Intelligent Analysis System and Method for Endocrine Abnormality Detection

Abstract

The present invention relates to the technical field of medical data processing. Further, it relates to an intelligent analysis system and method for endocrine disorder detection. The system includes: a hormone kinetics and receptor interaction analysis unit, an intracellular signal transduction analysis unit, a metabolic network and stress response analysis unit, and a system evaluation unit. The hormone kinetics and receptor interaction analysis unit is used to obtain the concentration of receptor-hormone complexes. The intracellular signal transduction analysis unit is used to obtain the ion current concentration. The metabolic network and stress response analysis unit is used to calculate the degree of cell stress. The system evaluation unit is used to calculate the endocrine disorder degree value. The present invention provides analysis results with high precision, personalization, and dynamic adaptation.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical data processing, and particularly relates to an intelligent analysis system and method for endocrine disorder detection. Background Art

[0002] The endocrine system regulates various physiological processes in organisms through hormones, including metabolism, growth and development, stress response, and reproductive functions. Hormones, as signaling molecules, trigger a series of complex signal transduction processes by binding to target receptors, regulating cell functions and metabolic activities. However, endocrine disorders are usually closely related to various major diseases, including diabetes, thyroid dysfunction, polycystic ovary syndrome, and osteoporosis. Therefore, the detection and evaluation of endocrine disorders are of great significance in modern medical diagnosis. With the progress of artificial intelligence technology, endocrine detection systems combining biological big data and intelligent analysis are becoming a new research hotspot. However, there are still many problems in the dynamic analysis, multi-parameter fusion, and precision of abnormal diagnosis in the existing technologies, and new technical means are urgently needed to make breakthroughs.

[0003] Currently, the detection of endocrine disorders mainly relies on the detection technology of hormone concentration. Commonly used detection methods in laboratories include enzyme-linked immunosorbent assay (ELISA), radioimmunoassay (RIA), and chemiluminescence immunoassay (CLIA). These methods can provide certain disease diagnosis information by detecting the concentration of specific hormones in blood, urine, or saliva. For example, the determination of serum insulin, cortisol, and thyroid hormone levels is a standard index for evaluating pancreatic function, adrenal function, and thyroid diseases. However, the application of these detection technologies mainly focuses on static detection, that is, analyzing the instantaneous concentration of hormones by single sampling, and fails to reflect the dynamic characteristics of hormone secretion. In addition, traditional technologies usually only focus on a single index of hormone concentration and ignore the complex effects of hormone signals at the molecular, cellular, and metabolic network levels. In recent years, dynamic hormone monitoring technologies have gradually attracted attention. For example, subcutaneous microdialysis systems and integrated sensor technologies based on continuous monitoring can achieve real-time tracking of hormone concentration. However, these technologies are usually limited by the types and resolutions of monitored hormones and are difficult to comprehensively cover various hormones in the endocrine system. In addition, such technologies often only provide raw data output and lack in-depth analysis of hormone signal transduction, metabolic network effects, and cellular stress responses, resulting in limited application scope in disease diagnosis. Summary of the Invention

[0004] The main object of the present invention is to provide an intelligent analysis system and method for endocrine disorder detection, which realizes the full-chain, cross-scale and multi-dimensional analysis from hormone secretion dynamics, signal transduction to system metabolism. The system uses dynamic concentration feature extraction, non-linear kinetic modeling and multi-parameter integration to comprehensively capture the complex features of endocrine disorders, and generates a quantitative index of the degree of endocrine disorder through time integration, providing high-precision, personalized and dynamically adaptable analysis results.

[0005] To solve the above problems, the technical solution of the present invention is realized as follows:

[0006] An intelligent analysis system for endocrine disorder detection, the system includes: a hormone kinetics and receptor interaction analysis unit and an intracellular signal transduction analysis unit; the hormone kinetics and receptor interaction analysis unit is used to extract the dynamic concentration features of each hormone over time by constructing a high-dimensional feature space mapping function based on the inherent parameters of each hormone and the real-time concentration of each hormone at each time; combining the dynamic concentration features and the inherent parameters of each hormone, describing the binding and dissociation processes between the hormone and its receptor, establishing a non-linear kinetic model, and obtaining the concentration of the receptor-hormone complex; the intracellular signal transduction analysis unit is used to convert the concentration of the receptor-hormone complex into an intracellular concentration response through a multi-stage amplification mechanism based on the concentration of the receptor-hormone complex and the inherent parameters of each hormone; using the modified Nernst-Planck equation to analyze the influence of hormone signals on ion channels and transporters, simulating the flow of ions on the cell membrane, and obtaining the ion current concentration.

[0007] Further, the system further includes: a metabolic network and stress response analysis unit; the metabolic network and stress response analysis unit is used to construct a flux balance-based metabolic network model based on the ion current concentration, simulate the influence of hormone signals and ion flow on cell metabolic pathways, and obtain metabolite concentrations; evaluate the stress level of cells under endocrine disorders, quantify the expression level of stress proteins, and calculate the cell stress level.

[0008] Further, the system further includes: a system evaluation unit; the system evaluation unit is used to calculate the value of the degree of endocrine disorder according to the metabolite concentration, cell stress level, ion current concentration and receptor-hormone complex concentration, compare the value of the degree of endocrine disorder with a preset abnormal threshold, and obtain an analysis and comparison result.

[0009] Further, the inherent parameters of the hormone include: reference concentration for describing the hormone concentration under normal conditions, hormone secretion peak time, hormone molecular weight, hormone half-life, circadian rhythm frequency, receptor affinity coefficient, receptor binding rate constant, receptor dissociation rate constant, ion valence, diffusion coefficient, activation energy and inorganic phosphate concentration.

[0010] Furthermore, the dynamic concentration characteristics are represented by the following formula:

[0011] ;

[0012] where is the high-dimensional concentration characteristic of the th hormone at time ; is an integer subscript index; is the real-time concentration of the th hormone at time ; is the reference concentration of the th hormone; is the hormone secretion peak time of the th hormone; is the hormone half-life of the th hormone; is the hormone molecular weight of the th hormone; is the Boltzmann constant; is the body temperature; is the circadian rhythm frequency of the th hormone; is the initial phase angle of the th hormone, which is a set value with a value range of 30 degrees to 45 degrees; is the receptor affinity coefficient of the th hormone.

[0013] An intelligent analysis method for endocrine disorder detection, the method comprising:

[0014] Step 1: Based on the inherent parameters of each hormone and the real-time concentration of each hormone at each time, extract the dynamic concentration characteristics of each hormone over time by constructing a high-dimensional feature space mapping function; combine the dynamic concentration characteristics and the inherent parameters of each hormone to describe the binding and dissociation process between the hormone and its receptor, establish a nonlinear kinetic model, and obtain the receptor-hormone complex concentration;

[0015] Step 2: Based on the receptor-hormone complex concentration and the inherent parameters of each hormone, through a multi-stage amplification mechanism, convert the receptor-hormone complex concentration into an intracellular concentration response; use the modified Nernst-Planck equation to analyze the influence of hormone signals on ion channels and transporters, simulate the flow of ions across the cell membrane, and obtain the ion current concentration;

[0016] Step 3: Based on the ion flow concentration, construct a metabolic network model based on flux balance, simulate the effects of hormone signals and ion flow on cell metabolic pathways to obtain metabolite concentrations; evaluate the stress level of cells under endocrine disorders, quantify the expression level of stress proteins, and calculate the cell stress level;

[0017] Step 4: Calculate the endocrine disorder degree value according to the metabolite concentration, cell stress level, ion flow concentration and receptor-hormone complex concentration, and compare the endocrine disorder degree value with a preset abnormal threshold to obtain an analysis and comparison result.

