. When follicular growth arrest is observed, it means that the follicle has been damaged irreversibly. Secondly, serum hormone testing has a time lag, reflecting only the instantaneous state at the time of blood collection, and it is difficult to capture continuous physiological fluctuations such as nocturnal hypoglycemia or daytime autonomic nervous system dysregulation.

[0004] Therefore, existing technologies lack the ability to integrate continuous physiological signals and morphological data, making it impossible to accurately quantify and assess complex neuro-metabolic coupling resistance. This leads to difficulties in distinguishing between insufficient drug dosage and excessive body environmental resistance, thus hindering the accurate control of ovulation-inducing drug dosage and affecting the accurate treatment of polycystic ovary syndrome. Summary of the Invention

[0005] To address the technical problem of inaccurate reproductive function assessment caused by the lack of quantitative methods for assessing the stiffness of neuro-metabolic coupling in existing technologies, which makes it impossible to accurately evaluate the dynamic resistance of the body environment to follicle development, the present invention aims to provide a reproductive function assessment system based on multimodal physiological data. The specific technical solution adopted is as follows:

[0006] This invention provides a reproductive function status assessment system based on multimodal physiological data, the system comprising:

[0007] The data acquisition module is used to acquire blood glucose data, heart rate data, and body motion acceleration data of the target object at each moment within a specified time period; and to acquire the observed value of the follicle diameter of the target object.

[0008] The data analysis module is used to divide a specified time period into sleep and wake periods based on changes in body motion acceleration data; to obtain the degree of glucose deficit during sleep based on the difference between blood glucose data and a preset blood glucose baseline; and to identify inverse linkage event segments between blood glucose data and heart rate data during wake periods, and to obtain the degree of synchronization characterizing the stiffness of neuro-metabolic regulation based on the correlation between changes in blood glucose data and heart rate data within the inverse linkage event segments.

[0009] The physiological resistance index acquisition module is used to obtain the physiological resistance index of the target object based on the degree of glucose deficit, the result of nonlinear gain processing of the frequency of reverse linkage event segments using the degree of synchronization, and the nonlinear mapping result of the observed follicle diameter.

[0010] The data processing module is used to obtain assessment results of reproductive function status based on changes in observed follicle diameter and in combination with the physiological resistance index.

[0011] Furthermore, the method for obtaining the sleep period and wakefulness period is as follows:

[0012] The first sliding window is slid in chronological order within a specified time period to obtain the variance of the body motion acceleration data within the time period corresponding to each sliding window, and then arranged in the order of acquisition to obtain the acceleration variance sequence.

[0013] The time periods corresponding to consecutive variance values ​​in the acceleration variance sequence that are less than a preset rest threshold are taken as sleep periods;

[0014] The time period excluding sleep within the specified time frame is designated as the waking period.

[0015] Furthermore, the method for obtaining the degree of glucose deficit is as follows:

[0016] For any point in time during sleep, the difference between the preset blood glucose baseline and the blood glucose data at that point will be used as the blood glucose missing value at that point.

[0017] When the missing blood glucose analysis value is greater than or equal to 0, the missing blood glucose analysis value is taken as the missing blood glucose value at that moment.

[0018] When the blood glucose missing value is less than 0, 0 is taken as the blood glucose missing value at that moment;

[0019] The sum of the glucose deficit values ​​at all times during the sleep period is used as the degree of glucose deficit during the sleep period.

[0020] Furthermore, the method for obtaining the reverse linkage event fragment is as follows:

[0021] The second sliding window is slid in chronological order during the waking period, and the end time of each slide is taken as the analysis time for each slide.

[0022] For any analysis time, the slope of the straight line fitted by the blood glucose data in the local time period corresponding to that analysis time according to the time order is obtained, and it is used as the first change value for that analysis time.

[0023] The slope of the straight line fitted by the heart rate data of the local time period corresponding to the sliding moment at the analysis time is obtained in chronological order and used as the second change value at the analysis time.

[0024] When the first change value is less than the preset decreasing threshold and the second change value is greater than the preset increasing threshold, the analysis time is marked as the reverse linkage time.

[0025] Each reverse linkage moment and its preset neighboring analysis moment constitute a segment as a reverse linkage event segment; wherein, if a certain reverse linkage moment is the preset neighboring analysis moment of another preceding reverse linkage moment, the reverse linkage event segment corresponding to that reverse linkage moment is not acquired.

[0026] Furthermore, the method for obtaining the degree of synchronization is as follows:

[0027] For any reverse linkage event segment, the first change value at each analysis time within the reverse linkage event segment is arranged in chronological order to obtain the first change sequence;

[0028] Arrange the second change values ​​at each analysis time point within the reverse linkage event segment in chronological order to obtain the second change sequence;

[0029] The absolute value of the Pearson correlation coefficient between the first and second change sequences is taken as the degree of correlation of the reverse linkage event segment.

[0030] The mean of the correlation of all reverse-linked event segments is used as the synchronization degree characterizing the stiffness of neuro-metabolic regulation.

[0031] Furthermore, the method for obtaining the physiological resistance index is as follows:

[0032] The product of the first preset damping coefficient and the degree of glucose deficit is used as the metabolic deficit characteristic value.

[0033] The result of nonlinear gain processing of the frequency of reverse linkage event segments using the degree of synchronization is used as the rigid feature value of neural regulation.

[0034] The result of vector synthesis of metabolic deficit eigenvalues ​​and neural regulatory rigidity eigenvalues ​​is used as the baseline inhibition rate.

[0035] The difference between the observed follicle diameter and the preset critical threshold, and the result of a nonlinear mapping, is used as the susceptibility weight.

