A method and system for risk analysis of patients with early-stage precocious puberty

Abstract

This invention relates to the field of physiological data analysis technology for precocious puberty, specifically to a method and system for risk analysis of patients in the early stages of precocious puberty. The invention obtains the degree of dimensional deviation based on the distribution of patient data in each dimension across all data, thereby screening out similar patient groups; it obtains the degree of individual difference based on the similarity and correlation between patients and similar patient groups in each dimension; it obtains the degree of precocious puberty tendency in each dimension based on the proportion of patients in similar patient groups within the data of each dimension; it screens out dimensions with minor differences based on the degree of individual difference, thereby obtaining model error terms; and it uses the degree of individual difference, the degree of precocious puberty tendency, and the model error terms to obtain a regression model for precocious puberty risk analysis, and performs risk analysis on patients with precocious puberty. This invention can greatly reduce the computational complexity and noise interference of the precocious puberty risk analysis regression model, thereby obtaining accurate risk analysis results.

Description

Technical Field

[0001] This invention relates to the field of physiological data analysis technology for precocious puberty, specifically to a method and system for risk analysis of patients in the early stages of precocious puberty. Background Technology

[0002] Precocious puberty is a common developmental disorder of puberty, referring to the premature sexual development in children before the normal age range, mainly manifested as the early appearance of secondary sexual characteristics. The pathogenesis of precocious puberty is complex, likely closely related to multiple factors such as genetics, environment, and endocrine hormones. This condition not only seriously affects children's growth and development, mental health, and social adaptability, but may also increase the risk of other related diseases (such as decreased bone density and metabolic abnormalities). Therefore, early identification and accurate assessment of the risks of precocious puberty are crucial for intervention and treatment.

[0003] Conventional methods for analyzing the risk of precocious puberty primarily rely on indicators such as age, hormone levels, and bone age. They assess the risk by analyzing clinical indicators and examination data. However, because developmental patterns vary across races, regions, and individuals, and each child's genetic background and living environment differ, traditional methods cannot comprehensively assess the influence of multiple factors and fail to fully consider individual characteristics. Furthermore, physiological indicators typically have multiple dimensions, and the impact of each indicator on the target individual may differ. Without feature selection and analysis, computational complexity and noise interference would significantly increase, affecting the stability and accuracy of the risk analysis results. Summary of the Invention

[0004] To address the technical problem that traditional analysis methods cannot comprehensively assess the multi-factor impact of precocious puberty, and that the numerous dimensions of physiological indicator data greatly increase computational complexity and noise interference, thus affecting the accuracy of risk analysis results, the present invention aims to provide a risk analysis method and system for patients in the early stages of precocious puberty. The specific technical solution adopted is as follows:

[0005] A risk analysis method for patients in the early stages of precocious puberty includes:

[0006] Obtain physiological indicator data for all dimensions of all patients with precocious puberty;

[0007] Select one patient with precocious puberty as the target patient; choose any dimension of the target patient as the target dimension; based on the data distribution of the target patient's physiological indicator data in the target dimension among all physiological indicator data, obtain the degree of deviation of the target patient in the target dimension; screen all other patients with precocious puberty based on the degree of deviation to obtain a similar patient group in the target dimension; based on the data similarity between the target patient and the similar patient group in the target dimension, and the correlation between the target dimension and other dimensions, obtain the degree of individual difference of the target patient in the target dimension; based on the changing characteristics of the proportion of patients with precocious puberty in the similar patient group under the physiological indicator data of the target dimension, obtain the degree of precocious puberty tendency in the target dimension.

[0008] Based on the degree of individual differences, all minor difference dimensions of the target patient are screened out; based on the degree of individual differences of the target patient in all minor difference dimensions, the model error term is obtained; based on the degree of individual differences of the target patient in each dimension, the degree of precocious puberty tendency, and the model error term, a precocious puberty risk analysis regression model is obtained; based on the precocious puberty risk analysis regression model, risk analysis is performed on the physiological indicator data of the precocious puberty patient.