[0018] The intelligent analysis system and method for endocrine disorder detection of the present invention have the following beneficial effects: Most traditional endocrine detection methods are static analyses of single sampling, which are difficult to capture the dynamic characteristics of hormone secretion. Through the hormone kinetics and receptor interaction analysis unit, the present invention uses a high-dimensional feature space mapping function to extract the dynamic characteristics of hormone concentration over time, and combines a non-linear kinetics model to accurately describe the binding and dissociation processes between hormones and receptors. This design can track the dynamic changes of hormone secretion in real time, including key parameters such as secretion peak time, circadian rhythm frequency and half-life, providing a high-resolution dynamic description of the hormone secretion pattern under abnormal conditions. This dynamic analysis ability can significantly improve the detection sensitivity of early endocrine disorders and avoid missed diagnosis problems caused by insufficient data at a single time point. The endocrine system is a highly complex non-linear dynamic network. By introducing a non-linear kinetics model, the present invention significantly improves the simulation ability of hormone signal transduction, amplification and its system-level effects. For example, the non-linear model of receptor-hormone complex concentration accurately captures the complex interaction behaviors in a multi-hormone environment by combining dynamic concentration characteristics, receptor saturation effects and binding / dissociation rates. At the same time, in the modeling of the metabolic network, the system first combines dynamic hormone signals with the kinetic behaviors of metabolic pathways, truly reflecting the multi-dimensional regulatory effects of hormone signals on the metabolic network. This kinetics modeling ability enables the system to more accurately capture the complex dynamic characteristics of endocrine disorders. The intelligent analysis system of the present invention realizes cross-scale integrated analysis from the molecular level to the cell level and then to the system level. Through dynamic concentration feature extraction and kinetics modeling, the system first describes the kinetic behaviors of hormones at the molecular level; through the quantification of signal transduction and ion flow, it further reveals the conduction and amplification processes of hormone signals at the cell level; finally, through metabolic network and stress response analysis, it reveals the cascade effects of hormone signals at the system metabolism level. This cross-scale comprehensive analysis ability enables the system to comprehensively analyze the manifestations of endocrine disorders at different biological levels, providing comprehensive data support for the accurate diagnosis and grading of abnormal conditions. Description of the Drawings

[0019] Figure 1Schematic diagram of the system structure of the intelligent analysis system for endocrine disorder detection provided by the embodiments of the present invention. Detailed implementation manners

[0020] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0021] Example 1: Refer to Figure 1 , an intelligent analysis system for endocrine disorder detection, the system includes: a hormone kinetics and receptor interaction analysis unit, an intracellular signal transduction analysis unit, a metabolic network and stress response analysis unit, and a system evaluation unit; the hormone kinetics and receptor interaction analysis unit is used to extract the dynamic concentration characteristics of each hormone over time by constructing a high-dimensional feature space mapping function based on the inherent parameters of each hormone and the real-time concentration of each hormone at each time; combining the dynamic concentration characteristics and the inherent parameters of each hormone, describe the binding and dissociation process between the hormone and its receptor, establish a non-linear kinetic model, and obtain the concentration of the receptor-hormone complex; the intracellular signal transduction analysis unit is used to convert the concentration of the receptor-hormone complex into an intracellular concentration response through a multi-stage amplification mechanism based on the concentration of the receptor-hormone complex and the inherent parameters of each hormone; use the modified Nernst-Planck equation to analyze the influence of hormone signals on ion channels and transporters, simulate the flow of ions on the cell membrane, and obtain the ion current concentration; the metabolic network and stress response analysis unit is used to construct a flux balance-based metabolic network model based on the ion current concentration, simulate the influence of hormone signals and ion flow on cell metabolic pathways, and obtain metabolite concentrations; evaluate the stress level of cells under endocrine disorders, quantify the expression level of stress proteins, and calculate the cell stress level; the system evaluation unit is used to calculate the endocrine disorder degree value according to the metabolite concentration, cell stress level, ion current concentration and receptor-hormone complex concentration, compare the endocrine disorder degree value with a preset abnormal threshold, and obtain an analysis and comparison result.

[0022] Specifically, the design of the hormone kinetics and receptor interaction analysis unit is based on an in-depth understanding of the mechanism of hormone action in the body. Its core lies in capturing the temporal dynamics of hormone concentration and accurately describing the binding and dissociation processes between hormones and target receptors, thereby providing data support for the intelligent detection of endocrine disorders. In the endocrine system, hormones, as signaling molecules, are secreted by glands into the bloodstream or interstitial fluid. Their concentrations fluctuate over time and bind to specific receptors at the cellular level, triggering signal pathways and a series of physiological responses. However, this dynamic process is affected by multiple factors, including the secretion rate, diffusion coefficient, metabolic clearance rate of hormones, as well as the distribution and activity state of receptors, etc., and thus has a high degree of complexity. To precisely analyze this process, the present invention has established a complete description method from hormone secretion to receptor binding through a high-dimensional feature space mapping function and nonlinear kinetics modeling. The temporal dynamic characteristics of hormone concentration are the basis for the analysis of this unit. The hormone concentration usually shows a rapid upward trend at the initial stage of secretion and then gradually decreases to a stable level due to diffusion and metabolism. During this process, the change in hormone concentration is regulated by the secretion source and affected by external stimuli, and may show periodic fluctuations or short-term pulse signals. The present invention first constructs a high-dimensional feature space mapping function to transform the dynamic changes of hormone concentration into feature vectors to comprehensively characterize its change pattern. For example, the feature vectors may include the slope of concentration change, peak time, fluctuation frequency, and diffusion rate, etc. These features not only reflect the concentration distribution of hormones at different time points but also capture the dynamic behavior of hormone concentration changes, providing multi-dimensional information support for subsequent modeling.

