Queue follow-up system, method, equipment and medium for early screening of autism

Abstract

The invention relates to the technical field of queue follow-up visit, and discloses a queue follow-up visit system, method, equipment and medium for early screening of autism, and the queue follow-up visit system comprises a timing push unit, a data storage unit and an analysis decision unit; the timing pushing unit is used for regularly pushing follow-up visit questionnaires to follow-up visit users according to the user types, receiving follow-up visit data and sending the follow-up visit data to the data storage unit; the data storage unit is used for performing data processing and data storage on the follow-up visit data, and receiving and storing the screening result from the analysis and decision-making unit; and the analysis decision unit is used for extracting the follow-up data from the data storage unit, analyzing and calculating the follow-up data by adopting a decision model to obtain a screening result of the follow-up user, and sending the screening result to the data storage unit. By simplifying the operation of the queue follow-up visit mode, the data collection rate is improved, the follow-up visit data are analyzed through machine learning, and the screening timeliness and result accuracy of the follow-up visit data are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cohort follow-up, and particularly to a cohort follow-up system, method, device and medium for early screening of autism. Background Art

[0002] Autism spectrum disorder is a group of brain development disorders that occur in infancy. Currently, various internal and external environmental factors during pregnancy and infancy may be factors affecting the outcome of autism. However, there is still a lack of large-scale, multi-center prospective cohort study support for the hypotheses of various possible influencing factors. Identifying risk factors during pregnancy and infancy is of great significance for the early prevention and early screening of autism.

[0003] However, the traditional cohort follow-up mode is cumbersome and complex to operate, requires a large amount of manpower and material resources to establish a cohort, and the willingness of enrolled personnel to participate is weak, the compliance is poor, the dropout rate is relatively high, and the missing rate of the collected data is relatively high. For the research on autism with multiple factors and unknown etiology, it is difficult to implement the traditional cohort follow-up mode. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a cohort follow-up system, method, device and medium for early screening of autism, which simplifies the operation of the cohort follow-up mode and analyzes the follow-up data, so as to achieve the technical effect of improving the timeliness and accuracy of autism screening.

[0005] In a first aspect, the present invention provides a cohort follow-up system for early screening of autism, and the system includes:

[0006] A timing push unit, a data storage unit and an analysis and decision-making unit;

[0007] The timing push unit is configured to regularly push follow-up questionnaires to follow-up users according to user types, receive follow-up data from the follow-up users, and send the follow-up data to the data storage unit;

[0008] The data storage unit is configured to perform data processing on the follow-up data, store the processed follow-up data, and receive screening results from the analysis and decision-making unit and store the screening results.

[0009] The analysis and decision-making unit is configured to extract the follow-up data from the data storage unit, analyze and calculate the follow-up data by using a decision model constructed based on a decision tree algorithm, obtain screening results of the follow-up users, and send the screening results to the data storage unit.

[0010] Furthermore, the timed push unit is also used to push the follow-up questionnaire to the follow-up user on a regular basis, and after a preset time, determine whether the follow-up data corresponding to the follow-up questionnaire is received, if so, mark the follow-up questionnaire as completed in stages, if not, resend the follow-up questionnaire.

[0011] Furthermore, the data storage unit is further used to calculate the standardized distance between the follow-up data and a preset data average value, and determine whether the standardized distance is within a preset range. If so, the follow-up data is stored; otherwise, the follow-up data is discarded;

[0012] The standardized distance is expressed by the following formula:

[0013]

[0014] In the formula, x represents the follow-up data, μ represents the mean value of the data, and σ represents the standard deviation of the data.

[0015] Furthermore, the system also includes a clustering retrieval module;

[0016] The cluster retrieval module is used to extract the follow-up data and the corresponding screening results from the data storage unit, perform cluster analysis on the follow-up data based on the screening results using a cluster analysis algorithm, and store the obtained classification results in the data storage unit to achieve classification retrieval.

[0017] In a second aspect, the present invention provides a cohort follow-up method for early screening of autism, the method comprising:

[0018] According to the user type, regularly push the follow-up questionnaire to the follow-up user, and receive the follow-up data from the follow-up user;

[0019] Processing the follow-up data, and storing the processed follow-up data;

[0020] The stored follow-up data is obtained, and a decision model constructed based on a decision tree algorithm is used to analyze and calculate the follow-up data to obtain a screening result of the follow-up user.

[0021] Furthermore, the step of regularly pushing the follow-up questionnaire to the follow-up user and receiving the follow-up data from the follow-up user includes:

[0022] Follow-up questionnaires are pushed to the follow-up users at regular intervals, and after a preset time, it is determined whether the follow-up data corresponding to the follow-up questionnaire is received. If so, the follow-up questionnaire is marked as completed in stages; if not, the follow-up questionnaire is resent.

