Child integrated growth and development assessment management system

Abstract

The invention discloses an integrated growth and development evaluation management system for children, and particularly relates to the technical field of growth and development evaluation. Child growth and development stages are divided through child physiological parameter collection and dynamic time sequence analysis based on machine learning; processing the child limb proportion time sequence data by using a dynamic time warping algorithm, and evaluating the synchronism of bone growth and soft tissue development; identifying whether the children have development deviation risks or not according to the growth and development stages and synchronism; for children with development deviation risks, combining gene information, and adopting a genetic algorithm and a dynamic programming model to evaluate the growth potential of children individuals; according to the method, the synchronism of child bone growth and soft tissue development and child individual growth potential and development adaptability are subjected to correlation analysis, the probability of potential development abnormality is evaluated, whether personalized intervention measures are started or not is judged, comprehensive monitoring and risk early warning of child growth and development states are achieved, and scientificity and practicability are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of growth and development assessment, and more specifically, to an integrated growth and development assessment and management system for children. Background Art

[0002] At present, the management of children's growth and development mainly relies on regular physical examinations and doctors' experience and judgment, lacking real-time monitoring and accurate risk warning methods. In existing technologies, multimodal physiological data, limb proportion information, and genetic information are collected in a scattered manner, making it difficult to effectively integrate and deeply analyze them, resulting in the difficulty of timely detection of potential developmental abnormalities in children. Traditional data processing methods cannot fully capture the dynamic changes and stage characteristics of children's growth, and it is difficult to accurately assess the synchronization of bone growth and soft tissue development and individual growth potential.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an integrated growth and development assessment and management system for children to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An integrated growth and development assessment and management system for children, comprising a development stage determination module, a synchronization assessment module, a deviation risk identification module, a growth potential assessment module and an abnormal probability assessment module;

[0007] The developmental stage determination module collects children's real-time multimodal physiological parameter data, divides children's growth and development status using a dynamic time series analysis algorithm based on machine learning, and determines children's growth and development stages;

[0008] The synchronization assessment module performs a dynamic time warping algorithm on the continuously collected children's limb proportion time series data to assess the synchronization of children's bone growth and soft tissue development;

[0009] The deviation risk identification module uses a decision tree to identify whether a child has a developmental deviation risk based on the child's growth and development stage and the synchronization of the child's bone growth and soft tissue development;

[0010] For children at risk of developmental deviation, the growth potential assessment module analyzes the children's genetic information and uses a genetic algorithm combined with a dynamic programming model to assess the children's individual growth potential.

[0011] The abnormality probability assessment module conducts correlation analysis on the synchronization of children's bone growth and soft tissue development and their individual growth potential, assesses the probability of potential developmental abnormalities in children, and determines whether to initiate personalized intervention measures.

[0012] In a preferred embodiment, real-time multimodal physiological parameter data of children are collected, and the growth and development status of children is divided using a dynamic time series analysis algorithm based on machine learning to determine the growth and development stage of children, specifically:

[0013] Collect children's multimodal physiological data in real time;

[0014] Clean the children's multimodal physiological data series and achieve time series synchronization correction;

[0015] Build dynamic time series models based on machine learning to extract key features and patterns;

[0016] Use dynamic time series analysis algorithm to divide growth states and output growth stage division indicators

[0017] Determine the children's growth and development stages based on growth stage division indicators.

[0018] In a preferred embodiment, a dynamic time warping algorithm is performed on the continuously collected children's limb proportion time series data to evaluate the synchronization of children's bone growth and soft tissue development, specifically:

[0019] Obtain continuous children's limb proportion time series data, covering bone and soft tissue parameters;

[0020] Use dynamic time warping algorithm to achieve time series data alignment;

[0021] Calculate the difference between bone growth rate and soft tissue development rate;

[0022] To assess the synchronization of children's bone growth and soft tissue development based on difference indicators.

[0023] In a preferred embodiment, based on the growth and development stage of children and the synchronization of bone growth and soft tissue development of children, a decision tree is used to identify whether a child has a risk of developmental deviation, specifically:

[0024] Obtain the results of the division of children's growth and development stages, and define the data of children's growth and development stages;

[0025] The data of children's growth and development stages were integrated with the synchronization evaluation index to construct a standardized feature vector;

[0026] A decision tree model was designed and feature vectors were input for classification training to identify whether children were at risk of developmental deviation.