[0023] After extracting the dynamic characteristics of the hormone, the next step is to describe its interaction with the receptor in combination with its inherent parameters. The binding and dissociation processes of the hormone and the receptor are essentially a chemical kinetic reaction, and its rate is jointly determined by the concentration of the hormone and the availability of the receptor. When a hormone molecule approaches the receptor, binding occurs with a certain probability to form a receptor-hormone complex. When the external conditions change or the receptor state is unstable, the complex may dissociate, releasing the free states of the hormone and the receptor. This process can be described by a nonlinear kinetic model, and its reaction rate depends not only on the instantaneous concentration of the hormone but also on the association rate constant and the dissociation rate constant. Specifically, when the hormone concentration is high, the receptor binding rate increases, and the production rate of the receptor-hormone complex reaches its peak. Conversely, when the hormone concentration decreases or the receptor is occupied, the dissociation rate of the complex will dominate the whole process. This unit accurately calculates the concentration of the receptor-hormone complex through real-time simulation of this dynamic behavior, which is a direct characterization of the signal transmission intensity. In addition to describing the binding and dissociation processes, the present invention also considers the influence of hormone diffusion on the binding efficiency. The diffusion of hormone molecules in the interstitial fluid is a physical process, and its rate is affected by factors such as molecular size, medium viscosity, and temperature. The diffusion process determines the available concentration of the hormone near the target receptor, thereby affecting the efficiency of the binding reaction. This unit simulates the diffusion behavior through a model and dynamically adjusts the input parameters of the hormone concentration, so as to more accurately predict the production rate of the receptor-hormone complex. This method is particularly applicable to the analysis of special cases where the hormone concentration is low or diffusion is limited, such as local signal transmission in a microenvironment.

[0024] The intracellular signal transduction analysis unit is an important component in this invention for analyzing how hormone signals are transmitted from receptors on the cell membrane to the interior of the cell and trigger a series of physiological responses. Its principle is based on the precise modeling of signal amplification mechanisms and ion dynamics. After a hormone binds to its target receptor, its effect is not limited to the cell membrane surface, but is amplified, dispersed, and integrated within the cell through a complex signal transduction network, thereby affecting the functional state of the cell interior. In this process, the intensity and speed of signal transmission determine the sensitivity and response ability of the cell to external stimuli. The intracellular signal transduction analysis unit of this invention systematically reveals how signals propagate within the cell and ultimately affect metabolic or stress responses through the quantitative input of receptor-hormone complexes, combined with the modeling of intracellular multi-level amplification mechanisms and ion flow. When a hormone binds to a receptor to form a receptor-hormone complex, this complex serves as the starting point of signal transduction and activates downstream intracellular molecules, such as enzymes, ion channels, or transporters. This activation typically occurs through two main pathways: one is the direct signal amplification dependent on the receptor complex within the membrane, such as the cascade reactions triggered by activating G protein-coupled receptors (GPCRs) or receptor tyrosine kinases (RTKs); the other is by changing the electrochemical environment of the cell membrane, further triggering ion flow or the generation of secondary signaling molecules. The analysis unit of this invention can receive the concentration change of the receptor-hormone complex as an input parameter and simulate the amplification process of signal intensity step by step based on the multi-level amplification model of intracellular signals. The core mechanism of signal amplification includes multiple non-linear processes, such as the acceleration of enzymatic reaction rates, the increase in the probability of channel opening, and the geometric multiplication of secondary signaling molecules. These non-linear processes are integrated into a dynamic model, enabling the system to accurately predict the diffusion and amplification effects of signals in different intracellular components.

[0025] Another key aspect of intracellular signal transduction is the dynamic change of ion flow. Hormone signals can directly or indirectly regulate the activities of ion channels and transporters, thereby changing the transmembrane ion flow pattern. Ions, such as calcium ions ( ), potassium ions ( ), sodium ions ( ), and chloride ions ( ),(which) play a crucial role in cell signal transduction as they are both carriers of signals and can further affect the activation state of other signal pathways through changes in membrane potential. The present invention precisely simulates the transmembrane ion flow induced by hormone signals by introducing a modified Nernst-Planck equation. Specifically, this model not only considers the diffusion driving force of ions but also combines the influence of the membrane potential gradient on ion flow, and further incorporates the influence of hormone signal dynamic regulatory factors, thereby being able to comprehensively reflect the changes in the electrochemical properties of the cell membrane under abnormal endocrine conditions. This simulation not only provides a basis for the quantification of ion flow concentration but also provides an accurate basis for the input parameters of the subsequent metabolic network.

[0026] The analysis ability of this unit is not only limited to the quantification of ion concentration but also can dynamically reflect the regulatory characteristics of the opening or closing of ion channels. The receptor-hormone complex further controls the opening and closing state of ion channels by activating secondary signal molecules, such as cyclic adenosine monophosphate (cAMP) or inositol trisphosphate (IP3), thereby regulating ion flow. This process has extremely high time resolution and usually occurs on a time scale from milliseconds to seconds. Therefore, this unit can capture the rapidly changing ion flow characteristics during signal transmission through a high-time-resolution modeling method, providing real-time data support for the detection of abnormal endocrine conditions. There is also a phenomenon of intracellular signal localization during signal transduction. Hormone signals usually form a specific spatial distribution within the cell through the diffusion of secondary signal molecules, and this distribution may show significant differences due to the shape, structure of the cell or the spatial localization of receptors. The present invention precisely describes the local distribution of signals by modeling the diffusion behavior of secondary signal molecules and combining intracellular structure parameters. The analysis of this spatial distribution is particularly important for evaluating the impact of abnormal endocrine conditions on specific functional regions (such as the nucleus, mitochondria or other subcellular organelles). In the intracellular signal transduction analysis unit, hormone signals are amplified, diffused and integrated to form a cell response pattern to external stimuli. This pattern is not only related to the initial concentration of hormones and receptor interaction characteristics but is also subject to the complex regulation of the intracellular signal transduction network. By simulating this process, the present invention can comprehensively reveal the dynamic propagation law of hormone signals within the cell, providing strong theoretical support and data support for the intelligent detection of abnormal endocrine conditions. The entire signal transduction analysis process realizes cross-scale modeling from receptors to ion flow, laying a solid foundation for metabolic network and stress response analysis, and at the same time significantly improving the detection accuracy and reliability of the system under different pathological conditions.