[0036] The product of susceptibility weight and baseline inhibition rate is used as the physiological resistance index of the target object.

[0037] Furthermore, the formula for calculating the neural regulation rigidity characteristic value is as follows:

[0038] In the formula, Y is the rigidity characteristic value of neural regulation; N is the number of reverse linkage event segments; and C is the degree of synchronization. The second preset damping coefficient; This is the preset gain coefficient.

[0039] Furthermore, the formula for calculating the susceptibility weight is as follows:

[0040] In the formula, Susceptibility weight; This is the current observed value of the follicle diameter; This is a preset critical threshold; is the preset variation factor; exp is an exponential function with the natural constant as the base.

[0041] Furthermore, the method for obtaining the assessment results of the reproductive function status is as follows:

[0042] Follicle growth rate is obtained by comparing the current follicle diameter observation with the historical follicle diameter observation;

[0043] The ratio of follicular growth rate to physiological resistance index is used as the measure of growth and survival.

[0044] When the degree of growth and survival is greater than or equal to the preset safety threshold, the assessment result of reproductive function status is normal growth;

[0045] When the growth survival rate is less than the preset safety threshold, the sum of the metabolic deficit characteristic value and the neural regulation rigidity characteristic value is obtained as the first result;

[0046] The proportion of metabolic deficit feature values ​​in the first result is taken as the proportion of metabolic component.

[0047] When the proportion of metabolic components exceeds a preset threshold, the assessment result of reproductive function status is a lack of metabolic substrates.

[0048] When the proportion of metabolic components is less than or equal to a preset threshold, the assessment result of reproductive function status is neural pathway rigidity.

[0049] Furthermore, the method for obtaining the follicle growth rate is as follows:

[0050] The difference between the current follicle diameter observation and the previous follicle diameter observation is taken as the first difference;

[0051] The difference between the current follicle diameter observation time and the previous observation time is used as the first interval duration;

[0052] The ratio of the first difference to the first interval duration is taken as the follicle growth rate.

[0053] The present invention has the following beneficial effects:

[0054] This invention first divides the sleep and wake periods into specified time periods based on changes in body motion acceleration data, facilitating precise quantitative analysis of different physiological characteristics under the human circadian rhythm (nighttime metabolic inhibition and daytime neural stress). To quantify the potential inhibitory effect of nighttime energy metabolism homeostasis deficit on the endocrine axis, the degree of glucose deficit during sleep is obtained based on the difference between blood glucose data and a preset blood glucose baseline, accurately reflecting the cumulative load of nocturnal occult hypoglycemia events. To capture abnormal regulatory behavior of the autonomic nervous system in response to metabolic fluctuations during the day, reverse linkage event segments between blood glucose and heart rate data are identified during the wake period, accurately reflecting the stress moment when the body experiences sympathetic nerve excitation to compensate for the decrease in blood glucose, which is beneficial for statistically analyzing the frequency of neurovasoconstriction events. Furthermore, based on the correlation between changes in blood glucose and heart rate data within the reverse linkage event segments, the degree of synchronization characterizing the stiffness of neuro-metabolic regulation is obtained, accurately reflecting the sympathetic... The tightness of neural responses to metabolic fluctuations and the state of pathological lock-in are helpful in distinguishing between benign physiological regulation and malignant neuro-metabolic rigid coupling. Furthermore, based on the degree of glucose deficit and the results of nonlinear gain processing of the frequency of reverse linkage event segments using synchronization degree, combined with the nonlinear mapping results of follicle diameter observations, a physiological resistance index can be obtained for the target object. This accurately reflects the comprehensive dynamic resistance encountered by dominant follicle growth under the current neuro-metabolic coupling environment, facilitating the unified mapping of discrete multidimensional physiological signals into a continuous resistance rate index. To quantify and assess the dynamic antagonistic relationship between follicle growth dynamics and body environmental resistance, and based on changes in follicle diameter observations combined with the physiological resistance index, accurate assessment results of reproductive function status can be obtained. This helps to promptly identify hidden risks of follicle development arrest and pinpoint the specific pathological sources of high resistance (metabolic deficiency or neural rigidity), ensuring that subsequent clinical interventions are targeted and avoiding blindly increasing drug dosages. Attached Figure Description

[0055] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a structural block diagram of a reproductive function status assessment system based on multimodal physiological data, provided in one embodiment of the present invention.

[0057] Figure 2 A flowchart illustrating a method for obtaining a physiological resistance index according to an embodiment of the present invention;

[0058] Figure 3 This is a schematic diagram of a computer device provided according to an embodiment of the present invention. Detailed Implementation

[0059] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a reproductive function status assessment system based on multimodal physiological data proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0061] The following description, in conjunction with the accompanying drawings, details a specific scheme for a reproductive function status assessment system based on multimodal physiological data provided by the present invention.

[0062] Example 1:

[0063] This invention proposes a reproductive function status assessment system based on multimodal physiological data. Please refer to [link / reference]. Figure 1 The diagram shows a structural block diagram of a reproductive function status assessment system based on multimodal physiological data provided in an embodiment of the present invention. The system includes: a data acquisition module 10, a data analysis module 20, a physiological resistance index acquisition module 30, and a data processing module 40.

[0064] The data acquisition module 10 is used to acquire blood glucose data, heart rate data, and body motion acceleration data of the target object at each moment within a specified time period; and to acquire the observed value of the follicle diameter of the target object.