[0009] Furthermore, the method for obtaining the degree of dimensional deviation includes:

[0010] The degree of dimensional deviation is obtained according to the formula for calculating the degree of dimensional deviation, which is shown below:

[0011] ;

[0012] In the formula, This indicates the degree of deviation of the target patient from the target dimension; This represents the maximum value of the target dimension physiological indicator data among all physiological indicator data; This represents the minimum value of the target dimension of the physiological indicator data among all physiological indicator data; Indicates the number of patients with precocious puberty; This represents the physiological indicators of the target patient in the target dimension; This represents the average value of all physiological indicators for the target dimension. Represents the absolute value function; This represents the logarithmic function with the natural constant as the base.

[0013] Furthermore, based on the degree of deviation from the stated dimension, all other patients with precocious puberty are screened to obtain a patient group similar to the target patient, including:

[0014] The minimum value of the neighborhood is obtained by subtracting the physiological index data of the target patient in the target dimension from the degree of deviation of the dimension, and the maximum value of the neighborhood is obtained by adding the physiological index data of the target patient in the target dimension to the degree of deviation of the dimension.

[0015] The neighborhood range of the target patient's physiological indicator data in the target dimension is obtained by using the minimum and maximum values ​​of the neighborhood.

[0016] Within the neighborhood of the target dimension's physiological indicator data, select all other precocious puberty patients who have the same physiological indicator data for each dimension, and iterate through all physiological indicator data within the neighborhood to obtain a similar patient group composed of all precocious puberty patients to the target patient.

[0017] Furthermore, the method for obtaining the degree of individual differences includes:

[0018] Calculate the Pearson correlation coefficient between the target patient and each other dimension in the target dimension to obtain the correlation between the target patient and each other dimension, and select the preset number of other dimensions with the largest correlation as the related dimensions of the target dimension;

[0019] The degree of individual difference is obtained according to the formula for calculating the degree of individual difference, which is shown below:

[0020] ;

[0021] In the formula, This indicates the degree of individual differences among target patients in the target dimension; This represents the variance of all physiological indicators across the target dimension for similar patient groups. Indicates the preset number of related dimensions; Indicates the first [patient's] [number] Physiological indicators of relevant dimensions in similar patient groups Standard scores among physiological indicator data of each relevant dimension; This indicates the target dimension of the target patient and the first The correlation coefficients between physiological indicator data of each relevant dimension; This represents the sum of correlation coefficients between the target dimension and the physiological indicator data of each relevant dimension for the target patient; Represents the normalization function; This represents the absolute value function.

[0022] Furthermore, the method for obtaining the degree of precocious puberty tendency includes:

[0023] The degree of precocious puberty tendency is obtained according to the formula for calculating the degree of precocious puberty tendency, which is as follows:

[0024] ;

[0025] In the formula, Indicates the degree of precocious puberty tendency in the target dimension; This indicates the number of other physiological indicator data points for the target patient within the neighborhood of the target dimension's physiological indicator data. This represents the first position within the neighborhood of physiological indicator data in the target dimension among similar patient groups. The percentage of patients with precocious puberty based on other physiological indicators; This represents the first position of a similar patient group within the neighborhood of physiological indicator data in the target dimension. The percentage of patients with precocious puberty based on other physiological indicators; This represents the absolute value function.

[0026] Furthermore, the method for obtaining the model error term includes:

[0027] The dimension in which the degree of individual difference of the target patient is less than a preset first threshold is used as the small difference dimension;

[0028] The individual differences in each minor dimension of the target patient are amplified and averaged to obtain the model error term.