[0023] Further, the step of processing the follow-up data includes:

[0024] Calculating the standardized distance between the follow-up data and a preset data average value, and determining whether the standardized distance is within a preset range. If so, storing the follow-up data; otherwise, eliminating the follow-up data;

[0025] Among them, the standardized distance is represented by the following formula:

[0026]

[0027] In the formula, x represents the follow-up data, μ represents the data average value, and σ represents the data standard deviation.

[0028] Further, after the step of obtaining the screening result of the follow-up user, it further includes:

[0029] Based on the screening result, performing cluster analysis on the follow-up data by using a cluster analysis algorithm, and storing the obtained classification result to achieve classification retrieval.

[0030] In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0031] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0032] The present invention provides a cohort follow-up system, method, device, and medium for early screening of autism. By simplifying the operation of the cohort follow-up mode, the present invention overcomes the problem of a relatively high data missing rate in the traditional cohort follow-up mode, improves the data collection rate, analyzes the follow-up data through a machine learning model, improves the accuracy of the screening result of the follow-up data, realizes accurate and efficient autism screening, and at the same time, by performing cluster analysis on the screening result, more precisely finds a model group with similar expressions, so as to help researchers quickly locate the required correlation information from a large amount of clinical data, and provides accurate data support for researchers to better analyze and study the inducing factors of autism. Description of the Drawings

[0033] Figure 1 is a schematic structural diagram of a cohort follow-up system for early screening of autism in an embodiment of the present invention;

[0034] Figure 2It is another structural schematic diagram of the cohort follow-up system for early autism screening in the embodiments of the present invention;

[0035] Figure 3 It is a flowchart of the cohort follow-up method for early autism screening in the embodiments of the present invention;

[0036] Figure 4 It is the internal structure diagram of the computer device in the embodiments of the present invention. Detailed implementation manners

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0038] Please refer to Figure 1 , a cohort follow-up system for early autism screening proposed in the first embodiment of the present invention includes: a timing push unit 10, a data storage unit 20, and an analysis and decision-making unit 30; wherein, the timing push unit is configured to push follow-up questionnaires to follow-up users regularly according to the user type, receive follow-up data from the follow-up users, and send the follow-up data to the data storage unit; the data storage unit is configured to perform data processing on the follow-up data, store the processed follow-up data, receive the screening results from the analysis and decision-making unit, and store the screening results; the analysis and decision-making unit is configured to extract the follow-up data from the data storage unit, analyze the follow-up data by using a decision model constructed based on a decision tree algorithm, obtain the screening results of the follow-up users, and send the screening results to the data storage unit.

[0039] The system provided by the present invention is mainly for early screening of autism. In the current research on autism, it is believed that various internal and external environmental effects during pregnancy and infancy may be factors affecting the outcome of autism. However, the current hypothesis of multiple possible influencing factors still lacks support from large-scale, multi-center prospective cohort studies. For this reason, in this system, pregnant women and children are selected from users who have established files in hospitals and other units as follow-up objects, and different follow-up cycles and follow-up times are set according to different user types. Specifically, according to the user type, the pregnancy and childbirth files of pregnant women and the health files of children are obtained from the database. For pregnancy and childbirth files, the gestational age is calculated by analyzing the pregnancy and childbirth information in the files. For different gestational weeks, the corresponding follow-up questionnaire is sent to the corresponding user. For health files, the age of infants and young children is calculated by calculating the birth date in the files. When the age reaches the preset follow-up age, the corresponding follow-up questionnaire is sent to the corresponding user. And in order to make the follow-up data continuous and more convenient for subsequent data analysis and screening, in a preferred embodiment, the present invention selects children in the infant and young child files bound to the pregnancy and childbirth files as follow-up objects on the basis of the follow-up objects of the pregnant women type selected in the early stage.

[0040] Further, in order to improve the collection rate of follow-up data, the present invention also provides a function of repeatedly sending follow-up questionnaires in the timing push unit 10, that is, to push the follow-up questionnaire to the follow-up user regularly, and after the preset duration, determine whether the follow-up data corresponding to the follow-up questionnaire is received, if so, the follow-up questionnaire is marked as completed in stages, if not, the follow-up questionnaire is resent. In the present embodiment, the feedback result of the follow-up questionnaire sent this time is monitored in real time, and when the follow-up data corresponding to the follow-up questionnaire is still not received after the preset duration, the follow-up questionnaire will be resent to the follow-up user, thereby avoiding the user from forgetting or other reasons causing the lack of follow-up data, thereby improving the data collection rate, and for the follow-up questionnaire that has received the follow-up data, the follow-up of this stage is indicated by marking the staged completion mark. Preferably, the present invention realizes the push of the follow-up questionnaire through a variety of application applets such as WeChat, thereby simplifying the operation of the queue follow-up mode, overcoming the problem of the high data missing rate collected by the traditional queue follow-up mode, and improving the data collection rate.

