A method and device for monitoring cross-age developmental stages based on a dynamic phase line chart

Abstract

The application discloses a kind of based on dynamic phase line chart cross-age developmental stage monitoring method and device, comprising: the relationship model between the known developmental stage of different ages of the person to be monitored is constructed;The age of each to-be-monitored interval of the person to be monitored is input into the relationship model of each developmental stage, the corresponding output value is obtained by prediction and is mapped as the numerical value of the age of each to-be-monitored interval in the normalized probability mass function corresponding to each developmental stage;The midpoint cumulative probability corresponding to the age of each to-be-monitored interval in each developmental stage is calculated using the intermediate P value method, and the midpoint cumulative probability is converted into the corresponding standard deviation score using the probit function;According to the standard deviation score corresponding to the age of each to-be-monitored interval in each developmental stage, a dynamic phase line chart is drawn, the evolution trend of developmental stage over time is visualized through the dynamic phase line chart, and the abnormal development period is identified.The application can reduce subjective misjudgment of developmental stage abnormalities.

Description

Technical Field

[0001] This invention relates to the field of data analysis, and specifically to a method and apparatus for monitoring cross-age developmental stages based on dynamic stage line graphs. Background Technology

[0002] In clinical practice regarding pediatric growth and development, the diagnosis and monitoring of endocrine disorders such as precocious puberty and delayed puberty heavily rely on the assessment of discrete developmental stages, such as Tanner staging and bone age determination. However, existing technologies have limitations, such as age-dependent interference, lack of continuous quantification capabilities, insufficient visualization tools, and inadequate primary healthcare resources, which directly affect the accuracy and efficiency of clinical decision-making. Summary of the Invention

[0003] The purpose of this application is to propose a method and device for monitoring cross-age developmental stages based on dynamic stage line graphs, addressing the aforementioned technical problems.

[0004] In a first aspect, the present invention provides a method for monitoring cross-age developmental stages based on a dynamic stage line graph, comprising the following steps:

[0005] The known discrete developmental stages corresponding to different ages of the individuals to be monitored are obtained and modeled to obtain a model of the relationship between age and different developmental stages;

[0006] The age of each monitoring interval of the person to be monitored is input into the relational model of each developmental stage, and the corresponding output value is predicted and mapped to the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage.

[0007] Based on the normalized probability mass function value corresponding to the age of each monitoring interval at each developmental stage, the midpoint cumulative probability corresponding to the age of each monitoring interval at each developmental stage is calculated using the intermediate P-value method. The probit function is then used to convert the midpoint cumulative probability corresponding to the age of each monitoring interval at each developmental stage into the standard deviation score corresponding to the age of each monitoring interval at each developmental stage.

[0008] A dynamic stage line graph is plotted based on the standard deviation of the age in each developmental stage for each monitoring interval. The dynamic stage line graph visualizes the evolution trend of developmental stages over time and identifies abnormal developmental periods.

[0009] Preferably, the developmental stage includes the stages divided by the Tanner staging, and the abnormal developmental period is the age group corresponding to the standard deviation score outside the ±2 range.

[0010] As a preferred approach, the modeling method adopts a generalized additive model or an ordered logistic regression model, where the independent variable is age and the dependent variable is developmental stage; the mapping method includes the Sigmoid function.

[0011] As a preferred option, it also includes:

[0012] Calculate the 95% confidence interval of the standard deviation score using Bootstrap resampling;

[0013] The developmental stage corresponding to the predicted standard deviation score closest to 0 was selected as the predicted developmental stage, and the calibration degree between the predicted developmental stage and the actual developmental stage was verified by Hosmer-LeMauch.

[0014] In response to the determination that the 95% confidence interval is less than the first threshold and the calibration degree is greater than the second threshold, the parameters of the relational model are the optimal parameters;

[0015] In response to determining that the 95% confidence interval is greater than or equal to the first threshold, or the calibration degree is less than the second threshold, the parameters of the relational model are readjusted until the optimal parameters are obtained.