[0065] Specifically, for better description, this embodiment uses a single target object as an example for analysis; all subsequent references to the target object refer to the same object. To cover the complete diurnal physiological rhythm, this embodiment sets the specified time period to 12:00 PM the previous day to 12:00 PM the current day, a total of 24 hours, ensuring complete capture of physiological characteristics during nighttime sleep and daytime wakefulness. The implementer can adjust the size of the specified time period according to actual circumstances; this is not limited here, but the specified time period must cover the target object's complete sleep cycle. To obtain continuous physiological indicators for more accurate analysis of the target object's reproductive function, this embodiment uses a continuous glucose monitoring device and a heart rate monitoring device worn by the target object, as well as wearable sensors, to acquire glucose, heart rate, and body motion acceleration data at each moment within the specified time period. This facilitates accurate subsequent analysis of the target object's neuro-metabolic coupling state. This embodiment sets the collection of glucose, heart rate, and body motion acceleration data synchronously, with a data collection frequency of once per minute. The implementer can adjust the data collection frequency according to actual circumstances; this is not limited here.

[0066] Because the sensitivity of follicles to the body's microenvironment changes non-linearly with developmental stages, especially after the follicle diameter exceeds a certain threshold (usually 12 mm) and develops into a dominant follicle, granulosa cells begin to express luteinizing hormone receptors in large quantities. At this time, their susceptibility to metabolic stress and neurovascular contraction increases exponentially. To avoid false alarms for early follicles in the non-sensitive period and to ensure the relevance of the assessment results, this embodiment obtains the follicle diameter observation value of the target subject through ultrasound examination. Considering the low-frequency nature of ultrasound examinations (usually every few days), this embodiment obtains the most recent follicle diameter observation value from the medical database. If there is no latest ultrasound data at the current time, the system determines whether the time difference between the current time and the stored most recent observation time is less than a preset validity window. If it is less, a zero-order hold strategy is adopted, and the most recent follicle diameter observation value stored in the system is automatically used to ensure the continuity of subsequent model calculations. If it is greater than or equal to, the current follicle diameter data is marked as invalid, or a prompt is made to update the clinical data, and no further growth and survival degree calculation is performed. It should be noted that, considering the possibility of multiple developing follicles existing simultaneously in practice, to ensure the specificity of the kinetic assessment, this embodiment selects the dominant follicle with the largest diameter as the observed follicle diameter for the target object, and continuously tracks the growth trajectory of this specific follicle. If multiple dominant follicles with the largest diameter exist, one dominant follicle is selected for analysis. The zero-order maintenance strategy is well-known and will not be elaborated further.

[0067] It should be noted that before obtaining the assessment results of reproductive function status, it is necessary to check whether the current follicle diameter observation value is marked as invalid. If it is marked as invalid, the subsequent growth and survival calculation will not be performed, and a prompt signal that clinical imaging data needs to be updated will be directly output; if it is not marked as invalid, the subsequent calculation steps will be performed.

[0068] The data analysis module 20 is used to divide a specified time period into sleep and wake periods based on changes in body motion acceleration data; to obtain the degree of glucose deficit during sleep based on the difference between blood glucose data and a preset blood glucose baseline during sleep; and to identify reverse linkage event segments between blood glucose data and heart rate data during wake periods, and to obtain the degree of synchronization characterizing the stiffness of neuro-metabolic regulation based on the correlation between changes in blood glucose data and heart rate data within the reverse linkage event segments.

[0069] Specifically, considering that the pathological characteristics of patients with polycystic ovary syndrome manifest differently under diurnal rhythms (mainly metabolic inhibition at night and mainly neural stress during the day), in order to quantify these two distinct physiological resistances separately and ensure that the physiological basis of the assessment results is sufficient, the sleep period and wakefulness period are first divided based on the changes in body motion acceleration data, because the continuous low fluctuation of body motion acceleration data is the most intuitive basis for determining whether a person has entered a sleep state.

[0070] To accurately analyze the impact of nocturnal energy metabolism homeostasis on the endocrine axis and quantify the load of occult hypoglycemia, this study aims to determine the degree of glycemic deficit during sleep based on the difference between blood glucose data during sleep and a preset baseline. This accurately reflects the cumulative intensity of nocturnal hypoglycemic events and is beneficial for assessing the rebound effect of stress hormones (such as cortisol). A greater glycemic deficit indicates a more insufficient supply of energy substrates at night, resulting in stronger inhibition of luteinizing hormone pulses. Furthermore, to capture abnormal regulatory behavior of the daytime autonomic nervous system, this study identifies inversely linked events between blood glucose and heart rate data during wakefulness—specifically, moments when a sharp drop in blood glucose is accompanied by a sharp rise in heart rate. This is helpful for subsequently statistically analyzing the frequency of neurological stress events.

[0071] To further differentiate between benign physiological regulation and malignant pathological lock-in, and to enable the assessment model to distinguish different levels of pathological depth, the degree of synchronization characterizing the stiffness of neuro-metabolic regulation is obtained based on the correlation between changes in blood glucose and heart rate data within the reverse linkage event segment. This accurately reflects the tightness of the sympathetic nervous system's response to metabolic fluctuations, which is beneficial for quantifying the amplification factor of vasoconstriction effects. A greater degree of synchronization indicates a more rigid neuro-metabolic coupling and a higher risk of obstructed blood flow perfusion in the ovarian microcirculation.