[0027] The metabolic network is a complex system composed of a series of metabolic pathways. These pathways convert substrates into products through enzymatic reactions to maintain the normal physiological functions of cells. In endocrine regulation, hormone signals not only act directly on key enzymes in metabolic pathways but also indirectly affect the rate of metabolic reactions by changing the intracellular ionic environment. For example, hormones may regulate the mitochondrial membrane potential by controlling ion channels, thereby affecting the efficiency of energy metabolism. The present invention systematically simulates the dynamic regulation of hormone signals on the metabolic network by constructing a flux balance-based metabolic network model. The core of flux balance analysis lies in dynamically solving the rate of each reaction in the network using the principle of mass conservation of metabolites. This method can comprehensively capture the generation, consumption, and transport processes of metabolites in cells, thus accurately reflecting the dynamic changes of the metabolic network. During the modeling process of the metabolic network, the ion flow concentration is integrated into the model as an external input parameter, directly affecting the activity and reaction rate of key enzymes in the network. For example, in the energy metabolism pathway, changes in calcium ion concentration may regulate the activity of enzymes in the tricarboxylic acid cycle, thereby altering the ATP production rate. By modeling the relationship between this ion concentration and metabolic reactions, the present invention can quantify the effect of hormone signals on the metabolic network. In addition, this unit also dynamically tracks the concentration changes of metabolites, including the dynamic distribution of key molecules such as glucose, lactate, and ATP. The concentrations of these molecules reflect the metabolic state of cells under different conditions. Through the analysis of these data, the specific effects of endocrine disorders on cell metabolic functions can be revealed, providing important clues for pathological diagnosis. The stress response is an adaptive response of the metabolic network under external stress or stimuli. In the context of endocrine disorders, this stress response often manifests as the remodeling of metabolic pathways and significant changes in the expression levels of stress proteins. Stress proteins (such as heat shock proteins, antioxidant enzymes, etc.) play a key role in the adaptation of cells to changes in the internal and external environments, and their expression levels directly reflect the stress state of the cells. The present invention quantifies the dynamic expression levels of stress proteins under different hormone signals by constructing a stress response model. For example, when the intracellular calcium ion concentration abnormally increases, stress proteins may be upregulated through the calcium signaling pathway, and this change will be captured by the system and converted into a quantitative index of the stress level. In addition, the stress response model can also combine the output of the metabolic network to evaluate the adaptive changes of metabolic pathways under stress conditions, such as whether there are metabolic bottlenecks or insufficient energy supply. This integrated analysis can comprehensively reflect the adaptability of cells under endocrine disorder conditions, providing more abundant information for clinical diagnosis. An important feature of the metabolic network and stress response analysis unit is its cross-scale modeling ability. The metabolic network analyzes the kinetic laws of chemical reactions at the molecular level, while the stress response analysis captures the overall performance of cells under dynamic stress at the system level. The combination of the two enables the system to simultaneously focus on local metabolic changes and global physiological states, thus providing a comprehensive understanding of endocrine disorders.For example, when a certain hormone signal triggers the accumulation of metabolites in a local metabolic pathway, the system can further analyze whether this local accumulation has a cascading effect on the global metabolic network, and then evaluate its overall impact on cell function.

[0028] In the complex regulatory network of the endocrine system, it is often difficult for an abnormality in a single parameter to comprehensively reflect the overall functional state of the system. For example, changes in hormone concentration may only be the primary manifestation of endocrine abnormalities, while their cascading effects on metabolic networks, ion dynamics, and stress responses are the key factors leading to functional disorders. Therefore, the system evaluation unit of the present invention first converts the output data from multiple analysis units into a comparable numerical format through a standardization method. For example, the concentration of receptor-hormone complex reflects the initial intensity of signal transduction, the concentration of ion flux describes the transmission of signals at the cell membrane level, the concentration of metabolites reflects the final effect of signals in the intracellular metabolic network, and the degree of cell stress reveals the overall response ability of the cell. These parameters reflect the state changes of the endocrine system from different dimensions. After standardization, they can be effectively integrated into a unified evaluation framework. The construction of the evaluation model is based on the principle of multi-parameter weight assignment, aiming to highlight the importance of each parameter under different pathological conditions. The setting of weights is supported by a large amount of experimental data and medical knowledge. For example, in some endocrine diseases, the metabolite concentration may be the most important indicator, while in other diseases, changes in the concentration of receptor-hormone complex may be more critical. The system evaluation unit adapts to the needs of different detection scenarios by dynamically adjusting the weight coefficients. This dynamic weight assignment mechanism can not only improve the accuracy of the evaluation results but also reveal the importance of certain parameters under specific abnormal conditions, providing guidance for subsequent diagnosis and treatment. After obtaining the comprehensive evaluation value, this unit further compares it with a preset abnormal threshold. The threshold is set based on statistical data of healthy and patient populations, considering various influencing factors such as age, gender, and lifestyle habits. Through this personalized comparison method, the system can distinguish the degree of abnormality of different patients and provide a quantitative abnormality level as the output result. This output not only intuitively reflects the health status of the endocrine system but also provides an important reference basis for clinicians' diagnosis.

[0029] Example 2: The inherent parameters of a hormone include: reference concentration for describing the hormone concentration under normal conditions, hormone secretion peak time, hormone molecular weight, hormone half-life, circadian rhythm frequency, receptor affinity coefficient, receptor binding rate constant, receptor dissociation rate constant, ion valence, diffusion coefficient, activation energy, and inorganic phosphorus concentration.

[0030] Specifically, the reference concentration of a hormone is used to describe the average concentration level of the hormone under normal physiological conditions and serves as a benchmark for detecting abnormalities. The reference concentration provides a comparison standard for the system. When the real-time concentration deviates significantly from this value, it indicates possible abnormal secretion or other pathological factors. The hormone secretion peak time is an important parameter reflecting the dynamic behavior of the hormone over time. Especially for circadian hormones (such as cortisol or melatonin), the peak time of their secretion is directly related to the normal operation of the biological rhythm. By recording and analyzing this parameter, this system can capture endocrine abnormalities caused by circadian rhythm disorders. The hormone molecular weight is an important determinant of its diffusion rate and transport ability. Hormones with larger molecular weights usually diffuse more slowly, and their range of action is also limited to a certain extent. This invention combines the molecular weight and diffusion coefficient to dynamically simulate the distribution of hormones in interstitial fluid or blood, thereby accurately describing the concentration change of hormones near the target receptor. This is crucial for accurately modeling the hormone-receptor interaction process. The hormone half-life is an important parameter for measuring the stability of hormones in the body and directly affects the duration of their biological activity. Hormones with shorter half-lives (such as insulin) need to be secreted frequently to maintain a stable physiological concentration, while hormones with longer half-lives (such as thyroid hormones) accumulate slowly in the body. This invention uses the half-life parameter and combines it with the dynamic curve of the real-time hormone concentration to simulate the metabolic clearance process of hormones, providing a basis for the kinetic modeling of endocrine abnormalities.

[0031] The circadian rhythm frequency reflects the time-period characteristics of hormone secretion and is a characteristic indicator of circadian rhythm hormones. By monitoring and analyzing this parameter, the system can determine whether an individual's circadian rhythm is normal and evaluate the possible impact of circadian rhythm disorders on the endocrine system. Abnormalities in circadian rhythm frequency are usually closely related to related diseases such as sleep disorders and chronic stress. The receptor affinity coefficient, receptor binding rate constant, and receptor dissociation rate constant are key parameters describing the binding kinetics of hormones to receptors. The affinity coefficient determines the ability of hormone molecules to bind to receptors, while the binding rate and dissociation rate describe the speed of the binding process and the stability of the complex, respectively. Through the dynamic modeling of these parameters, the present invention accurately simulates the non-linear process of hormone-receptor interaction and calculates the concentration change of the receptor-hormone complex, providing accurate input data for signal transduction analysis. The ionic valence and diffusion coefficient are mainly used to analyze the impact of hormone signals on the electrochemical environment of cell membranes. The ionic valence determines the movement ability of ions in an electric field, while the diffusion coefficient reflects the propagation rate of ions in the interstitial fluid or within the membrane. Combining these parameters, the present invention simulates the ion flow induced by hormone signals through a modified Nernst-Planck equation and quantifies the transmembrane ion concentration change. The activation energy is a parameter measuring the ease of initiation of hormone-mediated chemical reactions or biological processes. In the metabolic network, the rates of many enzymatic reactions depend on the changes in activation energy regulated by hormone signals. The present invention accurately simulates the response characteristics of metabolic pathways under hormone signal regulation by dynamically adjusting the activation energy parameter, providing important support for metabolic network modeling. Finally, the inorganic phosphate concentration is an important biochemical indicator measuring the energy metabolism state. As a substrate for ATP metabolism, the inorganic phosphate concentration directly reflects the energy supply level of cells. Abnormalities in inorganic phosphate concentration may indicate metabolic disorders. For example, hypophosphatemia may lead to impaired energy metabolism. The present invention combines the inorganic phosphate concentration parameter to evaluate the regulatory effect of hormone signals on the energy metabolism pathway, providing key input for the overall modeling of the metabolic network.