[0027] In a preferred embodiment, the genetic information of the children is analyzed and a genetic algorithm combined with a dynamic programming model is used to evaluate the individual growth potential of the children, specifically:

[0028] Collect genetic information of children at risk of developmental deviations and perform feature extraction;

[0029] Genetic algorithm is used to initialize multiple candidate solutions of children's individual growth potential;

[0030] The dynamic programming model is introduced into the algorithm iteration to evaluate the adaptability of the candidate solutions with growth potential;

[0031] Output the assessment results of children’s individual growth potential.

[0032] In a preferred embodiment, the synchronization of children's bone growth and soft tissue development and their individual growth potential are analyzed to assess the probability of potential developmental abnormalities in children and determine whether to initiate personalized intervention measures, specifically:

[0033] The correlation analysis between synchronization evaluation index and adaptability score was conducted based on the correlation function;

[0034] Based on the association results, the probability value of potential developmental abnormalities is calculated to determine whether to initiate personalized intervention measures.

[0035] In a preferred embodiment, the probability value of potential developmental abnormality is calculated based on the association results to determine whether to initiate personalized intervention measures, specifically:

[0036] A developmental abnormality probability threshold is preset, and the developmental abnormality probability value is compared with the developmental abnormality probability threshold:

[0037] When the developmental abnormality probability value is greater than or equal to the developmental abnormality probability threshold, it indicates that the child has a high probability of potential developmental abnormality;

[0038] When the developmental abnormality probability value is less than the developmental abnormality probability threshold, it indicates that the child's potential developmental abnormality probability is low and there is no need to initiate personalized intervention measures.

[0039] The technical effects and advantages of the integrated growth and development assessment and management system for children of the present invention are as follows:

[0040] Through the deep integration of multimodal physiological parameter data, limb proportion time series data and genetic information, dynamic time series analysis, dynamic time warping, decision trees, genetic algorithms and dynamic programming models are used to achieve accurate division and real-time monitoring of children's growth and development stages. It can not only objectively evaluate the synchronization of bone growth and soft tissue development, but also conduct a comprehensive evaluation of the growth potential and adaptability of children at risk of developmental deviation at the genetic level, and then calculate the probability value of potential developmental abnormalities, improve data integration and intelligent analysis capabilities, overcome the shortcomings of traditional physical examinations such as information lag and strong subjectivity in evaluation, and provide a scientific and accurate early warning and personalized intervention basis for children's health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a structural schematic diagram of an integrated growth and development assessment and management system for children according to the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example 1

[0044] Figure 1 The present invention provides an integrated growth and development assessment and management system for children, comprising a development stage determination module, a synchronization assessment module, a deviation risk identification module, a growth potential assessment module and an abnormal probability assessment module;

[0045] The developmental stage determination module collects children's real-time multimodal physiological parameter data, divides children's growth and development status using a dynamic time series analysis algorithm based on machine learning, and determines children's growth and development stages;

[0046] The synchronization assessment module performs a dynamic time warping algorithm on the continuously collected children's limb proportion time series data to assess the synchronization of children's bone growth and soft tissue development;

[0047] The deviation risk identification module uses a decision tree to identify whether a child has a developmental deviation risk based on the child's growth and development stage and the synchronization of the child's bone growth and soft tissue development;

[0048] For children at risk of developmental deviation, the growth potential assessment module analyzes the children's genetic information and uses a genetic algorithm combined with a dynamic programming model to assess the children's individual growth potential.

[0049] The abnormality probability assessment module conducts correlation analysis on the synchronization of children's bone growth and soft tissue development and their individual growth potential, assesses the probability of potential developmental abnormalities in children, and determines whether to initiate personalized intervention measures.

[0050] Specifically, we collect children's real-time multimodal physiological parameter data, use a dynamic time series analysis algorithm based on machine learning to divide the children's growth and development status, and determine the children's growth and development stages, including:

[0051] Real-time collection of children's multimodal physiological data: In order to comprehensively monitor the growth and development of children, multimodal physiological data is obtained in real time through multiple sensors. Multimodal physiological data includes but is not limited to: body surface temperature, pulse changes, skin resistance, respiratory rhythm, etc. In order to ensure the accuracy and continuity of the collected multimodal physiological data, each sensor needs to be calibrated. During the calibration process, the reference value is used for comparison and the calibration factor is set. The calibration factor is set to (in represents the calibration coefficient, whose value is determined by the standard reference sample), for multimodal physiological data Correction is performed, and its expression is:

[0052] ;in, represents the corrected multimodal physiological data sequence; Indicates time; represents the calibration factor; Represents multimodal physiological data collected by sensors.