[0029] Furthermore, the method for obtaining the regression model for the risk analysis of precocious puberty includes:

[0030] The regression model for the risk analysis of precocious puberty is obtained based on the formula for the risk analysis of precocious puberty, which is shown below:

[0031] ;

[0032] In the formula, Indicates the probability of precocious puberty in the target patient; This indicates the degree of precocious puberty tendency in the target patient in the first dimension; This indicates the degree of individual variability among target patients in the first dimension; This indicates the degree of precocious puberty tendency in the target patient in the second dimension; This indicates the degree of individual variability among target patients in the second dimension; Indicates the target patient in the first month The degree of precocious puberty tendency in each dimension; Indicates the target patient in the first month The degree of individual differences in each dimension; Represents the model error term; This represents an exponential function with the natural constant as its base.

[0033] A risk analysis system for patients with early precocious puberty, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the aforementioned risk analysis method for patients with early precocious puberty.

[0034] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for risk analysis of early-stage precocious puberty patients.

[0035] The present invention has the following beneficial effects:

[0036] This invention addresses the issue that height, bone age, hormone levels, and sexual organ function all influence a patient's diagnosis of precocious puberty. It obtains physiological indicator data across all dimensions for all patients with precocious puberty. Since the more unique a patient's physiological indicator data in each dimension is compared to all other physiological indicators within that dimension, the greater the variability, this invention first analyzes the degree of dimensional deviation. By comparing the target patient's physiological indicator data with those of other patients with similar precocious puberty in the target dimension, it is possible to identify individual differences within that dimension. Secondly, it analyzes and obtains similar patient groups within the target dimension. Finally, it considers the similarity between the target patient and similar patient groups in the target dimension, as well as the correlation between the target dimension and other dimensions. This invention obtains the degree of individual differences among target patients in a target dimension. Since the magnitude of individual differences does not directly represent the magnitude of precocious puberty risk, it is necessary to accurately assess the impact of physiological indicators in each dimension on the results of precocious puberty risk analysis. Therefore, the analysis obtains the precocious puberty tendency in the target dimension. The precocious puberty tendency in each dimension is used as a variable in constructing a regression model for precocious puberty risk analysis. Since dimensions with smaller individual differences have lower importance in risk analysis, they are initially removed. However, completely ignoring dimensions with smaller individual differences may introduce errors into the model; therefore, the error term of the model is constructed using dimensions with smaller individual differences, thus constructing a regression model for precocious puberty risk analysis. This model is then used to perform risk analysis on the physiological indicator data of patients with precocious puberty. This invention can greatly reduce the computational complexity and noise interference of the precocious puberty risk analysis regression model, thereby obtaining accurate risk analysis results. Attached Figure Description

[0037] 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.

[0038] Figure 1 This is a flowchart of a risk analysis method for patients with early precocious puberty, provided as an embodiment of the present invention. Detailed Implementation

[0039] 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 risk analysis method and system for early-stage precocious puberty 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.

[0040] 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.

[0041] The following description, in conjunction with the accompanying drawings, details the specific scheme of the risk analysis method for early-stage precocious puberty patients provided by this invention.

[0042] Please see Figure 1 This illustrates a risk analysis method for early-stage precocious puberty patients provided by an embodiment of the present invention, the method comprising:

[0043] Step S1: Obtain physiological indicator data for all dimensions of all patients with precocious puberty.

[0044] This invention is primarily applied to the analysis of physiological indicator data in patients with precocious puberty, in order to accurately assess their physical condition. Since a patient's height, bone age, hormone levels, and sexual organ function all influence whether they have precocious puberty, this invention first acquires physiological indicator data across all dimensions for all patients with precocious puberty.

[0045] In one embodiment of the present invention, the dimensions of the physiological indicator data are set as height, bone age, hormone levels, and sexual organ function. It should be noted that the data dimensions can be set arbitrarily and are not limited here. Since there are significant differences between males and females in their manifestations of precocious puberty, subsequent steps involve dividing all physiological indicator data into two categories based on males and females, and processing and analyzing them separately. All physiological indicator data are standardized and normalized before being uploaded to a data analysis system for further processing. The standardization and normalization operations are techniques well-known to those skilled in the art and will not be elaborated upon here.