[0032] Example 3: The dynamic concentration characteristics are represented by the following formula:

[0033] ;

[0034] where is the time at which the high-dimensional concentration characteristics of the th hormone are obtained; is an integer subscript index; is the time at which the real-time concentration of the th hormone is obtained; is the reference concentration of the th hormone; is the th hormone's hormone secretion peak time; is the hormone half-life of the th hormone; is the hormone molecular weight of the th hormone; is the Boltzmann constant; is the body temperature; is the circadian rhythm frequency of the th hormone; is the initial phase angle of the th hormone, which is a set value with a value range of 30 degrees to 45 degrees; is the receptor affinity coefficient of the th hormone.

[0035] Specifically, the concentration normalization part in the formula divides the real-time concentration by the reference concentration to achieve the dimensionless treatment of the hormone concentration. The purpose of this operation is to eliminate the differences in concentration magnitudes between different hormones, enabling the concentration changes of different hormones to be compared and analyzed on the same scale. The normalized concentration value can intuitively reflect the deviation degree of the hormone concentration from its normal reference value, which is of great significance for detecting endocrine abnormalities. When the real-time concentration of a certain hormone is significantly higher or lower than the reference concentration, the system can quickly identify the potential abnormal state. In the subsequent time dynamic weight part, a Gaussian function is used to perform time weighting on the hormone concentration. This part reflects the influence of the peak time and half-life of hormone secretion on the concentration characteristics. The secretion of hormones in the body usually has a specific time pattern. For example, the secretion of certain hormones reaches a peak at specific time points in a day, and then their concentrations gradually decrease due to the influence of the half-life. The introduction of the Gaussian function enables the formula to highlight the concentration change characteristics of hormones near the secretion peak time, while weakening the concentration influence at time points far from the peak time, thus more accurately capturing the secretion dynamic behavior of hormones.

[0036] The molecular physical property correction part combines the molecular weight of the hormone with the temperature through to further adjust the concentration characteristics. This term reflects the diffusion ability of hormone molecules and their movement characteristics in the body environment. The larger the molecular weight of a hormone, the lower its diffusion rate usually is, and thus its distribution range in the body is also limited. The Boltzmann constant and body temperature reflect the movement energy and diffusion behavior of molecules in the thermodynamic environment. Through this correction, the formula not only considers the absolute value of the hormone concentration but also incorporates its physical movement characteristics into the calculation of dynamic characteristics, making the concentration characteristics more biologically meaningful. The circadian rhythm modulation part The circadian rhythm characteristics of hormones are thus introduced into the dynamic concentration characteristics. The secretion of many hormones exhibits an obvious circadian rhythm. For example, the secretion of cortisol and melatonin shows periodic changes at different time points of the day. Frequency and the initial phase angle describe the specific manifestations of this periodic property. By introducing modulation in the form of a cosine function, the formula can capture the periodic changes in hormone secretion, enabling the dynamic concentration characteristics to not only reflect the immediate concentration of the hormone but also incorporate its long-term secretion pattern. This is particularly important for detecting endocrine abnormalities caused by circadian rhythm disorders, as many endocrine diseases are closely related to disruptions in the circadian rhythm of hormones. Finally, the receptor affinity weighting part further adjusts the dynamic concentration characteristics to reflect the binding characteristics between the hormone and the receptor. The receptor affinity coefficient describes the strength of the binding between the hormone and its receptor. The higher the affinity, the tighter the binding between the hormone and the receptor, and the higher the efficiency of signal transmission. By raising the entire expression to the power, the formula can enhance the influence of high-affinity hormones in the dynamic characteristics, making the role played by these hormones in the signal transmission process more prominent. This processing method ensures that the dynamic concentration characteristics not only reflect the concentration changes of the hormone but also take into account its actual effect in signal transmission.

[0037] Example 4: A non-linear kinetic model is established through the following formula to obtain the concentration of the receptor-hormone complex:

[0038] ;

[0039] where, represents time at which the concentration of the receptor-hormone complex corresponding to the th hormone; is the cell membrane dielectric constant; is the receptor binding rate constant corresponding to the th hormone; is the concentration of free receptors; is the total receptor concentration; represents time at which the concentration of the receptor-hormone complex corresponding to the th hormone; is an integer subscript index, and ; is the receptor dissociation rate constant corresponding to the th hormone; is the activation energy, representing the energy barrier that needs to be overcome during the binding or dissociation of the th hormone and the receptor; is the gas constant; is the type of hormone.

[0040] Specifically, the left - hand side of the formula represents the rate of change of the receptor - hormone complex concentration with time, and this rate of change consists of two main parts. First, the forward reaction term includes the hormone concentration , the concentration of free receptors , the receptor binding rate constant , and the high - dimensional concentration feature . The high - dimensional concentration feature is calculated by the aforementioned high - dimensional feature extraction formula, reflecting the dynamic behavior of hormone concentration at a specific time point. The dielectric constant of the cell membrane affects the binding efficiency of the hormone to the receptor, reflecting the regulatory effect of the cell membrane's physical environment on the receptor - hormone interaction. The negative reaction term is determined by the receptor dissociation rate constant and the receptor - hormone complex concentration , describing the dissociation process of the complex. In the forward reaction term, the product of the hormone concentration and the concentration of free receptors indicates that the binding rate of the hormone to the receptor depends not only on the concentration level of the hormone but also on the number of free receptors. In addition, the term in the parentheses represents the saturation effect of the receptor, that is, when the total concentration of the receptor - hormone complex approaches the total receptor concentration , further complex reactions are inhibited. This term reflects the limited nature of receptor resources, ensuring the physiological rationality of the model at high hormone concentrations. The high - dimensional concentration feature regulates the receptor binding rate by taking the square root of its ratio to the dielectric constant, making it more suitable for the electrochemical environment of the cell membrane. The dissociation reaction term is relatively simple, directly proportional to the complex concentration , multiplied by the dissociation rate constant . This term reflects the natural dissociation process of the complex in the absence of new hormone molecules binding. The dissociation rate constant describes the speed at which the complex returns from the stable state to the free state and is an important parameter determining the lifetime of the complex.