[0072] Preferably, in one feasible embodiment, the method for obtaining sleep and wake periods is as follows: A first sliding window is slid sequentially within a specified time period, and the variance of body motion acceleration data within the corresponding time period of each sliding window is obtained. These variances are then arranged according to the acquisition order to obtain an acceleration variance sequence. The larger the variance, the more active the target patient's state is within the corresponding time period of the sliding window, and the less likely the target patient is to be in a sleep stage. Therefore, this embodiment sets a preset rest threshold as... (where g is the unit of gravitational acceleration) to ensure effective filtering of normal turning movements and breathing fluctuations during sleep, accurately locking in a deep state of stillness. The implementer can set the preset stillness threshold according to the actual situation, which is not limited here. Then, the time period corresponding to the variance value of consecutive values ​​less than the preset stillness threshold in the acceleration variance sequence is taken as the sleep period; the time period other than the sleep period within the specified time period is taken as the wake period. In order to balance the stability and sensitivity of sleep state detection and avoid sleep segmentation caused by brief body movements, this embodiment sets the duration of the first sliding window to 15 minutes and the sliding step size to 1 minute, ensuring that the time resolution is high enough and that high-frequency noise can be smoothed out. The implementer can set the duration of the first sliding window and the sliding step size according to the actual situation, which is not limited here.

[0073] Preferably, in one feasible embodiment, the method for obtaining the degree of glucose deficit is as follows: For any moment during the sleep period, the difference between the preset blood glucose baseline and the blood glucose data at that moment is taken as the blood glucose deficit analysis value at that moment; the larger the blood glucose deficit analysis value, the smaller the blood glucose data at that moment, indicating that the body's energy substrate supply is more scarce at that moment, and the higher the risk of triggering compensatory secretion of glucagon; in order to accurately quantify this metabolic pressure, when the blood glucose deficit analysis value is greater than or equal to 0, the blood glucose deficit analysis value is taken as the blood glucose deficit value at that moment; when the blood glucose deficit analysis value is less than 0, it indicates that the blood glucose level at that moment is higher than the blood glucose baseline, which is an energy-sufficient state. In order to avoid the negative value offsetting the real risk of glucose deficit, 0 is directly taken as the blood glucose deficit value at that moment; in order to comprehensively assess the metabolic load of the entire sleep cycle, the cumulative result of the blood glucose deficit values ​​at all moments during the sleep period is taken as the degree of glucose deficit during the sleep period.

[0074] The method for obtaining the preset blood glucose baseline is as follows: taking the start time of the sleep period as the origin, a time period corresponding to one hour preceding it is selected as the blood glucose baseline analysis period, because the blood glucose level before falling asleep usually represents an individual's resting metabolic baseline, ensuring the personalized setting of the baseline; the implementer can set the length of the blood glucose baseline analysis period according to the actual situation, which is not limited here; in order to obtain a stable baseline value, the average of all blood glucose data within the blood glucose baseline analysis period is used as the reference blood glucose baseline; considering that a high-carbohydrate diet before bedtime may lead to an artificially high reference baseline (e.g., postprandial blood glucose has not yet dropped), directly using this as the baseline would lead to the misjudgment of normal nighttime blood glucose as a deficit, therefore, the reference blood glucose baseline is compared with the preset upper limit of blood glucose, and the smaller value is used as the preset blood glucose baseline. In this embodiment, the preset upper limit of blood glucose is set to 6.1 mmol / L by referring to the normal range of fasting blood glucose, ensuring the objectivity of the evaluation benchmark. The implementer can set the preset upper limit of blood glucose according to the actual situation, which is not limited here.

[0075] Preferably, in one feasible manner of this embodiment, the method for obtaining the reverse linkage event segment is as follows: the second sliding window is slid in chronological order during the awake period, and the end time corresponding to each slide is taken as the analysis time of each slide, which accurately defines the time anchor point for the calculation of the rate of change, which is conducive to achieving high temporal resolution event capture; for any analysis time, the slope of the straight line fitted by the blood glucose data in the local time period corresponding to the analysis time according to the time order is obtained, which is taken as the first change value of the analysis time, which accurately reflects the instantaneous change trend of blood glucose at the analysis time;

[0076] To synchronously monitor the response state of the autonomic nervous system, the slope of the straight line fitted by the heart rate data of the local time period corresponding to the analysis moment is further obtained according to the time sequence. This slope is used as the second change value at the analysis moment to accurately reflect the instantaneous change trend of heart rate at the analysis moment. It is known that when blood glucose drops sharply, the body will release catecholamines by activating the sympathetic nervous system, resulting in a compensatory increase in heart rate. When the first change value is less than the preset decrease threshold and the second change value is greater than the preset increase threshold, the analysis moment is marked as the reverse linkage moment, that is, a neuro-metabolic reverse coupling stress event has occurred. In this embodiment, the preset decrease threshold is set to -0.06 mmol / L / min and the preset increase threshold is set to 2.0 bpm / min to ensure that strong stress events with significant physiological significance can be screened out. The implementer can set the size of the preset decrease threshold and the preset increase threshold according to the actual situation, which is not limited here.

[0077] In order to extract complete event waveforms for subsequent correlation analysis, each reverse linkage moment and its preset neighboring analysis moment are combined into a single reverse linkage event segment to ensure coverage of the entire process of stress response occurrence, development, and decline. If a certain reverse linkage moment is a preset neighboring analysis moment of another preceding reverse linkage moment, the reverse linkage event segment corresponding to that reverse linkage moment is not acquired to avoid repeated extraction and counting of the same physiological event. In this embodiment, the 10 analysis times immediately before and after each reverse linkage moment are used as its preset neighboring analysis times. If there are fewer than 10 analysis times before or after a certain reverse linkage moment, the reverse linkage event segment corresponding to that moment is not acquired (i.e., edge data is discarded), or the missing part is zero-filled to ensure that all reverse linkage event segments participating in subsequent calculations have the same vector dimension (e.g., all with 21 data points). To balance the smoothness and sensitivity of local trend fitting, this embodiment sets the duration of the second sliding window to 5 minutes and the sliding step size to 1 minute to ensure the stability of the rate of change calculation. Implementers can set the preset neighboring analysis times for each reverse linkage moment according to the actual situation. The duration and sliding step size of the second sliding window are not limited here.