[0046] Step S2: Select any one patient with precocious puberty as the target patient; select any dimension of the target patient as the target dimension; based on the data distribution of the target patient's physiological indicator data in the target dimension among all physiological indicator data, obtain the degree of deviation of the target patient in the target dimension; screen all other patients with precocious puberty based on the degree of deviation to obtain a similar patient group in the target dimension; based on the data similarity between the target patient and the similar patient group in the target dimension, and the correlation between the target dimension and other dimensions, obtain the degree of individual difference of the target patient in the target dimension; based on the changing characteristics of the proportion of patients with precocious puberty in the similar patient group under the physiological indicator data of the target dimension, obtain the degree of precocious puberty tendency in the target dimension.

[0047] Because of individual differences among patients with precocious puberty, physiological indicators in different dimensions may have different importance in the risk analysis of precocious puberty in different patients. For example, although bone age is an important physiological indicator for assessing the risk of precocious puberty, the bone age of some patients with precocious puberty may deviate due to genetics, nutritional conditions or other environmental factors. Therefore, in reality, the physiological indicator data of the target patient in the target dimension will have a certain deviation. The more unique the physiological indicator data of the target patient in the target dimension is compared with all physiological indicator data in the target dimension, the greater the difference in the physiological indicator data of the target patient in the target dimension. In order to describe the difference, the degree of deviation of the target patient in the target dimension is first obtained. In this embodiment of the invention, the degree of deviation of the target patient in the target dimension is obtained according to the data distribution of the physiological indicator data of the target patient in the target dimension among all physiological indicator data.

[0048] Preferably, in one embodiment of the present invention, the method for obtaining the degree of dimensional deviation includes:

[0049] The degree of dimensional deviation is obtained according to the formula for calculating the degree of dimensional deviation, as shown below:

[0050] ;

[0051] In the formula, This indicates the degree of deviation of the target patient from the target dimension; This represents the maximum value of the target dimension physiological indicator data among all physiological indicator data; This represents the minimum value of the target dimension of the physiological indicator data among all physiological indicator data; Indicates the number of patients with precocious puberty; This represents the physiological indicators of the target patient in the target dimension; This represents the average value of all physiological indicators for the target dimension. Represents the absolute value function; This represents the logarithmic function with the natural constant as the base.

[0052] It should be noted that in one embodiment of the present invention, the number of patients with precocious puberty is set to 5, and the number of patients with precocious puberty can be set by oneself and is not limited here.

[0053] In the formula for calculating the degree of dimensional deviation, the range of physiological indicator data for the target dimension is... The larger the value, the greater the data variation in the target dimension among different precocious puberty patients. This indicates a larger deviation range in the physiological indicators of the target dimension, and a wider selection range when screening other precocious puberty patients with similar physiological indicators in the target dimension. The difference between the target patient's physiological indicator data in the target dimension and the average of all physiological indicators in the target dimension is also significant. The larger the value, the more unique the physiological indicators of the target patient in the target dimension. In this case, the greater the deviation range of the target patient in the target dimension, that is, the greater the degree of deviation of the target patient in the target dimension. This is further explained by the logarithmic function. Scaling is performed.

[0054] By comparing the differences in physiological indicators of the target patient with those of other patients with precocious puberty in the target dimension, the individual differences of the target patient in the target dimension can be analyzed. Therefore, in this embodiment of the invention, a group of patients with similar target dimensions is first screened.

[0055] Preferably, in one embodiment of the present invention, all other patients with precocious puberty are screened based on the degree of dimensional deviation to obtain a patient group similar to the target patient, including:

[0056] The minimum value in the neighborhood is obtained by subtracting the physiological indicator data of the target patient in the target dimension from the degree of deviation of the dimension, and the maximum value in the neighborhood is obtained by adding the physiological indicator data of the target patient in the target dimension to the degree of deviation of the dimension.