[0016] Preferably, the midpoint cumulative probability of the age of each monitoring interval at each developmental stage is calculated using the intermediate P-value method based on the normalized probability mass function value corresponding to the age of each monitoring interval at each developmental stage. Specifically, this includes:

[0017] Iterate through the values ​​of the normalized probability mass function corresponding to each monitoring interval and each developmental stage. Add the value of the normalized probability mass function corresponding to the age at the start of one monitoring interval and the age at the end of one monitoring interval and the value of the normalized probability mass function corresponding to the age at the end of one developmental stage, and then divide by two to obtain the value of the probability mass function at the midpoint.

[0018] Calculate the cumulative sum of the normalized probability mass function values ​​for each age in one of the monitoring intervals and subtract the probability mass function value at the midpoint to obtain the cumulative probability at the midpoint of each age in one of the monitoring intervals.

[0019] The process continues until all monitored intervals and all developmental stages have been traversed, and the values ​​of the normalized probability mass function corresponding to each interval are obtained, thus yielding the cumulative probability of the age at the midpoint of each developmental stage for each monitored interval.

[0020] As a preferred option, the dynamic stage line graph uses age as the horizontal axis and the standard deviation of age for each developmental stage for each monitored interval as the vertical axis.

[0021] Secondly, the present invention provides a cross-age developmental stage monitoring device based on a dynamic stage line graph, comprising:

[0022] The model building module is configured to acquire and model the known discrete developmental stages of the monitored individuals at different ages, thereby obtaining a model of the relationship between age and different developmental stages.

[0023] The prediction module is configured to input the age of each monitoring interval of the person to be monitored into the relational model of each developmental stage, predict the corresponding output value and map it to the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage.

[0024] The standard deviation score calculation module is configured to calculate the midpoint cumulative probability of the age of each monitoring interval at each developmental stage using the intermediate P-value method based on the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage, and use the probit function to convert the midpoint cumulative probability of the age of each monitoring interval at each developmental stage into the standard deviation score of the age of each monitoring interval at each developmental stage.

[0025] The visualization output module is configured to draw a dynamic stage line graph based on the standard deviation score corresponding to the age of each developmental stage in each monitoring interval. The dynamic stage line graph visualizes the evolution trend of developmental stages over time and identifies abnormal developmental periods.

[0026] Thirdly, the present invention provides an electronic device including one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0027] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any of the implementations of the first aspect.

[0028] Fifthly, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the method as described in any of the implementations in the first aspect.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] (1) The cross-age developmental stage monitoring method based on dynamic stage line diagram mentioned in this invention calculates the cumulative probability of the midpoint corresponding to each developmental stage by means of the intermediate P-value method, eliminates age bias, provides objective quantitative basis, and reduces subjective judgment errors such as Tanner staging.

[0031] (2) The cross-age developmental stage monitoring method based on dynamic stage line graph mentioned in this invention uses the range of standard deviation scores obtained by midpoint cumulative probability transformation to determine whether it is in an abnormal developmental stage, captures early abnormalities, and provides data support for the timing of GnRH analog treatment.

[0032] (3) The cross-age developmental stage monitoring method based on dynamic stage line graph mentioned in this invention can help doctors quickly judge abnormalities such as precocious puberty, developmental delay, and rapid puberty through the visualized dynamic stage line graph, reduce subjective misjudgment, and the automated tool helps the grassroots complete the initial screening, alleviate the problem of uneven distribution of medical care, and provide a new generation of standardized, visualized and intelligent tools for the clinical management of children's developmental abnormalities, improve the efficiency of doctor-patient communication, and have significant clinical application potential and social benefits. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0034] Figure 1 This is a flowchart illustrating a cross-age developmental stage monitoring method based on a dynamic stage line graph, as an embodiment of this application.

[0035] Figure 2 A dynamic stage line graph of girls in a certain region was drawn using the cross-age developmental stage monitoring method based on dynamic stage line graphs according to an embodiment of this application.

[0036] Figure 3 A dynamic stage line graph of boys in a certain region was drawn using the cross-age developmental stage monitoring method based on dynamic stage line graphs according to an embodiment of this application.

[0037] Figure 4 This is a schematic diagram of a cross-age developmental stage monitoring device based on a dynamic stage line graph, which is an embodiment of this application.