[0041] The second formula involves the activation energy , which is a parameter describing the energy barrier that needs to be overcome during the binding or dissociation process of the hormone to the receptor. The gas constant and the temperature The activation energy is then normalized so that it can be compared and applied under different temperature conditions. The introduction of the activation energy enables the model to consider the influence of temperature on the hormone-receptor interaction process, thereby enhancing the adaptability and accuracy of the model under different physiological conditions. The intelligent analysis system of the present invention can calculate and track the concentration change of the receptor-hormone complex in real time through the non-linear kinetic model in Example 4. This model not only considers the instantaneous concentration of the hormone and the availability of the receptor, but also integrates the influence of the hormone secretion pattern, molecular characteristics, and cell membrane environment through parameters such as the dynamic concentration characteristics and activation energy. This enables the system to provide more detailed and dynamic analysis results in the face of complex endocrine disorders. For example, in certain endocrine diseases, the total concentration of the receptor may change, or the peak time of hormone secretion and the half-life may deviate from the normal values. Through the non-linear kinetic model, these changes can be accurately captured and quantified. In addition, the multi-hormone interaction in the model is reflected through the summation term , demonstrating the competition and synergy effects between different hormones in the system. This design ensures that the model can handle the complex situation where multiple hormones coexist and interact with each other, further enhancing the reliability and practicality of the system in actual applications. With the help of this model, the intelligent analysis system can comprehensively consider the dynamic behavior of multiple hormones and receptor interactions, generate accurate receptor-hormone complex concentration data, which will serve as the key input for subsequent signal transduction and metabolic network analysis.

[0042] Example 5: The concentration response in the cell is converted from the receptor-hormone complex concentration through the following formula:

[0043] ;

[0044] where, represents the concentration response in the cell of the receptor-hormone complex corresponding to the th hormone at time ; is the number of layers of the cascade reaction; is the dissociation constant; is the ATP concentration; is the Michaelis constant for the th level of amplification; is the change in phosphorylation free energy; is an integer index; is an integer index.

[0045] Specifically, the summation symbol in the formula represents the cumulative effect of the signal on the multi-level reaction hierarchy, where is the number of layers of the cascade reaction. The reaction at each layer is represented by the product term which reflects the amplification effect of the signal at each layer. This multi-level amplification mechanism mimics typical processes in intracellular signal transduction, such as enzymatic reactions and protein kinase cascades, enabling weak initial signals to be effectively amplified and generating significant cellular responses. In the formula, normalizes the concentration of the receptor-hormone complex to a dimensionless quantity, is the dissociation constant, reflecting the affinity of the hormone for the receptor. A lower value indicates high affinity, meaning that even at low hormone concentrations, the receptor can effectively bind the hormone and promote signal transduction. Through this normalization process, the formula can effectively compare and analyze different hormones and receptors, ensuring the generality and applicability of the model. The following product term describes the regulatory effect of ATP concentration on the reaction rate during each stage of amplification. As the main energy molecule in the cell, ATP provides the necessary energy support during signal transduction, driving the activity of various enzymatic reactions and protein kinases. is the Michaelis constant for the stage of amplification, reflecting the half-saturation concentration of ATP in each reaction. Through this term, the formula can dynamically adjust the efficiency of signal transduction, simulating the impact of ATP concentration changes on signal amplification, and thus more realistically reflecting the regulation of intracellular energy status on signal transduction.

[0046] The square of the entire expression further enhances the amplification effect of the signal at each stage, mimicking the common non-linear amplification characteristics in biological systems. This square relationship means that the signal intensity grows exponentially at each stage, ensuring that even weak initial signals can generate significant cellular responses after multiple levels of amplification. This is particularly important for endocrine disorder detection because the early signals of many endocrine diseases may be relatively weak, and through this efficient amplification mechanism, the system can capture these subtle abnormal changes. The exponential decay term in the formula describes the decay process of the signal over time, where is the half-life of the th hormone. This term reflects the natural decay trend during signal transduction, mimicking the self-regulatory mechanism of intracellular signals. Under physiological conditions, signal transduction does not increase indefinitely but is regulated by time and feedback mechanisms to avoid over-amplification of signals and imbalance of cell functions. By introducing this decay term, the formula can more accurately simulate the dynamic changes of signals in the cell, ensuring the biological rationality of the model. Finally, Represents the phosphorylation free energy change, which is an important parameter for energy conversion in the signal transduction process. The phosphorylation reaction is a key step in intracellular signal transduction. Through the catalysis of protein kinases, the phosphorylation of substrate proteins further transmits and amplifies signals. The free energy change reflects the energy requirements and releases of the phosphorylation reaction, and has an important impact on the efficiency and stability of signal transduction. Incorporating this energy parameter into the formula enables the model to not only consider the concentration changes of signals but also integrate the dynamic process of energy conversion, enhancing the model's ability to simulate the complex signal transduction mechanism in cells.

[0047] Example 6: By the following formula, the flow of ions across the cell membrane is simulated to obtain the ion current concentration:

[0048] ;

[0049] where represents time the ion current concentration of the ion corresponding to the th hormone regulation at time, and the hormone indirectly affects the transmembrane flow of ions by regulating ion channels or transporters; is the diffusion coefficient of the th hormone; is the gradient operator; is the valence number of the ion corresponding to the ion regulated by the th hormone; is the Faraday constant; is the membrane potential; is the membrane viscosity.

[0050] Specifically, the first term of the formula describes the diffusion process driven by the ion concentration gradient. Diffusion is the natural migration phenomenon of ions on both sides of the cell membrane due to concentration differences. The diffusion coefficient characterizes the diffusion ability of ions in the medium. The ion concentration gradient is larger, the diffusion driving force is stronger, and the migration rate of ions is also faster. Through this term, the formula can reflect the passive migration behavior of ions on the cell membrane, which is the basic mechanism for cells to maintain the ion balance between the internal and external environments. The second term considers the influence of the electric field on the ion flow. This term is derived from the modified Nernst-Planck equation and describes the driving force of the membrane potential gradient on charged ions. is the valence number of the ion, reflecting the number of charges carried by the ion; is the Faraday constant, connecting the conversion relationship between charge and matter; is the gas constant, is the absolute temperature. The membrane potential gradient The larger it is, the stronger the driving effect of the electric field on ions. Especially for charged ions, the influence of the electric field is significant. Through this term, the formula can dynamically reflect the regulation of ion flow by changes in the electrochemical environment of the cell membrane, which is of great significance for understanding how hormone signals affect ion distribution by changing the membrane potential. The third term introduces a source term that describes the regulation of ion flow by intracellular signal transduction. is the intracellular concentration response corresponding to the receptor-hormone complex concentration, is the membrane viscosity, which reflects the fluidity and resistance of the membrane. This term indicates that hormones regulate the signal transduction process through the receptor-hormone complex, further affecting the transmembrane flow of ions. For example, hormone signals may activate specific ion channels or transporters, thereby changing the rate of ion influx or efflux. Through this term, the formula can closely combine the intracellular signal transduction process with ion flow, realizing a full-chain simulation from external hormone signals to intracellular ion dynamics.

[0051] Example 7: The metabolite concentration is calculated through the following formula:

[0052] ;

[0053] where is time at the th hormone corresponding metabolite concentration; is the proton electrochemical potential difference, which is a set value; is the membrane potential difference, which is a set value; is the substrate concentration, and its value is equal to .