[0057] The neighborhood range of the target patient's physiological indicator data in the target dimension is obtained by using the minimum and maximum values ​​of the neighborhood. .

[0058] Within the neighborhood of the target dimension's physiological indicator data, select all other precocious puberty patients who have the same physiological indicator data for each dimension, and iterate through all physiological indicator data within the neighborhood to obtain a similar patient group composed of all precocious puberty patients to the target patient.

[0059] Secondly, based on the degree of data similarity between the target patient and similar patient groups in the target dimension, as well as the correlation between the target dimension and other dimensions, the degree of individual difference of the target patient in the target dimension is obtained.

[0060] Preferably, in one embodiment of the present invention, the method for obtaining the degree of individual differences includes:

[0061] Calculate the Pearson correlation coefficient between the target patient and each other dimension in the target dimension to obtain the correlation between the target patient and each other dimension. Select the preset number of other dimensions with the largest correlation as the related dimensions of the target dimension.

[0062] The degree of individual difference is obtained according to the formula for calculating the degree of individual difference, which is shown below:

[0063] ;

[0064] In the formula, This indicates the degree of individual differences among target patients in the target dimension; This represents the variance of all physiological indicators across the target dimension for similar patient groups. Indicates the preset number of related dimensions; Indicates the first [patient's] [number] Physiological indicators of relevant dimensions in similar patient groups Standard scores among physiological indicator data of each relevant dimension; This indicates the target dimension of the target patient and the first The correlation coefficients between physiological indicator data of each relevant dimension; This represents the sum of correlation coefficients between the target dimension and the physiological indicator data of each relevant dimension for the target patient; Represents the normalization function; This represents the absolute value function.

[0065] In the formula for calculating the degree of individual differences, in one embodiment of the present invention, the preset quantity is set to 3. The preset quantity can be set by itself and is not limited here. The standard score is a technical means well known to those skilled in the art and will not be described in detail here. The larger the target patient and similar patient groups are in the first month The greater the difference in physiological indicators across the relevant dimensions, the greater the difference between the target patient's target dimension and the first dimension. The proportion of the correlation coefficient among the physiological indicators of each relevant dimension to the total correlation coefficient. The larger the value, the higher the level of the target patient's level. The correlation and closeness between the relevant dimensions and the target dimension, at this point... Each relevant dimension The higher the weight, the greater the variance of all physiological indicators in the target dimension for similar patient groups. The smaller the value, the higher the stability of the target dimension among similar patient groups. In this case, the individual differences in the target dimension of the target patients are more easily reflected, and therefore the greater the degree of individual differences in the target dimension among the target patients.

[0066] In reality, the degree of individual differences cannot directly represent the magnitude of the risk of precocious puberty. For example, a higher hormone level in a similar group does not necessarily indicate a higher risk of precocious puberty; it may be a temporary phenomenon caused by environmental factors, diet, etc. Therefore, in order to accurately assess the impact of physiological indicator data of each dimension on the results of precocious puberty risk analysis, in this embodiment of the invention, the degree of precocious puberty tendency in the target dimension is obtained based on the changing characteristics of the proportion of patients with precocious puberty in the physiological indicator data of the target dimension in a similar patient group.

[0067] Preferably, in one embodiment of the present invention, the method for obtaining the degree of precocious puberty tendency includes:

[0068] Physiological indicators of precocious puberty can be obtained directly and will not be elaborated here.

[0069] The degree of precocious puberty tendency is obtained according to the formula for calculating the degree of precocious puberty tendency, which is shown below:

[0070] ;

[0071] In the formula, Indicates the degree of precocious puberty tendency in the target dimension; This indicates the number of other physiological indicator data points for the target patient within the neighborhood of the target dimension's physiological indicator data. This represents the first position within the neighborhood of physiological indicator data in the target dimension among similar patient groups. The percentage of patients with precocious puberty based on other physiological indicators; This represents the first position of a similar patient group within the neighborhood of physiological indicator data in the target dimension. The percentage of patients with precocious puberty based on other physiological indicators; This represents the absolute value function.