[0078] It should be noted that the reverse linkage event specifically refers to the acute, strongly coupled pathological moment when the sympathetic nervous system responds immediately and strongly to metabolic fluctuations. Although the normal physiological regulatory process may have a delayed response, this approach focuses on extracting this most representative rigid-locked acute feature as an assessment basis to distinguish it from normal physiological regulation with a buffer delay.

[0079] Preferably, in one feasible embodiment, the method for obtaining the degree of synchronization is as follows: For any reverse linkage event segment, the first change value at each analysis time within the reverse linkage event segment is arranged in chronological order to obtain a first change sequence; the second change value at each analysis time within the reverse linkage event segment is arranged in chronological order to obtain a second change sequence; when the first change sequence and the second change sequence show a high linear correlation in waveform morphology, it indicates that the sympathetic nervous system's response to blood glucose changes is extremely close, i.e., there is a rigid locking phenomenon. Therefore, in this embodiment, the absolute value of the Pearson correlation coefficient between the first change sequence and the second change sequence is used as the degree of correlation of the reverse linkage event segment; considering that within a short time window, the signal change rate may be constant, resulting in a variance of zero, which may lead to a division-by-zero error, this embodiment modifies the existing formula for obtaining the Pearson correlation coefficient, wherein the formula for calculating the degree of correlation is: In the formula, The degree of relevance of the k-th reverse-linked event segment; It is the i-th first change value in the first change sequence of the k-th reverse linkage event segment; It is the mean of all first change values ​​in the first change sequence of the k-th reverse linkage event segment; It is the i-th second change value in the second change sequence of the k-th reverse linkage event segment; It is the mean of all second change values ​​in the second change sequence of the k-th reverse linkage event segment; To preset a very small positive number, this embodiment sets it to be... To avoid denominators of 0 and ensure computational stability, implementers can set the appropriate parameters based on actual conditions. The size is not limited here; This is an absolute value function. To quantify the average neural regulatory stiffness of the target object within the observation period, the mean of the correlation between all inverse linkage event segments is used as a characterizing the degree of synchronization of neural-metabolic regulatory stiffness.

[0080] The physiological resistance index acquisition module 30 is used to obtain the physiological resistance index of the target object based on the degree of glucose deficit, the result of nonlinear gain processing of the frequency of reverse linkage event segments using the degree of synchronization, and the nonlinear mapping result of the observed follicle diameter.

[0081] Specifically, it is known that follicular development arrest is usually caused by the combined effects of two physiological resistances: metabolic substrate deficiency and neurovascular contraction. The degree of influence of these two factors on the follicle is regulated by the follicle's own developmental stage. In order to uniformly map discrete and multidimensional physiological interference signals into specific kinetic inhibition values ​​for follicular growth, so that clinicians can intuitively assess the resistance density of the current body microenvironment and ensure that diagnostic and treatment decisions are based on quantitative pathological load, the physiological resistance index of the target object can be obtained based on the degree of glucose deficit and the results of nonlinear gain processing of the frequency of reverse linkage event segments using the degree of synchronization, combined with the nonlinear mapping results of follicle diameter observations. This accurately reflects the theoretical attenuation of the growth rate of the dominant follicle under the current neuro-metabolic coupling environment, which is conducive to constructing an adversarial model between growth dynamics and environmental resistance.

[0082] Preferably, in one feasible embodiment, the method for obtaining the physiological resistance index is described in [reference needed]. Figure 2 The document presents a flowchart of a method for obtaining a physiological resistance index, as provided in this embodiment. The method includes the following steps:

[0083] Step S201: Obtain metabolic deficit characteristic values.

[0084] Considering that the nocturnal glucose deficit is an integral part of the energy metabolism dimension, it needs to be mapped to an assessment value of the same order of magnitude as the follicle growth rate. To unify the feature dimensions for subsequent vector synthesis, the product of a first preset damping coefficient and the degree of glucose deficit is used as the metabolic deficit feature value, accurately reflecting the growth inhibition rate directly resulting from substrate scarcity. In this embodiment, the first preset damping coefficient is set to... Because the unit for measuring the degree of glucose deficit is... To ensure the compatibility of dimensional conversion, the implementer can set the size of the first preset damping coefficient according to the actual situation, without limitation here.

[0085] Step S202: Obtain the rigidity feature value of neural regulation.

[0086] Considering that the impact of neural stress on follicles depends not only on the frequency of events but also on the intensity of vasoconstriction (i.e., stiffness) during each stress, in order to accurately reproduce the nonlinear amplification effect of pathological stiffness on resistance, the result of nonlinear gain processing of the frequency of reverse linkage event segments using the degree of synchronization is used as the neural regulation stiffness characteristic value. This accurately reflects the comprehensive physical resistance exerted by the neurovascular pathway on follicle development, which is helpful in distinguishing between simple high-frequency stress and high-stiffness pathological locking.