[0053] Since the physiological data collected by each sensor have different sampling frequencies and time windows, data fusion technology is used to integrate the physiological data. The physiological data collected by each sensor are defined as (in represents different sensor numbers), the integrated multimodal physiological data sequence is recorded as:

[0054] ;in, Indicates at time When , the multimodal physiological data sequence after fusion processing; represents the data fusion function; Indicates the number of sensors.

[0055] Clean the children's multimodal physiological data sequence and realize time series synchronization correction: use the outlier detection algorithm based on statistical methods to identify and eliminate abnormal points in multimodal physiological data. For example, set the mean value in the data window to , standard deviation is , using the three sigma criterion (i.e. if the data point exceeds , it is considered abnormal), the cleaned multimodal physiological data sequence is recorded as , whose expression is:

[0056] ;in, represents the cleaned multimodal physiological data sequence; Represents the mean value within the data window; Represents the standard deviation within the data window; It indicates that when a data point is judged to be abnormal, the estimated value is obtained by interpolating the adjacent normal data points.

[0057] In order to solve the clock drift problem that may occur during the multimodal physiological data acquisition process, the time sequence alignment of the data is achieved through the timestamp matching algorithm. The cross-correlation algorithm is used to calculate the delay between each data sequence, and the data is interpolated and corrected so that each data sequence is synchronized under the same time reference. The time delay between a data sequence and the standard time sequence is defined as , then the correction formula is: ;in, represents a multimodal physiological data sequence after time series synchronization correction; Represents the time delay between the data series and the standard time series.

[0058] Build a dynamic time series model based on machine learning to extract key features and patterns: After completing data preprocessing, build a machine learning model to dynamically model the multimodal physiological data sequence and extract the key features and patterns of children's growth and development, specifically:

[0059] Using sliding window technology to analyze multimodal physiological data sequences Perform local feature extraction and define the sliding window size as , and calculate the statistical features in each sliding window, such as mean, variance, peak value, etc. Define the multimodal physiological data in the sliding window as , calculate the mean The formula is: ;in, represents the average eigenvalue calculated within the sliding window; Indicates the size of the sliding window; Indicates the first The value of each multimodal physiological data point.

[0060] Other statistical features (such as variance, peak, etc.) are calculated similarly and are all components of the feature vector.

[0061] The long short-term memory network is used to construct a time series model to capture the temporal correlation in the growth and development of children. The long short-term memory network model constructed is defined as , the input of the long short-term memory network model is a feature vector sequence , the output is the hidden state sequence , the expression is: ;in, Represents the implicit state of the output; Represents the Long Short-Term Memory Network model.

[0062] Based on the hidden state sequence , use clustering algorithms (such as K-Means or DBSCAN) to classify the latent states and identify the patterns corresponding to different growth and development stages. Define the clustering result as , each cluster center represents a typical growth and development pattern. The calculation formula is: ;in, Indicates The center vector of each cluster; Indicates The total number of data samples in the clusters; Indicates The sample in The hidden state vector in each cluster.

[0063] Through clustering, key characteristic patterns associated with different growth stages can be automatically identified.

[0064] Use dynamic time series analysis algorithm to divide the growth state and output growth stage division indicators: based on the extracted implicit state sequence And clustering results , design a state partitioning model, which uses a hidden Markov model to calibrate the multimodal physiological data sequence after time synchronization correction To model the state transition. The hidden Markov model is denoted as , where the state set is defined , the transition probability matrix is ​​recorded as , the observation probability is The hidden Markov model formula is: ;in, Indicates that given the observed data (i.e., the implicit state of the output) condition, the child is in a growth state The conditional probability of Represents a state in the hidden Markov model, corresponding to a certain growth and development stage of a child; represents a hidden Markov model; State transition probability matrix in hidden Markov model; Indicates that it is in a growing state The hidden state is observed The probability of observation.