[0038] Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0040] Figure 1 The illustration shows an embodiment of the present application providing a method for monitoring cross-age developmental stages based on a dynamic stage line graph, comprising the following steps:

[0041] S1: Obtain the known discrete developmental stages of the individuals to be monitored at different ages and model them to obtain a relationship model between age and different developmental stages.

[0042] In a specific embodiment, the developmental stage includes the stages divided by the Tanner staging, and the abnormal developmental period is the age group corresponding to the standard deviation score outside the ±2 range.

[0043] In specific embodiments, the modeling method adopts a generalized additive model or an ordered logistic regression model, where the independent variable is age and the dependent variable is developmental stage; the mapping method includes the Sigmoid function.

[0044] The embodiments of this application employ a generalized additive model (GAM) or an ordered logistic regression model to smoothly model the age dependence of discrete developmental stages (such as Tanner stages), thereby obtaining a relationship model between age and different developmental stages. That is, a relationship model about age is established for different developmental stages. Subsequently, the Sigmoid function is combined to map the output value predicted by the relationship model to the corresponding normalized probability mass function value, thereby capturing the nonlinear relationship between age and the probability of different developmental stages.

[0045] In one embodiment, a generalized additive model g(μ) = β0 + f(x) is used in the modeling process, where β0 is a constant, f(•) represents the equilibrium function, x is the independent variable of the relational model (age), and g(μ) is the quantitative characteristic corresponding to stage μ in the Tanner stage classification. The Tanner stage classification consists of 1 to 5 stages. In other embodiments, other developmental stage classification methods may also be used.

[0046] S2 inputs the age of each monitoring interval of the person to be monitored into the relational model of each developmental stage, predicts the corresponding output value, and maps it to the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage.

[0047] Specifically, to reduce the interference of age on the distribution of different developmental stages and to enable direct comparison of the developmental status of individuals of different ages, the embodiments of this application employ the median P-value method to calculate the midpoint cumulative probability corresponding to each Tanner stage. First, the age to be predicted is divided into several monitoring intervals, each containing several ages. Each age in each monitoring interval is input into the relational model corresponding to each developmental stage. The output value of the relational model for the corresponding developmental stage is predicted, and then mapped using the Sigmoid function to the value of the normalized probability mass function (PMF) corresponding to each age in each monitoring interval at that developmental stage. The value of the normalized probability mass function is the original probability corresponding to the Tanner stage.

[0048] S3. Based on the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage, the midpoint cumulative probability corresponding to the age of each monitoring interval at each developmental stage is calculated using the intermediate P-value method. The probit function is then used to convert the midpoint cumulative probability corresponding to the age of each monitoring interval at each developmental stage into the standard deviation score corresponding to the age of each monitoring interval at each developmental stage.

[0049] In a specific embodiment, the midpoint cumulative probability of the age of each monitored interval at each developmental stage is calculated using the intermediate P-value method based on the value of the normalized probability mass function corresponding to the age of each monitored interval at each developmental stage. Specifically, this includes:

[0050] Iterate through the values ​​of the normalized probability mass function corresponding to each monitoring interval and each developmental stage. Add the value of the normalized probability mass function corresponding to the age at the start of one monitoring interval and the age at the end of one monitoring interval and the value of the normalized probability mass function corresponding to the age at the end of one developmental stage, and then divide by two to obtain the value of the probability mass function at the midpoint.

[0051] Calculate the cumulative sum of the normalized probability mass function values ​​for each age in one of the monitoring intervals and subtract the probability mass function value at the midpoint to obtain the cumulative probability at the midpoint of each age in one of the monitoring intervals.

[0052] The process continues until all monitored intervals and all developmental stages have been traversed, and the values ​​of the normalized probability mass function corresponding to each interval are obtained, thus yielding the cumulative probability of the age at the midpoint of each developmental stage for each monitored interval.

[0053] Specifically, the principle of the intermediate P-value method in the embodiments of this application is to "halve" the original probability in half and then sum them up. This is equivalent to using the cumulative probability of the midpoint corresponding to each developmental stage of each monitoring interval as the query value to query the quantile of the standard normal distribution, thus obtaining the standard deviation score corresponding to each developmental stage of each monitoring interval.