[0072] In the formula for calculating the degree of precocious puberty tendency, the proportion of patients with precocious puberty within the neighborhood of physiological indicator data of the target dimension in a similar patient group is considered. The larger the value, the greater the influence of the target dimension on the onset of precocious puberty, indicating a greater predisposition to precocious puberty within the target dimension's physiological indicator data neighborhood; the change rate of the proportion of patients with precocious puberty within a similar patient group within the target dimension's physiological indicator data neighborhood. The larger the value, the higher the sensitivity of the similar patient group to changes in physiological indicators of the target dimension. This indicates that the similar patient group is not stable under the target dimension, and at this time, it indicates that the precocious puberty tendency of the target dimension is relatively large.

[0073] Step S3: Filter out all minor difference dimensions of the target patient based on the degree of individual differences; obtain the model error term based on the degree of individual differences of the target patient in all minor difference dimensions; obtain the precocious puberty risk analysis regression model based on the degree of individual differences of the target patient in each dimension, the degree of precocious puberty tendency, and the model error term; perform risk analysis on the physiological indicator data of the precocious puberty patient based on the precocious puberty risk analysis regression model.

[0074] The degree of precocious puberty tendency in each dimension is used as a variable to construct a regression model for the risk analysis of precocious puberty. Since the dimension with small individual differences has low importance in the risk analysis, it is removed first. However, completely ignoring the dimension with small individual differences may cause errors in the model. Therefore, the error term of the model is constructed using the dimension with small individual differences, and then the regression model for the risk analysis of precocious puberty is constructed.

[0075] Preferably, in one embodiment of the present invention, the method for obtaining the model error term includes:

[0076] The dimension where the degree of individual difference of the target patient is less than a preset first threshold is taken as the small difference dimension. In one embodiment of the present invention, the preset first threshold is set to 0.5. It should be noted that in other embodiments of the present invention, the preset first threshold can be set by itself, and is not limited here.

[0077] The degree of individual variability in each minor dimension of the target patient is amplified and averaged to obtain the model error term. In one embodiment of the present invention, the formula for calculating the model error term is as follows:

[0078] ;

[0079] In the formula, Represents the model error term; The number of dimensions representing minute differences in the target patient; Indicates the target patient in the first month The degree of individual difference in a small dimension.

[0080] In the formula for calculating the model error term, the degree of individual difference in each small dimension of the target patient is amplified by an exponential function and then averaged.

[0081] Preferably, in one embodiment of the present invention, the method for obtaining the regression model for precocious puberty risk analysis includes:

[0082] The regression model for the risk analysis of precocious puberty is obtained based on the formula for the risk analysis of precocious puberty. The formula for the risk analysis of precocious puberty is shown below:

[0083] ;

[0084] In the formula, Indicates the probability of precocious puberty in the target patient; This indicates the degree of precocious puberty tendency in the target patient in the first dimension; This indicates the degree of individual variability among target patients in the first dimension; This indicates the degree of precocious puberty tendency in the target patient in the second dimension; This indicates the degree of individual variability among target patients in the second dimension; Indicates the target patient in the first month The degree of precocious puberty tendency in each dimension; Indicates the target patient in the first month The degree of individual differences in each dimension; Represents the model error term; This represents an exponential function with the natural constant as its base.

[0085] In one embodiment of the present invention, the probability of a patient with precocious puberty developing precocious puberty in the future is calculated using the regression model of precocious puberty risk analysis obtained from the above operations, and different clinical management is carried out according to the probability. If the probability value is less than 0.3, it is considered to be in the low-risk range, and further observation is allowed; if the probability value is between 0.3 and 0.6, it is considered to be in the medium-risk range, and further examination (such as imaging examination) should be considered to better assess the risk; if the probability value is greater than 0.6, it is considered to be in the high-risk range, and timely intervention or treatment should be carried out to avoid adverse effects on the physical or psychological development of the target child.