[0087] The formula for calculating the rigidity characteristic value of neural regulation is as follows: In the formula, Y is the rigidity characteristic value of neural regulation; N is the number of reverse linkage event segments; and C is the degree of synchronization. The second preset damping coefficient; This is the preset gain coefficient. Where N is in units of... The unit of C is dimensionless. To make the unit of Y... In this embodiment, a second preset damping coefficient is set. for This allows the frequency to be mapped to the basic resistance value, ensuring that the baseline order of magnitude for resistance calculations conforms to physiological common sense; a preset gain coefficient is set. The value is 1.5, allowing high stiffness to amplify the basic drag by 2.5 times. This results in a significantly higher calculated drag for the same frequency of stress compared to low stiffness patients. It should be noted that in the formula... This demonstrates the physical mechanism of pathological stiffness as a multiplicative gain factor, enabling precise resistance profiling of patients with different pathological subtypes; through It demonstrates the equivalent neural impact intensity after stiffness correction, completing the scientific mapping from discrete event statistics to continuous physical resistance.

[0088] Step S203: Obtain the baseline inhibition rate.

[0089] Metabolic inhibition and neural inhibition are known to be two relatively independent physiological dimensions, which can be considered as orthogonal resistance vectors in kinetics. To obtain the total scalar resistance imposed by the environment, the result of vector synthesis of metabolic deficit characteristic values ​​and neural regulatory rigidity characteristic values ​​is used as the baseline inhibition rate. This rate preliminarily reflects the objective background pressure of the body's microenvironment without considering the state of the follicles themselves, which is beneficial for establishing a unified resistance assessment standard. The formula for calculating the baseline inhibition rate is: In the formula, X is the basic inhibition rate; X is the metabolic deficit characteristic value; Y is the neural regulation rigidity characteristic value.

[0090] Step S204: Obtain susceptibility weights.

[0091] The sensitivity of follicles to the environment varies with developmental stages. Only when they develop to a certain size (dominant follicle) are they highly sensitive to luteinizing hormone pulses and blood flow fluctuations. To avoid overestimating false resistance for early insensitive follicles, the difference between the observed follicle diameter and the preset critical threshold is nonlinearly mapped as a susceptibility weight. This accurately reflects the actual degree of acceptance of the current follicle to environmental fluctuations and is conducive to achieving adaptive resistance assessment that dynamically adjusts with the developmental process.

[0092] The formula for calculating susceptibility weight is as follows: In the formula, Susceptibility weight; This is the current observed value of the follicle diameter; This is a preset critical threshold; is a preset variation factor; exp is an exponential function with the natural constant as the base. This embodiment sets a preset critical threshold. for This ensures that the target is the physiological node where the expression of the luteinizing hormone receptor surges; the preset change factor is set to 0.8 to ensure that the weight increases smoothly and rapidly with the increase of diameter; the implementer can set the preset critical threshold and the size of the preset change factor according to the actual situation, which is not limited here.

[0093] Step S205: Obtain the physiological resistance index.

[0094] It is known that the effective resistance acting on follicles is the result of the coupling between basal environmental resistance and the follicle's own susceptibility. In order to obtain the final dynamic correction value, the product of susceptibility weight and basal inhibition rate is used as the physiological resistance index of the target object.

[0095] It should be noted that the various operational coefficients in this embodiment (including the first preset damping coefficient, the second preset damping coefficient, the preset gain coefficient, and the preset variation factor) are essentially feature normalization weighting factors, used to map heterogeneous physiological signal features to a unified resistance-rate dimension. The initial values ​​of these coefficients can be obtained based on the statistical distribution characteristics of a large sample of historical clinical data (such as the mean of a normal distribution); or they can be initialized and matched according to the baseline characteristics of the target object (such as BMI index, disease duration) (for example, objects with higher BMI can be automatically matched with a larger first preset damping coefficient). During actual system operation, these coefficients can be iteratively calibrated using subsequently input clinical feedback data to improve the individual adaptability of the evaluation model.

[0096] The data processing module 40 is used to obtain the assessment results of reproductive function status based on the changes in the observed follicle diameter and in combination with the physiological resistance index.

[0097] Specifically, it is known that the final outcome of follicular development depends on whether its intrinsic growth drive can effectively overcome the physiological inhibition resistance imposed by the external environment. In order to quantify and arbitrate this dynamic growth-inhibition antagonistic relationship, and based on the changes in follicular diameter observations, combined with the physiological resistance index, the assessment results of reproductive function status can be obtained. This accurately reflects the dynamic probability of follicles continuing to survive and ovulate under the current environmental resistance, which is conducive to timely detection of hidden arrest risks and identification of specific pathological subtypes leading to high resistance, thereby providing data support for personalized lifestyle interventions.

[0098] Preferably, in one feasible embodiment, the method for obtaining the assessment result of reproductive function status is as follows: In order to assess the developmental momentum of the follicle itself, the follicle growth rate is obtained based on the change of the current follicle diameter observation value relative to the historical follicle diameter observation value, accurately reflecting the morphological expansion speed of the follicle per unit time; wherein, the method for obtaining the follicle growth rate is as follows: the difference between the current follicle diameter observation value and the previously obtained follicle diameter observation value is taken as the first difference, accurately reflecting the net growth between the two observation time points; in order to align the time dimension, the difference between the current follicle diameter observation time and its previous observation time is further obtained as the first interval duration, accurately reflecting the time span experienced by the growth process; in order to obtain a standardized rate index for follicle growth, so that the growth data under different observation intervals are comparable, the ratio of the first difference to the first interval duration is taken as the follicle growth rate; it should be noted that the first interval duration must be greater than 0, if only the current follicle diameter observation value is stored, the follicle growth rate is assumed to be 0.