[0054] In calculating the cumulative probability of the midpoint of each monitored interval at each developmental stage, the normalized probability mass function values ​​(raw probabilities) of the starting and ending ages of one monitored interval at one developmental stage are first added together, and then divided by two to obtain the probability mass function value of the midpoint of one monitored interval at one developmental stage. Then, combined with the raw probabilities of each age of one monitored interval at one developmental stage, the cumulative probability of the midpoint of one monitored interval at one developmental stage is calculated, as shown in the following formula:

[0055] probs = np.cumsum(probabilities_origin) - probabilities_half;

[0056] Where np.cumsum represents the cumulative sum function of the array, probability_half represents the value of the probability mass function of one of the monitored intervals being at the midpoint of one of the developmental stages, probability_origin represents the original probability of one of the monitored intervals being at one of the developmental stages, and probs represents the cumulative probability of one of the monitored intervals being at the midpoint of one of the developmental stages.

[0057] Finally, by inputting the cumulative probability of the midpoint of one of the monitored intervals at one developmental stage into the inverse function of the standard normal distribution, the standard deviation (SDS) of the age of one of the monitored intervals at one developmental stage can be calculated. The standard deviation (SDS) represents the deviation value under the standard normal distribution scale. Alternatively, it can be described as using the probit function to convert the cumulative probability of the midpoint of one of the monitored intervals at one developmental stage into the corresponding standard deviation (SDS).

[0058] SDS directly reflects the developmental level relative to peers. For example, SDS = +2.0 indicates that the development is ahead by 2 standard deviations. SDS can be used to quantify an individual's developmental rate. Age groups with SDS within ±2 are considered normal developmental periods, while age groups outside this range are considered abnormal developmental periods.

[0059] In specific embodiments, it also includes:

[0060] Calculate the 95% confidence interval of the standard deviation score using Bootstrap resampling;

[0061] The developmental stage corresponding to the predicted standard deviation score closest to 0 was selected as the predicted developmental stage, and the calibration degree between the predicted developmental stage and the actual developmental stage was verified by Hosmer-LeMauch.

[0062] In response to the determination that the 95% confidence interval is less than the first threshold and the calibration degree is greater than the second threshold, the parameters of the relational model are the optimal parameters;

[0063] In response to determining that the 95% confidence interval is greater than or equal to the first threshold, or the calibration degree is less than the second threshold, the parameters of the relational model are readjusted until the optimal parameters are obtained.

[0064] Specifically, in the embodiments of this application, the 95% confidence interval of the SDS is calculated by Bootstrap resampling (1000 times), and the stability of the relational model is evaluated using the 95% confidence interval. If the 95% confidence interval of the SDS is greater than or equal to a first threshold, the relational model is considered to be unstable; if the 95% confidence interval of the SDS is less than the first threshold, the relational model is considered to be stable.

[0065] Furthermore, the Tanner stage corresponding to the predicted standard deviation score closest to 0 is selected as the predicted Tanner stage. The calibration between the predicted Tanner stage and the actual Tanner stage is verified using the Hosmer-Lemeshow test. If the p-value is greater than 0.05, the correlation model is considered validated; otherwise, it is not. If the correlation model is not stable or fails validation, the parameters of the correlation model are adjusted until the correlation model is both stable and validated. The parameters of the correlation model at this point are considered the optimal parameters, and these optimal parameters are used to further predict the standard deviation scores corresponding to the ages of the remaining monitored intervals at each developmental stage.

[0066] S4. Based on the standard deviation of the age of each monitoring interval at each developmental stage, a dynamic stage line graph is plotted. The evolution trend of developmental stages over time is visualized through the dynamic stage line graph, and abnormal developmental periods are identified.

[0067] In a specific embodiment, the dynamic stage line graph uses age as the horizontal axis and the standard deviation of age for each developmental stage for each monitored interval as the vertical axis.