[0065] Solve the hidden Markov model to obtain the optimal growth state sequence Each growth state Each corresponds to an indicator for dividing a growth and development stage.

[0066] The solution formula for the optimal state sequence is: ;in, represents the best growth state sequence determined by the hidden Markov model after optimal path search; It is a mathematical symbol, indicating that in all growth states Select the growth state that maximizes the probability expression; In the implicit state , state transition probability matrix And the observation probability Conditions, growth status The joint probability of .

[0067] Output It can be used as an indicator for dividing growth stages.

[0068] Determine the growth and development stage of children according to the growth stage division indicators: according to the sequence of optimal growth status , establish the mapping relationship between the state and the growth stage. Define the mapping function as , whose expression is: ;in, Indicates the growth and development stages of children, including the initial development stage, accelerated development stage and stable development stage; is the mapping function.

[0069] Specifically, a dynamic time warping algorithm is used to continuously collect children's limb proportion time series data to evaluate the synchronization of children's bone growth and soft tissue development, including:

[0070] Obtain continuous children's limb proportion time series data, covering bone and soft tissue parameters: Use multi-sensor fusion to obtain key parameters of children's bone and soft tissue development. Sensors include but are not limited to optical measurement equipment, ultrasonic scanners, etc., which are used to obtain growth data such as bone length, joint angle, muscle thickness, etc. All data are recorded according to a unified timestamp to ensure the time continuity and synchronization of the data. Define continuous time series data as: ;in, Indicates the sampling time The limb proportion data series collected below; Indicates the sampling time.

[0071] The collected limb proportion data sequence contains two main components: bone parameters and soft tissue parameters. The signal separation algorithm is used to perform a preliminary separation of the original data to obtain two subsequences. Decompose into and ;in, Indicates sampling time The bone growth data series below; Indicates sampling time The soft tissue development data sequence below.

[0072] Use dynamic time warping algorithm to achieve timing data alignment: Since bone growth and soft tissue development may produce timing deviations due to sensor sampling frequency, data loss or clock drift during the actual collection process, it is necessary to use a dynamic time warping algorithm to achieve timing alignment of the two sets of data to ensure the best match between the data sequences on the time axis.

[0073] The goal of the dynamic time warping algorithm is to find the optimal matching path so that the cumulative distance between two sets of data sequences is minimized. The alignment cost function is defined as: ;in, represents the cumulative alignment cost calculated by the dynamic time warping algorithm; It represents a specific alignment path, i.e., a set of mapping relationships, which determines the correspondence between bone growth data and soft tissue development data on the time axis; Represents the set of all possible alignment paths; Represents the distance metric function, which calculates the bone growth data at the sampling time and soft tissue development data at the time of alignment The difference between them is usually Euclidean distance; Indicates bone growth data at sampling time The value of Represents the corresponding moment in the soft tissue development data sequence mapped by the alignment path The value of represents the sampling time in the bone growth data series; Represents the sampling time corresponding to the sequence in the alignment path mapped to the soft tissue development data.

[0074] Calculate the difference between bone growth rate and soft tissue development rate: Derivative the aligned bone growth data and soft tissue development data respectively:

[0075] The formula for calculating bone growth rate is: ;in, Indicates the sampling time The instantaneous rate of bone growth.

[0076] Similarly, the formula for calculating the soft tissue development rate is: ;in, Indicates the sampling time The instantaneous rate of soft tissue development.

[0077] The difference between the bone growth rate and the soft tissue development rate is defined and expressed as an absolute value function:

[0078] ;in, Indicates the sampling time The difference between the bone growth rate and the soft tissue development rate.

[0079] By comparing the difference between bone growth rate and soft tissue development rate at different times, the asynchrony between bone growth and soft tissue development was quantified.

[0080] Assess the synchronization of children's bone growth and soft tissue development based on difference indicators: perform overall statistics on the difference indicators, and construct a synchronization evaluation index based on the similarity calculation method to assess the synchronization of children's bone growth and soft tissue development.

[0081] The calculation formula for defining the synchronization evaluation index is: ;in, It represents the synchronization evaluation index, and its value range is between 0 and 1; Indicates sampling time Total number of; Indicates the sampling time The difference between the bone growth rate and the soft tissue development rate.