[0086] This concludes the risk analysis of physiological indicators for patients with precocious puberty.

[0087] In summary, the following steps were taken: Physiological indicator data across all dimensions were obtained from all patients with precocious puberty; one patient was randomly selected as the target patient; any dimension of the target patient was chosen as the target dimension; the deviation of the target patient from the target dimension was determined based on the data distribution of the target patient's physiological indicator data across all physiological indicator data; all other patients with precocious puberty were screened based on the deviation to obtain a similar patient group for the target patient's target dimension; the individual difference of the target patient in the target dimension was determined based on the similarity between the target patient and the similar patient group in the target dimension, as well as the correlation between the target dimension and other dimensions; the precocious puberty tendency in the target dimension was determined based on the changing characteristics of the proportion of patients with precocious puberty in the similar patient group under the physiological indicator data of the target dimension; all minor difference dimensions of the target patient were screened based on the degree of individual difference; the model error term was obtained based on the degree of individual difference of the target patient in all minor difference dimensions; a precocious puberty risk analysis regression model was obtained based on the individual difference degree of the target patient in each dimension, the precocious puberty tendency, and the model error term; and risk analysis was performed on the physiological indicator data of patients with precocious puberty based on the precocious puberty risk analysis regression model.

[0088] One embodiment of the present invention provides a risk analysis system for patients with early precocious puberty. The system includes a memory, a processor, and a computer program. The memory is used to store the corresponding computer program, and the processor is used to run the corresponding computer program. When the computer program runs in the processor, it can implement the methods described in steps S1-S3.

[0089] A third objective of this invention is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the methods described in steps S1-S3.

[0090] The fourth objective of this invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in steps S1-S3.

[0091] 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.

[0092] 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 method for risk analysis of patients in the early stages of precocious puberty, characterized in that, The method includes: acquiring physiological indicator data for all dimensions of all patients with precocious puberty; randomly selecting one patient with precocious puberty as the target patient; selecting any dimension of the target patient as the target dimension; obtaining the degree of deviation of the target patient in the target dimension based on the data distribution of the target patient's physiological indicator data in the target dimension among all physiological indicator data; filtering all other patients with precocious puberty based on the degree of deviation to obtain a similar patient group for the target patient in the target dimension, including: subtracting the degree of deviation from the physiological indicator data of the target patient in the target dimension to obtain the minimum value of the neighborhood, and adding the physiological indicator data of the target patient in the target dimension to the degree of deviation to obtain the maximum value of the neighborhood; obtaining the neighborhood range of the physiological indicator data of the target patient in the target dimension based on the minimum and maximum values ​​of the neighborhood; selecting all other patients with precocious puberty with the same physiological indicator data within the neighborhood range of the physiological indicator data of the target dimension, traversing all physiological indicator data within the neighborhood range to obtain a similar patient group for the target patient composed of all patients with precocious puberty; obtaining the similarity of the target patient and the similar patient group in the target dimension based on the data similarity of the target patient and the similar patient group in the target dimension, and the correlation between the target dimension and other dimensions. The method for obtaining the degree of individual differences includes: calculating the Pearson correlation coefficient between the target patient and each other dimension in the target dimension to obtain the correlation between the target patient and each other dimension; selecting a preset number of other dimensions with the largest correlation as the relevant dimensions of the target dimension; obtaining the degree of individual differences according to the formula for calculating the degree of individual differences; obtaining the degree of precocious puberty tendency in the target dimension based on the changing characteristics of the proportion of patients with precocious puberty in the physiological indicator data of the target dimension in similar patient groups; filtering out all minor difference dimensions of the target patient based on the degree of individual differences; obtaining a model error term based on the degree of individual differences of the target patient in all minor difference dimensions, wherein the method for obtaining the model error term includes: taking the dimensions where the degree of individual differences of the target patient is less than a preset first threshold as minor difference dimensions; amplifying the degree of individual differences of the target patient in each minor difference dimension and averaging the data to obtain the model error term; obtaining a precocious puberty risk analysis regression model based on the degree of individual differences of the target patient in each dimension, the degree of precocious puberty tendency, and the model error term; and performing risk analysis on the physiological indicator data of patients with precocious puberty based on the precocious puberty risk analysis regression model.