[0068] Specifically, in the embodiments of this application, a dynamic stage graph is drawn with age as the horizontal axis and standard deviation score as the vertical axis to intuitively show the evolution trend of developmental stages over time, such as... Figure 2 and Figure 3As shown, developmental stages are visualized through dynamic stage line graphs, supporting the identification of abnormal developmental stages, such as a steep rise in the precocious puberty curve and a long-term stagnation in the developmental delay curve. By integrating the characteristics of dynamic stage line graphs, it supports both individualized prediction and dynamic stage display.

[0069] Further reference Figure 4 As an implementation of the methods shown in the above figures, this application provides an embodiment of a cross-age developmental stage monitoring device based on a dynamic stage line graph. This device embodiment is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0070] This application provides a cross-age developmental stage monitoring device based on a dynamic stage line graph, including:

[0071] Model building module 1 is configured to acquire and model the known discrete developmental stages of the monitored individuals at different ages, thereby obtaining a model of the relationship between age and different developmental stages.

[0072] Prediction module 2 is configured to input the age of each monitoring interval of the person to be monitored into the relational model of each developmental stage, predict the corresponding output value and map it to the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage.

[0073] The standard deviation score calculation module 3 is configured to calculate the midpoint cumulative probability of the age of each monitoring interval at each developmental stage using the intermediate P-value method based on the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage, and use the probit function to convert the midpoint cumulative probability of the age of each monitoring interval at each developmental stage into the standard deviation score of the age of each monitoring interval at each developmental stage.

[0074] The visualization output module 4 is configured to draw a dynamic stage line graph based on the standard deviation score corresponding to the age of each monitoring interval at each developmental stage. The dynamic stage line graph visualizes the evolution trend of developmental stages over time and identifies abnormal developmental periods.

[0075] Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. For example... Figure 5 As shown, the electronic device of this embodiment includes a processor 501 and a memory 502; wherein the memory 502 is used to store computer execution instructions; and the processor 501 is used to execute the computer execution instructions stored in the memory to implement the various steps performed by the electronic device in the above embodiment. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0076] Alternatively, the memory 502 can be either standalone or integrated with the processor 501.

[0077] When the memory 502 is set up independently, the electronic device also includes a bus 503 for connecting the memory 502 and the processor 501.

[0078] This invention also provides a computer storage medium storing computer execution instructions, which, when executed by processor 501, implement the above method.

[0079] This invention also provides a computer program product, including a computer program that, when executed by a processor 501, implements the above-described method.

[0080] In the embodiments provided by this invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0081] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0082] Furthermore, the functional modules in the various embodiments of this invention can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit formed by the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0083] The integrated modules implemented as software functional modules described above can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor 501 to execute some steps of the methods of the various embodiments of this application.

[0084] It should be understood that the processor 501 described above can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor, or the processor 501 can be any conventional processor 501. The steps of the method disclosed in this invention can be directly manifested as the hardware processor 501 executing the steps, or as a combination of hardware and software modules within the processor 501 executing the steps.

[0085] The memory 502 may include high-speed RAM memory, and may also include non-volatile memory NVM, such as at least one disk storage device, and may also be a USB flash drive, portable hard drive, read-only memory, disk or optical disc, etc.

[0086] Bus 503 can be an Industry Standard Architecture (ISA), a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Bus 503 can be divided into address bus, data bus, control bus, etc. For ease of illustration, the bus 503 in the accompanying drawings of this application is not limited to only one bus 503 or one type of bus 503.

[0087] The aforementioned storage medium can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0088] An exemplary storage medium is coupled to processor 501, enabling processor 501 to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of processor 501. Processor 501 and storage medium can reside in application-specific integrated circuits (ASICs). Alternatively, processor 501 and storage medium can exist as discrete components in an electronic device or host device.

[0089] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring cross-age developmental stages based on dynamic stage line graphs, characterized in that, Includes the following steps: The known discrete developmental stages corresponding to different ages of the individuals to be monitored are obtained and modeled to obtain a model of the relationship between age and different developmental stages; The age of each monitoring interval of the person to be monitored is input into the relational model of each developmental stage, and the corresponding output value is predicted and mapped to the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage. Based on the normalized probability mass function value corresponding to the age of each monitoring interval at each developmental stage, the midpoint cumulative probability corresponding to the age of each monitoring interval at each developmental stage is calculated using the intermediate P-value method. The probit function is then used to convert the midpoint cumulative probability corresponding to the age of each monitoring interval at each developmental stage into the standard deviation score corresponding to the age of each monitoring interval at each developmental stage. A dynamic stage line graph is plotted based on the standard deviation score corresponding to the age of each monitoring interval at each developmental stage. The dynamic stage line graph visualizes the evolution trend of developmental stages over time and identifies abnormal developmental periods.