[0082] The closer the synchronization evaluation index is to 1, the higher the synchronization between the child's bone growth and soft tissue development. That is, it indicates that the child's bone growth and soft tissue development maintain basically the same growth rate and change trend during the growth process, reflecting a coordinated and stable growth process, which indicates that the child's overall development is healthy and stable.

[0083] Specifically, based on the growth and development stage of children and the synchronization of bone growth and soft tissue development, a decision tree is used to identify whether children are at risk of developmental deviation, including:

[0084] Obtain the results of the division of children's growth and development stages: children's growth and development stages, including the initial development stage, accelerated development stage and stable development stage.

[0085] The data of children's growth and development stages are defined as: ;in, Indicates the time variable The growth and development stages of children. It indicates that the child is in the initial development stage; It indicates that the child is in a stage of accelerated development; Indicates that the child is in a stable development stage.

[0086] Integrate the children's growth and development stage data with the synchronization evaluation index to construct a standardized feature vector: Normalize the children's growth and development stage data. Define the normalized children's growth and development stage data as Based on the synchronization evaluation index and the normalized children's growth and development stage data, a standardized feature vector is constructed and recorded as: ;in, Represents a two-dimensional feature vector that combines the normalized children's growth and development stage data and the synchronization evaluation index; Represents the synchronization evaluation index.

[0087] Design a decision tree model, input feature vectors for classification training, and identify whether children are at risk of developmental deviation: Based on the constructed standardized feature vector , a decision tree classification model is used to determine the risk of children and screen and identify children with developmental deviation risks. The decision tree model is defined as ;in, Represents the developmental deviation risk determination result output by the decision tree model (the output is usually binary, 1 indicates that the child has a developmental deviation risk, and 0 indicates normal); Represents a decision tree classification function.

[0088] During the training process of the decision tree model, a large amount of labeled data is used for supervised learning, and the child's growth and development stage and synchronization evaluation index in the feature vector are used to build a tree structure, automatically generate branch judgment conditions, and form risk judgment nodes. The decision tree model has the advantages of being intuitive, highly interpretable, and having low computational complexity, and is suitable for rapid screening of children's growth and development status.

[0089] After the decision tree model is trained, the constructed standardized feature vector is input , and based on the developmental deviation risk determination results output by the decision tree model Identify children at risk for developmental deviations; among them, Indicates that the child is at risk of developmental deviation. Indicates normal.

[0090] Specifically, by analyzing the genetic information of children, a genetic algorithm combined with a dynamic programming model is used to evaluate the growth potential of individual children, including:

[0091] Collect genetic information of children at risk of developmental deviation and perform feature extraction: Obtain genetic information of children at risk of developmental deviation, defined as ;in, Indicates the number genetic information data of children.

[0092] We conduct an in-depth analysis of each child’s genetic information data to extract feature sequences related to growth potential, and define the feature extraction formula as follows: ;in, Indicates that from number The feature vectors extracted from the genetic information data of children reflect the gene sequence patterns and variation information related to growth potential; Represents a function for feature extraction of genetic information data using machine learning models, statistical analysis, or pattern recognition methods.

[0093] Using genetic algorithm to initialize multiple candidate solutions for children's individual growth potential: Based on eigenvector , the sampling genetic algorithm generates multiple candidate solutions, representing different prediction results of individual growth potential of children. The candidate solution set is defined as: ;in, Indicates the number The child is the first in the candidate solution set Growth potential candidate solutions; Represents the total number of growth potential candidate solutions generated by the genetic algorithm.

[0094] The generation of candidate solutions uses the genetic algorithm function: ;in, Represents the initialization function of the genetic algorithm, which is used to generate growth potential candidate solutions from the eigenvectors.

[0095] The initialization function includes basic operations such as selection, crossover, and mutation to ensure the diversity of candidate solutions with growth potential.

[0096] Introducing the dynamic programming model into the algorithm iteration to evaluate the adaptability of the growth potential candidate solution: In order to optimize the growth potential candidate solution and accurately evaluate the growth potential of children, the dynamic programming model is introduced to iteratively optimize the growth potential candidate solution generated by the genetic algorithm. The adaptability evaluation function of the growth potential candidate solution is defined as:

[0097] ;

[0098] in, Indicates the number of children The fitness score of each growth potential candidate solution; Represents the candidate solution for growth potential The score obtained by evaluating the partial adaptability of the genetic algorithm; Represents the dynamic programming model for the growth potential candidate solution Additional score obtained after iterative optimization; Represents the weight coefficient of some evaluation functions of genetic algorithm; Represents the weight coefficient of the evaluation part of the dynamic programming model. The weight coefficient satisfies .