[0099] To assess whether growth momentum is sufficient to overcome environmental resistance and accurately analyze the current suppression of follicle development by the body's environment, the ratio of follicle growth rate to physiological resistance index is used as the degree of growth survival, accurately reflecting the remaining growth momentum (i.e., kinetic safety margin) under unit environmental resistance. When the degree of growth survival is greater than or equal to a preset safety threshold, it indicates that the follicle growth momentum is strong and sufficient to resist the current environmental pressure. At this time, the assessment result of reproductive function status is normal growth. It should be noted that, in order to avoid the physiological resistance index being 0, which would render the calculation of the degree of growth survival meaningless, this embodiment uses the sum of the physiological resistance index and a preset minimum positive number as the denominator, thus avoiding the situation where the denominator is 0 when obtaining the degree of growth survival.

[0100] When the growth and survival rate is less than a preset safety threshold, it indicates that excessive environmental resistance is causing follicles to face the risk of developmental arrest. To clarify the specific pathological source of high resistance, the sum of metabolic deficit characteristic values ​​and neural regulatory rigidity characteristic values ​​is obtained as the first result. Then, the proportion of metabolic deficit characteristic values ​​in the first result is taken as the metabolic component proportion, accurately reflecting the contribution weight of metabolic factors in the total resistance. This embodiment uses... Obtain the percentage of metabolic components, where X is the metabolic deficit characteristic value; and Y is the neural regulatory rigidity characteristic value. To minimize positive values ​​and avoid denominators of 0, when the proportion of metabolic components exceeds a preset threshold, it indicates that the resistance primarily stems from endocrine suppression caused by nighttime energy deficit. In this case, the reproductive function assessment indicates a lack of metabolic substrates. To assist in subsequent targeted improvement, the system generates a first-type state signal, signifying that current reproductive function is dominated by metabolic resistance. The display terminal responds to this first-type state signal by displaying preset first-type lifestyle support tags (such as metabolic substrate focus). When the proportion of metabolic components is less than or equal to the preset threshold, it indicates that the resistance primarily stems from vascular transection caused by daytime sympathetic nerve stiffness. In this case, the reproductive function assessment indicates neural pathway stiffness. To specifically reduce neural resistance, the system generates a second-type state signal, signifying that current reproductive function is dominated by neural resistance. The display terminal responds to this second-type state signal by displaying preset second-type lifestyle support tags (such as neural tension focus). In this embodiment, a preset safety threshold is set to 1.0. The preset safety threshold is set based on the theoretical balance point between follicle growth dynamics and environmental resistance (i.e., the critical value when dynamics equal resistance) to ensure that the critical state of dynamic imbalance can be sensitively identified. A preset proportion threshold is set to 0.5 to ensure that the dominant position of the two sources of resistance can be objectively distinguished. The implementer can set the size of the preset safety threshold and the preset proportion threshold according to the actual situation, which is not limited here.

[0101] In summary, this embodiment includes: a data acquisition module for acquiring blood glucose, heart rate, acceleration data, and follicle diameter; a data analysis module for dividing sleep and wakefulness periods, calculating the degree of glucose deficit during sleep, and determining the degree of synchronization characterizing neuro-metabolic regulatory stiffness by analyzing the correlation between blood glucose and heart rate inverse linkage events during wakefulness; a physiological resistance index acquisition module for calculating the physiological resistance index based on the degree of glucose deficit, the frequency of inverse linkages gained through synchronization, and the susceptibility weight of follicle diameter; and a data processing module for combining follicle growth status with the physiological resistance index to obtain the evaluation results. This invention, by quantifying neuro-metabolic stiffness and environmental resistance, solves the problem of distinguishing between insufficient drug dosage and excessive body environmental resistance, effectively improving the accuracy of reproductive function status assessment.

[0102] Example 2:

[0103] This invention also proposes a reproductive function status assessment device based on multimodal physiological data. The device includes a memory and a processor. The memory stores executable program code, and the processor calls and executes the executable program code to perform the reproductive function status assessment system based on multimodal physiological data provided in this application. Specifically, the device may be a chip, component, or module. The chip may include a connected processor and memory; the memory stores instructions, and when the processor calls and executes the instructions, the chip can perform the reproductive function status assessment system based on multimodal physiological data provided in the above embodiment.

[0104] Furthermore, this application also protects a computer device; please refer to [link to relevant documentation]. Figure 3 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the aforementioned reproductive function status assessment systems based on multimodal physiological data.

[0105] Example 3:

[0106] The present invention also provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform the aforementioned method steps to implement the reproductive function status assessment system based on multimodal physiological data provided in the above embodiments.

[0107] Example 4:

[0108] The present invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to realize the reproductive function status assessment system based on multimodal physiological data provided in the above embodiments.

[0109] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0110] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A reproductive function status assessment system based on multimodal physiological data, characterized in that, The system includes: The data acquisition module is used to acquire blood glucose data, heart rate data, and body motion acceleration data of the target object at each moment within a specified time period; and to acquire the observed value of the follicle diameter of the target object. The data analysis module is used to divide a specified time period into sleep and wake periods based on changes in body motion acceleration data; to obtain the degree of glucose deficit during sleep based on the difference between blood glucose data and a preset blood glucose baseline; and to identify inverse linkage event segments between blood glucose data and heart rate data during wake periods, and to obtain the degree of synchronization characterizing the stiffness of neuro-metabolic regulation based on the correlation between changes in blood glucose data and heart rate data within the inverse linkage event segments. The physiological resistance index acquisition module is used to obtain the physiological resistance index of the target object based on the degree of glucose deficit, the result of nonlinear gain processing of the frequency of reverse linkage event segments using the degree of synchronization, and the nonlinear mapping result of the observed follicle diameter. The data processing module is used to obtain assessment results of reproductive function status based on changes in observed follicle diameter and in combination with the physiological resistance index.