[0054] Specifically, the core part of the formula describes the change rate of the metabolite concentration , and its dynamic change is jointly determined by the generation process driven by ion flow and the consumption process restricted by substrate kinetics. In the generation process, the driving force of ion flow comes from the transmembrane electrochemical gradient. This gradient is jointly formed by the ion concentration difference and the membrane potential difference, and is the key energy source for the cell to maintain its metabolic function. The formula quantifies the contribution of ion flow to metabolite generation through an expression containing ion concentration , membrane potential gradient and diffusion coefficient . The higher the ion concentration and the larger the membrane potential gradient, the faster the metabolite generation rate, which reflects that the cell can efficiently operate metabolic pathways under sufficient energy conditions. However, the generation of metabolites is not unlimited, and its rate is strictly regulated by substrate concentration and enzyme kinetics. The consumption term in the formula describes the metabolite at the substrate concentration through a kinetic model The consumption behavior under this condition. This part of the model adopts the typical Michaelis-Menten kinetics form, where the ratio of substrate concentration to its Michaelis constant determines the reaction rate. A higher substrate concentration can promote metabolite production, but when the substrate concentration approaches or is lower than the Michaelis constant, the production rate significantly decreases, which simulates the inhibitory effect of substrate deficiency on the metabolic network. Through this dynamic restriction mechanism, the formula can not only capture the balance relationship between metabolite production and consumption, but also reflect the potential impact of substrate concentration fluctuations on the metabolic pathway.

[0055] The formula further considers the energy regulation effect of transmembrane electrochemical potential difference and membrane potential difference on metabolite production. The proton electrochemical potential difference and the membrane potential difference jointly determine the free energy reserve of the cell, and this energy is used to drive a series of key reactions in the metabolic pathway. The formula incorporates the energy parameter into the calculation through an exponential term, which not only enables the model to reflect the efficient operation of the metabolic network under normal physiological conditions, but also can simulate the change of metabolite production rate under energy-limited conditions. For example, in some endocrine disorders, hormone signals may cause abnormal fluctuations in membrane potential, which in turn affect the transmembrane proton gradient and ultimately have a profound impact on the overall function of the metabolic network. Through the dynamic simulation of the formula, these changes in energy states can be accurately quantified, providing an important basis for anomaly detection. It should be noted that the formula also closely couples the ion flow concentration that affects ion flow with metabolic reactions. Ion flow not only drives metabolite production, but also has an important impact on the consumption process by regulating the electrochemical potential and membrane potential. This two-way mechanism widely exists in many biological systems. For example, in mitochondria, the proton gradient not only drives the synthesis of ATP, but also further affects the metabolic balance by regulating the transmembrane transport of substrates and products. By integrating these complex mechanisms into a unified mathematical framework, the formula captures the dynamic characteristics of multi-factor interactions in the metabolic network and provides deep analysis capabilities for intelligent analysis systems. The application of this formula in intelligent analysis systems is particularly suitable for detecting the early effects of endocrine disorders on the metabolic network. For example, in the case of hormone signal disorders, the system can capture the subtle changes in ion flow and metabolic reactions through the formula and generate accurate dynamic curves of metabolite concentration. These dynamic characteristics can not only be used to judge whether the metabolic function is normal, but also provide specific information about abnormal patterns, such as the excessive accumulation or rapid consumption of metabolites. By combining the metabolite concentrations corresponding to different hormones, the system can construct a comprehensive metabolic network state map, thereby achieving precise detection of endocrine disorders.

[0056] Example 8: The degree of cell stress is calculated through the following formula:

[0057] ;

[0058] where, is the inorganic phosphorus concentration of the th hormone; is the intracellular calcium ion concentration; is the protein folding energy; is the concentration of heat shock protein corresponding to the th hormone; is the degree of cellular stress corresponding to the th hormone at time .

[0059] Specifically, the heat shock protein concentration is an important indicator of the stress response. Heat shock proteins (HSPs) are a class of protective proteins widely expressed by cells in response to high temperatures, oxidative stress, or other stresses. Their main function is to help damaged proteins fold back into the correct three-dimensional structure or prevent further aggregation. The formula reflects the change of heat shock protein concentration relative to the reference value by normalizing to a fixed ratio (such as 1.2). This normalization process enables comparison of the expression changes of heat shock proteins under different hormone conditions, thereby revealing the variation law of stress intensity. Secondly, the exponential term in the formula incorporates the protein folding energy into the calculation of the stress degree. Protein folding energy reflects the energy barrier that heat shock proteins need to overcome to repair damaged proteins. is the Boltzmann constant, is the absolute temperature. A higher folding energy indicates that more heat shock protein activity is required to maintain protein stability, and thus the stress degree is higher. By introducing this term, the formula can dynamically capture the changes in heat shock protein activity under different temperature and pressure conditions, thereby more accurately reflecting the stress state.

[0060] The second main factor of the formula is the calcium ion concentration . Calcium ions are key regulatory factors in cell signal transduction. Under stress conditions, the intracellular calcium ion concentration usually increases significantly. The formula introduces the change of calcium ion concentration into the calculation of the stress degree through the term . When the calcium ion concentration rises, the value of this term also increases, reflecting the state that the cell activates more stress pathways due to enhanced calcium signals. For example, calcium ions can activate various signal proteins, such as calmodulin kinase (CaMK), thereby further amplifying the stress signal. Finally, the in the formula reflects the influence of the cell energy state on the stress response. ATP is the main energy molecule in cells, and the inorganic phosphorus concentration It reflects the metabolic state after ATP decomposition. Under stress conditions, the cell's demand for ATP increases, so the ratio of ATP to inorganic phosphate becomes an important indicator of the energy supply capacity. Through the form of taking the square root, this ratio is introduced into the calculation of the stress level in the formula, enabling the quantification of the cell's stress ability under energy-deficient conditions.

[0061] Example 9: Calculate the endocrine abnormality degree value through the following formula:

[0062] ;

[0063] where, is the endocrine abnormality degree value at time ; is the number of hormone types; is the normalized mean value of the set cell stress level; is the normalized mean value of the set ion current concentration; is the mean value of the set metabolite concentration; is the normalized mean value of the set receptor-hormone complex concentration.