[0099] In the iterative process of the dynamic programming model, a multi-stage optimal decision calculation is performed for each growth potential candidate solution, and the adaptability score is optimized through a recursive method. Specifically, the dynamic programming model uses the following iterative relationship to update the state of the candidate solution: ;in, Indicates the number of children The cumulative cost of the growth potential candidate solutions; Represents the candidate solution from the growth potential Growth potential candidate solution Immediate costs incurred when Indicates the number of children The cumulative cost of the growth potential candidate solutions; Represents the index set of candidate solutions in the dynamic programming model. The set contains all the growth potential candidate solutions to be evaluated, and the optimal conversion path is found by traversal.

[0100] The dynamic programming model is combined with the genetic algorithm, and the iterative update and optimal path search method are used to refine the adaptability score of the growth potential candidate solution. , ensuring that each growth potential candidate solution accurately reflects the child’s growth potential.

[0101] Output the evaluation results of children's individual growth potential: After the genetic algorithm generates growth potential candidate solutions and the dynamic programming model is iteratively optimized, all growth potential candidate solutions are and its adaptability score Compare and select the candidate solution with the highest growth potential with the highest fitness score. The final output result is defined as:

[0102] ;in, Indicates the number The final growth potential assessment results of the children are the candidate solutions with the highest adaptability scores; Indicates the number of children growth potential candidate solutions, that is, the growth potential candidate solutions with the highest fitness scores; Represents the index of the candidate solution with the highest growth potential with the highest fitness score determined after screening.

[0103] Specifically, the synchronization of children's bone growth and soft tissue development and their individual growth potential is analyzed to assess the probability of children's potential developmental abnormalities and determine whether to initiate personalized intervention measures, including:

[0104] The correlation analysis of the synchronization evaluation index and the adaptability score was performed according to the correlation function: the correlation analysis was performed between the synchronization evaluation index corresponding to the synchronization of children's bone growth and soft tissue development and the adaptability score corresponding to children's individual growth potential, and the correlation function was defined as:

[0105] ;in, represents the strength of the association between the synchronicity evaluation index and the adaptability score; Represents the calculation function of correlation analysis; represents the synchronicity evaluation index; Indicates the number of children The fitness score of each growth potential candidate solution.

[0106] Calculate the probability value of potential developmental abnormalities based on the association results to determine whether to initiate personalized intervention measures: Calculate the probability value of potential developmental abnormalities for children, specifically: ;in, It indicates the probability value of potential developmental abnormality of children; Represents a function that calculates the probability of dysplasia.

[0107] A developmental abnormality probability threshold is preset, and the developmental abnormality probability value is compared with the developmental abnormality probability threshold:

[0108] When the probability value of developmental abnormality is greater than or equal to the probability threshold of developmental abnormality, it indicates that the child has a high probability of potential developmental abnormality and the child's growth potential and developmental adaptability deviate from the normal range; personalized intervention measures need to be initiated to reduce the possible risk of developmental abnormality through early monitoring, further diagnosis and targeted treatment plans;

[0109] When the developmental abnormality probability value is less than the developmental abnormality probability threshold, it means that the child's potential developmental abnormality probability is low, indicating that the child's growth and development process is in line with expectations and there is no risk of deviating from the normal development trajectory, and there is no need to initiate personalized intervention measures.

[0110] The setting of the probability threshold of developmental abnormalities is based on large-scale statistical analysis of clinical data and expert consensus, with the aim of scientifically distinguishing normal development from potential abnormal risks. Usually, a large amount of children's growth data is collected and trained to determine the probability distribution at different growth stages and developmental states, and then the key percentiles in the statistical distribution (such as the 90th or 95th percentile) are selected as the threshold. In addition, the threshold will be calibrated and optimized based on actual clinical conditions, genetic research results, and long-term follow-up data.