2. The method for monitoring cross-age developmental stages based on dynamic stage line graphs according to claim 1, characterized in that, The developmental stages include those defined by the Tanner staging system, and the abnormal developmental period is the age range corresponding to a standard deviation score outside the ±2 range.

3. The method for monitoring cross-age developmental stages based on dynamic stage line graphs according to claim 1, characterized in that, The modeling method employs a generalized additive model or an ordered logistic regression model, where the independent variable is age and the dependent variable is developmental stage; the mapping method includes the Sigmoid function.

4. The method for monitoring cross-age developmental stages based on dynamic stage line graphs according to claim 1, characterized in that, Also includes: Calculate the 95% confidence interval of the standard deviation score using Bootstrap resampling; The developmental stage corresponding to the predicted standard deviation score closest to 0 was selected as the predicted developmental stage, and the calibration degree between the predicted developmental stage and the actual developmental stage was verified by Hosmer-LeMauch. In response to the determination that the 95% confidence interval is less than the first threshold and the calibration degree is greater than the second threshold, the parameters of the relational model are the optimal parameters. In response to determining that the 95% confidence interval is greater than or equal to the first threshold, or the calibration degree is less than the second threshold, the parameters of the relational model are readjusted until the optimal parameters are obtained.

5. The method for monitoring cross-age developmental stages based on a dynamic stage line graph according to claim 1, characterized in that, Based on the normalized probability mass function value corresponding to the age of each monitoring interval at each developmental stage, the midpoint cumulative probability corresponding to the age of each monitoring interval at each developmental stage is calculated using the intermediate P-value method. Specifically, this includes: Iterate through the values ​​of the normalized probability mass function corresponding to each monitoring interval and each developmental stage. Add the value of the normalized probability mass function corresponding to the age at the start of one monitoring interval and the age at the end of one monitoring interval and the value of the normalized probability mass function corresponding to the age at the end of one developmental stage, and then divide by two to obtain the value of the probability mass function at the midpoint. Calculate the cumulative sum of the normalized probability mass function values ​​for each age in one of the monitoring intervals and subtract the probability mass function value at the midpoint to obtain the cumulative probability at the midpoint of each age in one of the monitoring intervals. The process continues until all monitored intervals and all developmental stages have been traversed, and the values ​​of the normalized probability mass function corresponding to each interval are obtained, thus yielding the cumulative probability of the age at the midpoint of each developmental stage for each monitored interval.

6. The method for monitoring cross-age developmental stages based on a dynamic stage line graph according to claim 1, characterized in that, The dynamic stage line graph uses age as the horizontal axis and the standard deviation of age for each developmental stage for each monitored interval as the vertical axis.

7. A cross-age developmental stage monitoring device based on a dynamic stage line graph, characterized in that, include: The model building module is configured to acquire and model the known discrete developmental stages of the monitored individuals at different ages, thereby obtaining a model of the relationship between age and different developmental stages. The prediction module is configured to input the age of each monitoring interval of the person to be monitored into the relational model of each developmental stage, predict the corresponding output value and map it to the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage. The standard deviation score calculation module is configured to calculate the midpoint cumulative probability of the age of each monitoring interval at each developmental stage using the intermediate P-value method based on the value of the normalized probability mass function corresponding to the age of each monitoring interval at each developmental stage, and use the probit function to convert the midpoint cumulative probability of the age of each monitoring interval at each developmental stage into the standard deviation score of the age of each monitoring interval at each developmental stage. The visualization output module is configured to draw a dynamic stage line graph based on the standard deviation score corresponding to the age of each developmental stage in each monitoring interval. The dynamic stage line graph visualizes the evolution trend of developmental stages over time and identifies abnormal developmental periods.

8. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

Images