2. The reproductive function status assessment system based on multimodal physiological data as described in claim 1, characterized in that, The method for obtaining the sleep period and wakefulness period is as follows: The first sliding window is slid in chronological order within a specified time period to obtain the variance of the body motion acceleration data within the time period corresponding to each sliding window, and then arranged in the order of acquisition to obtain the acceleration variance sequence. The time periods corresponding to consecutive variance values ​​in the acceleration variance sequence that are less than a preset rest threshold are taken as sleep periods; The time period excluding sleep within the specified time frame is designated as the waking period.

3. The reproductive function status assessment system based on multimodal physiological data as described in claim 1, characterized in that, The method for obtaining the degree of glucose deficit is as follows: For any point in time during sleep, the difference between the preset blood glucose baseline and the blood glucose data at that point will be used as the blood glucose missing value at that point. When the missing blood glucose analysis value is greater than or equal to 0, the missing blood glucose analysis value is taken as the missing blood glucose value at that moment. When the blood glucose missing value is less than 0, 0 is taken as the blood glucose missing value at that moment; The sum of the glucose deficit values ​​at all times during the sleep period is used as the degree of glucose deficit during the sleep period.

4. The reproductive function status assessment system based on multimodal physiological data as described in claim 1, characterized in that, The method for obtaining the reverse linkage event fragment is as follows: The second sliding window is slid in chronological order during the waking period, and the end time of each slide is taken as the analysis time for each slide. For any given analysis time, the slope of the straight line fitted by the blood glucose data in the local time period corresponding to that analysis time according to the time sequence is obtained, and it is used as the first change value for that analysis time. The slope of the straight line fitted by the heart rate data of the local time period corresponding to the sliding moment at the analysis time is obtained in chronological order and used as the second change value at the analysis time. When the first change value is less than the preset decreasing threshold and the second change value is greater than the preset increasing threshold, the analysis time is marked as the reverse linkage time. Each reverse linkage moment and its preset neighboring analysis moment constitute a segment as a reverse linkage event segment; wherein, if a certain reverse linkage moment is the preset neighboring analysis moment of another preceding reverse linkage moment, the reverse linkage event segment corresponding to that reverse linkage moment is not acquired.

5. The reproductive function status assessment system based on multimodal physiological data as described in claim 4, characterized in that, The method for obtaining the synchronization level is as follows: For any reverse linkage event segment, the first change value at each analysis time within the reverse linkage event segment is arranged in chronological order to obtain the first change sequence; Arrange the second change values ​​at each analysis time point within the reverse linkage event segment in chronological order to obtain the second change sequence; The absolute value of the Pearson correlation coefficient between the first and second change sequences is taken as the degree of correlation of the reverse linkage event segment. The mean of the correlation of all reverse-linked event segments is used as the synchronization degree characterizing the stiffness of neuro-metabolic regulation.

6. The reproductive function status assessment system based on multimodal physiological data as described in claim 1, characterized in that, The method for obtaining the physiological resistance index is as follows: The product of the first preset damping coefficient and the degree of glucose deficit is used as the metabolic deficit characteristic value. The result of nonlinear gain processing of the frequency of reverse linkage event segments using the degree of synchronization is used as the rigid feature value of neural regulation. The result of vector synthesis of metabolic deficit eigenvalues ​​and neural regulatory rigidity eigenvalues ​​is used as the baseline inhibition rate. The difference between the observed follicle diameter and the preset critical threshold, and the result of a nonlinear mapping, is used as the susceptibility weight. The product of susceptibility weight and baseline inhibition rate is used as the physiological resistance index of the target object.

7. The reproductive function status assessment system based on multimodal physiological data as described in claim 6, characterized in that, The formula for calculating the rigidity characteristic value of neural regulation is as follows: In the formula, Y is the rigidity characteristic value of neural regulation; N is the number of reverse linkage event segments; and C is the degree of synchronization. The second preset damping coefficient; This is the preset gain coefficient.

8. The reproductive function status assessment system based on multimodal physiological data as described in claim 6, characterized in that, The formula for calculating the susceptibility weight is as follows: In the formula, Susceptibility weight; This is the current observed value of the follicle diameter; This is a preset critical threshold; is the preset variation factor; exp is an exponential function with the natural constant as the base.

9. The reproductive function status assessment system based on multimodal physiological data as described in claim 1, characterized in that, The method for obtaining the assessment results of reproductive function status is as follows: Follicle growth rate is obtained by comparing the current follicle diameter observation with the historical follicle diameter observation; The ratio of follicular growth rate to physiological resistance index is used as the measure of growth and survival. When the degree of growth and survival is greater than or equal to the preset safety threshold, the assessment result of reproductive function status is normal growth; When the growth survival rate is less than the preset safety threshold, the sum of the metabolic deficit characteristic value and the neural regulation rigidity characteristic value is obtained as the first result; The proportion of metabolic deficit feature values ​​in the first result is taken as the proportion of metabolic component. When the proportion of metabolic components exceeds a preset threshold, the assessment result of reproductive function status is a lack of metabolic substrates. When the proportion of metabolic components is less than or equal to a preset threshold, the assessment result of reproductive function status is neural pathway rigidity.

10. A reproductive function status assessment system based on multimodal physiological data as described in claim 9, characterized in that, The method for obtaining the follicle growth rate is as follows: The difference between the current follicle diameter observation and the previous follicle diameter observation is taken as the first difference; The difference between the current follicle diameter observation time and the previous observation time is used as the first interval duration; The ratio of the first difference to the first interval duration is taken as the follicle growth rate.

Images