[0111] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0112] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0113] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0115] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0116] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0118] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0119] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0120] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An integrated growth and development assessment and management system for children, characterized in that: It includes a development stage determination module, a synchronization assessment module, a deviation risk identification module, a growth potential assessment module, and an abnormal probability assessment module; The developmental stage determination module collects children's real-time multimodal physiological parameter data, divides children's growth and development status using a dynamic time series analysis algorithm based on machine learning, and determines children's growth and development stages; The synchronization assessment module performs a dynamic time warping algorithm on the continuously collected children's limb proportion time series data to assess the synchronization of children's bone growth and soft tissue development; The deviation risk identification module uses a decision tree to identify whether a child has a developmental deviation risk based on the child's growth and development stage and the synchronization of the child's bone growth and soft tissue development; For children at risk of developmental deviation, the growth potential assessment module analyzes the children's genetic information and uses a genetic algorithm combined with a dynamic programming model to assess the children's individual growth potential. The abnormality probability assessment module conducts correlation analysis on the synchronization of children's bone growth and soft tissue development and their individual growth potential, assesses the probability of potential developmental abnormalities in children, and determines whether to initiate personalized intervention measures.

2. The integrated growth and development assessment and management system for children according to claim 1, characterized in that: Collect children's real-time multimodal physiological parameter data, use the dynamic time series analysis algorithm based on machine learning to divide the children's growth and development status, and determine the children's growth and development stages, specifically: Collect children's multimodal physiological data in real time; Clean the children's multimodal physiological data series and achieve time series synchronization correction; Build dynamic time series models based on machine learning to extract key features and patterns; Use dynamic time series analysis algorithm to divide growth states and output growth stage division indicators Determine the children's growth and development stages based on growth stage division indicators.

3. The integrated growth and development assessment and management system for children according to claim 2, characterized in that: The dynamic time warping algorithm is used to continuously collect children's limb proportion time series data to evaluate the synchronization of children's bone growth and soft tissue development, specifically: Obtain continuous children's limb proportion time series data, covering bone and soft tissue parameters; Use dynamic time warping algorithm to achieve time series data alignment; Calculate the difference between bone growth rate and soft tissue development rate; To assess the synchronization of children's bone growth and soft tissue development based on difference indicators.

4. The integrated growth and development assessment and management system for children according to claim 3, characterized in that: Based on the growth and development stages of children and the synchronization of bone growth and soft tissue development, a decision tree is used to identify whether children are at risk of developmental deviation, specifically: Obtain the results of the division of children's growth and development stages, and define the data of children's growth and development stages; The data of children's growth and development stages were integrated with the synchronization evaluation index to construct a standardized feature vector; A decision tree model was designed and feature vectors were input for classification training to identify whether children were at risk of developmental deviation.

5. The integrated growth and development assessment and management system for children according to claim 4, characterized in that: By analyzing the genetic information of children, a genetic algorithm combined with a dynamic programming model is used to evaluate the individual growth potential of children. Specifically: Collect genetic information of children at risk of developmental deviations and perform feature extraction; Genetic algorithm is used to initialize multiple candidate solutions of children's individual growth potential; The dynamic programming model is introduced into the algorithm iteration to evaluate the adaptability of the candidate solutions with growth potential; Output the assessment results of children’s individual growth potential.

6. The integrated growth and development assessment and management system for children according to claim 5, characterized in that: The synchronization of children's bone growth and soft tissue development and their individual growth potential are analyzed to assess the probability of children's potential developmental abnormalities and determine whether to initiate personalized intervention measures, specifically: The correlation analysis between synchronization evaluation index and adaptability score was conducted based on the correlation function; Based on the association results, the probability value of potential developmental abnormalities is calculated to determine whether to initiate personalized intervention measures.

7. The integrated growth and development assessment and management system for children according to claim 6, characterized in that: Based on the association results, the probability value of potential developmental abnormalities is calculated to determine whether to initiate personalized intervention measures, specifically: A developmental abnormality probability threshold is preset, and the developmental abnormality probability value is compared with the developmental abnormality probability threshold: When the developmental abnormality probability value is greater than or equal to the developmental abnormality probability threshold, it indicates that the child has a high probability of potential developmental abnormality; When the developmental abnormality probability value is less than the developmental abnormality probability threshold, it indicates that the child's potential developmental abnormality probability is low and there is no need to initiate personalized intervention measures.

Images