[0064] Specifically, in the summation part of the formula, the number of hormone types determines the hormone range analyzed by the system. Each hormone is weighted and normalized for its contribution to the abnormality degree through its corresponding specific biological parameters (stress level , ion current concentration , metabolite concentration , receptor-hormone complex concentration ). This structure not only ensures that the independent effects of different hormones on the abnormality degree are included in the evaluation, but also reflects the importance of each parameter through weight assignment. The weight coefficients 0.3, 0.3, 0.2, and 0.2 in the formula are empirically set based on biological significance and experimental data. The cell stress level and the ion current concentration each account for 30% of the weight, indicating that in the evaluation of endocrine abnormality, the impacts of these two on the system function state are relatively significant. The cell stress level reflects the cell's adaptability in the case of endocrine abnormality and is usually a sensitive indicator in the early stage of the disease; while the ion current concentration reflects the regulation of the endocrine signal on the cell membrane electrochemical environment and is an important link in hormone signal transduction. The metabolite concentration and the receptor-hormone complex concentration each account for 20% of the weight, indicating that although the impacts of the metabolic process and hormone-receptor interaction on the endocrine state are slightly lower than the previous two, they are still key factors that cannot be ignored. The normalized mean value The introduction is to eliminate the differences in dimension and scale among different parameters, enabling them to be weighted and compared within the same evaluation framework. The setting of the normalized mean is usually based on experimental data of healthy individuals. Through this processing, the formula can effectively reflect the degree of deviation of different parameters from the normal state. For example, if the degree of cellular stress caused by a certain hormone is significantly higher than the normalized mean , then the corresponding weighted value will increase, thus increasing its contribution to the endocrine abnormality degree value . The integral form of the formula provides a dynamic cumulative evaluation method for endocrine abnormality detection. As time progresses, the system continuously accumulates the change trends of multiple parameters, generating a gradually increasing abnormality degree value. This design can capture the cumulative effect of abnormal states in the endocrine system, especially suitable for dynamic monitoring and the assessment of disease progression. For example, in some chronic endocrine disorders (such as diabetes or thyroid diseases), the abnormal state may gradually worsen over time, and the value calculated by this formula can intuitively reflect the development trend of the disease, providing an important basis for clinical decision-making.

[0065] Example 10: An intelligent analysis method for endocrine abnormality detection, the method comprising:

[0066] Step 1: Based on the inherent parameters of each hormone and the real-time concentration of each hormone at each time, extract the dynamic concentration characteristics of each hormone over time by constructing a high-dimensional feature space mapping function; combine the dynamic concentration characteristics and the inherent parameters of each hormone to describe the binding and dissociation process between the hormone and its receptor, establish a nonlinear kinetic model, and obtain the concentration of the receptor-hormone complex;

[0067] Step 2: Based on the concentration of the receptor-hormone complex and the inherent parameters of each hormone, through a multi-stage amplification mechanism, convert the concentration of the receptor-hormone complex into an intracellular concentration response; use the modified Nernst-Planck equation to analyze the influence of the hormone signal on ion channels and transporters, simulate the flow of ions across the cell membrane, and obtain the ion current concentration;

[0068] Step 3: Based on the ion current concentration, construct a flux balance-based metabolic network model to simulate the influence of the hormone signal and ion flow on the cell metabolic pathway, obtain the metabolite concentration; evaluate the stress degree of the cell under endocrine abnormality, quantify the expression level of stress proteins, and calculate the cell stress degree;

[0069] Step 4: Calculate the endocrine abnormality degree value according to the metabolite concentration, cell stress degree, ion current concentration, and receptor-hormone complex concentration, and compare the endocrine abnormality degree value with a preset abnormality threshold to obtain an analysis and comparison result.

[0070] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An intelligent analysis system for endocrine disorder detection, characterized in that, The system includes: a hormone kinetics and receptor interaction analysis unit and an intracellular signal transduction analysis unit; the hormone kinetics and receptor interaction analysis unit is used to extract the dynamic concentration characteristics of each hormone over time by constructing a high-dimensional feature space mapping function based on the inherent parameters of each hormone and the real-time concentration of each hormone at each time; combining the dynamic concentration characteristics and the inherent parameters of each hormone, describe the binding and dissociation processes between the hormone and its receptor, establish a non-linear kinetic model, and obtain the concentration of the receptor-hormone complex; the intracellular signal transduction analysis unit is used to convert the concentration of the receptor-hormone complex into an intracellular concentration response through a multi-stage amplification mechanism based on the concentration of the receptor-hormone complex and the inherent parameters of each hormone; use the modified Nernst-Planck equation to analyze the influence of hormone signals on ion channels and transporters, simulate the flow of ions across the cell membrane, and obtain the ion current concentration; the dynamic concentration characteristics are represented by the following formula: ； Among them, is the high-dimensional concentration feature of the th hormone at time ; is an integer subscript index; is the real-time concentration of the th hormone at time ; is the reference concentration of the th hormone; is the hormone secretion peak time of the th hormone; is the hormone half-life of the th hormone; is the hormone molecular weight of the th hormone; is the Boltzmann constant; is the body temperature; is the circadian rhythm frequency of the th hormone; is the initial phase angle of the th hormone, which is a set value, and the value range is from 30 degrees to 45 degrees; is the receptor affinity coefficient of the th hormone.

2. The intelligent analysis system for endocrine disorder detection according to claim 1, wherein The system further includes: a metabolic network and stress response analysis unit; the metabolic network and stress response analysis unit is used to construct a flux balance-based metabolic network model based on the ion current concentration, simulate the influence of hormone signals and ion flow on cell metabolic pathways, and obtain metabolite concentrations; evaluate the stress level of the cell under endocrine disorders, quantify the expression level of stress proteins, and calculate the cell stress level.

3. The intelligent analysis system for endocrine disorder detection according to claim 2, wherein The system further includes: a system evaluation unit; the system evaluation unit is used to calculate the endocrine disorder degree value according to the metabolite concentration, cell stress level, ion current concentration and receptor-hormone complex concentration, compare the endocrine disorder degree value with a preset abnormal threshold, and obtain an analysis and comparison result.

4. The intelligent analysis system for endocrine disorder detection according to claim 3, wherein, The inherent parameters of the hormone include: reference concentration for describing the hormone concentration under normal conditions, hormone secretion peak time, hormone molecular weight, hormone half-life, circadian rhythm frequency, receptor affinity coefficient, receptor binding rate constant, receptor dissociation rate constant, ion valence, diffusion coefficient, activation energy, and inorganic phosphate concentration.

5. An intelligent analysis method for endocrine disorder detection, characterized in that, The method includes: Step 1: Based on the inherent parameters of each hormone and the real-time concentration of each hormone at each time, extract the dynamic concentration characteristics of each hormone over time by constructing a high-dimensional feature space mapping function; combine the dynamic concentration characteristics and the inherent parameters of each hormone, describe the binding and dissociation processes between the hormone and its receptor, establish a non-linear kinetic model, and obtain the concentration of the receptor-hormone complex; Step 2: Based on the concentration of the receptor-hormone complex and the inherent parameters of each hormone, convert the concentration of the receptor-hormone complex into an intracellular concentration response through a multi-stage amplification mechanism; use the modified Nernst-Planck equation to analyze the influence of hormone signals on ion channels and transporters, simulate the flow of ions across the cell membrane, and obtain the ion current concentration; Step 3: Based on the ion flow concentration, construct a flux balance-based metabolic network model to simulate the effects of hormone signals and ion flow on cell metabolic pathways, and obtain metabolite concentrations; evaluate the stress level of cells under endocrine disorders, quantify the expression level of stress proteins, and calculate the cell stress level; Step 4: Calculate the endocrine disorder degree value according to the metabolite concentration, cell stress level, ion flow concentration, and receptor-hormone complex concentration, compare the endocrine disorder degree value with a preset abnormal threshold, and obtain the analysis and comparison result.

Images