2. The method for risk analysis of patients with early precocious puberty according to claim 1, characterized in that, The method for obtaining the degree of dimensional deviation includes: obtaining the degree of dimensional deviation according to the formula for calculating the degree of dimensional deviation, as shown below: In the formula, This indicates the degree of deviation of the target patient from the target dimension; Indicates the number of patients with precocious puberty; This represents the maximum value of the target dimension physiological indicator data among all physiological indicator data; This represents the minimum value of the target dimension of the physiological indicator data among all physiological indicator data; This represents the physiological indicators of the target patient in the target dimension; This represents the average value of all physiological indicators for the target dimension. Represents the absolute value function; This represents the logarithmic function with the natural constant as the base.

3. The method for risk analysis of patients with early precocious puberty according to claim 1, characterized in that, The method for obtaining the formula for calculating the degree of individual differences includes: The formula for calculating the degree of individual differences is as follows: In the formula, This indicates the degree of individual differences among target patients in the target dimension; This represents the variance of all physiological indicators across the target dimension for similar patient groups. Indicates the preset number of related dimensions; Indicates the first [patient's] [number] Physiological indicators of relevant dimensions in similar patient groups Standard scores among physiological indicator data of each relevant dimension; This indicates the target dimension of the target patient and the first The correlation coefficients between physiological indicator data of each relevant dimension; This represents the sum of correlation coefficients between the target dimension and the physiological indicator data of each relevant dimension for the target patient; Represents the normalization function; This represents the absolute value function.

4. The method for risk analysis of patients with early precocious puberty according to claim 1, characterized in that, The method for obtaining the degree of precocious puberty tendency includes: obtaining the degree of precocious puberty tendency according to a calculation formula for the degree of precocious puberty tendency, the calculation formula for the degree of precocious puberty tendency is as follows: In the formula, Indicates the degree of precocious puberty tendency in the target dimension; This indicates the number of other physiological indicator data points for the target patient within the neighborhood of the target dimension's physiological indicator data. This represents the first position within the neighborhood of physiological indicator data in the target dimension among similar patient groups. The percentage of patients with precocious puberty based on other physiological indicators; This represents the first position of a similar patient group within the neighborhood of physiological indicator data in the target dimension. The percentage of patients with precocious puberty based on other physiological indicators; This represents the absolute value function.

5. The method for risk analysis of patients in the early stages of precocious puberty according to claim 1, characterized in that, The method for obtaining the regression model for the risk analysis of precocious puberty includes: obtaining the regression model for the risk analysis of precocious puberty according to the formula for the regression model for the risk analysis of precocious puberty, as shown below: In the formula, Indicates the probability of precocious puberty in the target patient; This indicates the degree of precocious puberty tendency in the target patient in the first dimension; This indicates the degree of individual variability among target patients in the first dimension; This indicates the degree of precocious puberty tendency in the target patient in the second dimension; This indicates the degree of individual variability among target patients in the second dimension; Indicates the target patient in the first The degree of precocious puberty tendency in each dimension; Indicates the target patient in the first month The degree of individual differences in each dimension; Represents the model error term; This represents an exponential function with the natural constant as its base.

6. A risk analysis system for patients in the early stages of precocious puberty, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for risk analysis of early-stage precocious puberty patients as described in any one of claims 1 to 5.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for risk analysis of early-stage precocious puberty patients as described in any one of claims 1 to 5.

Images