[0041] The follow-up data fed back by the follow-up users will be stored in the data storage unit 20. Since the follow-up data are released to the public, some invalid samples that do not cooperate with the follow-up survey may be generated, and these samples often have a very adverse impact on the research and analysis results. Therefore, when the follow-up data are included in the data storage unit 20 for sealing, the outliers in the follow-up data also need to be eliminated. By eliminating missing values ​​and outliers and other data, the accuracy and consistency of the follow-up data can be ensured.

[0042] In a preferred embodiment, the present invention screens the follow-up data based on the standardized distance. In this embodiment, the data storage unit 20 preprocesses the follow-up data. The preprocessing steps are to calculate the standardized distance between the follow-up data and the preset data average value, and then determine whether the standardized distance is within the preset range. The follow-up data within the preset range is stored, and the follow-up data outside the preset range is excluded. Among them, the calculation formula of the standardized distance is:

[0043]

[0044] In the formula, x represents the follow-up data, μ represents the data average value, and σ represents the data standard deviation.

[0045] In this embodiment, both the data average value and the data standard deviation are obtained by calculating a preset standard data set. And through statistical analysis of the actual follow-up data, the normal follow-up data is mainly distributed in the range of -3 < Z < 3. Therefore, abnormal data values can be screened out by determining |Z| ≥ 3.

[0046] For the follow-up data stored in the data storage unit 20, the present invention further analyzes these stored follow-up data through the analysis and decision-making unit 30 to obtain the screening results of the follow-up users. In this embodiment, the decision-making model in the analysis and decision-making unit 30 is constructed using the decision tree algorithm. The decision tree is an artificial intelligence machine learning algorithm, which is particularly effective in dealing with classification and regression problems. The theoretical basis of this method is statistics and decision theory, and it can very effectively simulate the human decision-making process. Therefore, in this system, the decision tree is used to recursively process the cleaned follow-up data step by step, and the result data is divided into multiple tree-like structure subsets, so that each internal node can represent the characteristic result of a follow-up data.

[0047] In the decision-making model of this embodiment, a consistency index is used to measure the feature consistency of the data. The consistency index can be expressed as:

[0048]

[0049] Among them, p i represents the probability of category i, and G(D) is the key index of the feature consistency of the data set. The smaller the value of G(D), the higher the feature consistency of the follow-up data.

[0050] The steps of analyzing and making decisions on the follow-up data of the follow-up users through the decision model are as follows: input the follow-up data into the decision tree model for traversal, and gradually select the optimal features to divide the data, thereby generating different subsets until a certain stop condition is met, thereby obtaining the prediction result. Specifically, when dividing the data, the data is divided by selecting the features with the highest consistency. The smaller G(D) is, the more effectively the feature can reduce uncertainty, thereby better dividing the data. After selecting a feature, the decision tree will divide the data set into different subsets according to the different values ​​of the feature. For each subset, the optimal feature is recursively selected to divide the data. After each division, the decision tree will recursively continue the same process for the subset until certain stop conditions are met, and the samples of the current node belong to the same category. At this point, no further division is required; when the attribute set is empty, or the sample has the same value on all attributes, the division cannot continue, and this node is set as a leaf node, and the category is the category with the most samples in the current subset; when the sample set is empty, the category with the most samples in the parent node is used as the prediction value. It should be noted that the specific decision-making steps for analyzing and making decisions on the follow-up data in this embodiment can refer to the tree building decision steps of the decision tree algorithm, and no further explanation or limitation is given here.

[0051] In a preferred embodiment, the follow-up system provided by the present invention further provides a cluster retrieval module 40, see Figure 2 The clustering retrieval module 40 is used to extract the follow-up data and the corresponding screening results from the data storage unit 20, and based on the screening results, a clustering analysis algorithm is used to perform clustering analysis on the follow-up data, and the obtained classification results are stored in the data storage unit 20 to achieve classification retrieval. In other words, through the clustering retrieval module 40, an advanced retrieval function can be achieved.

[0052] In this embodiment, the K-means clustering method is preferably used to further classify the stored follow-up data. When the early screening classification of autism has been basically determined, the clustering analysis algorithm is used to quickly classify the cases into the corresponding classification, which is particularly suitable for clustering large sample data. The specific implementation steps include:

[0053] (1) Initialization: Select K initial cluster centers

[0054] At the beginning of the algorithm, K data points need to be randomly selected as the initial cluster centers. The selection of these initial cluster centers has a certain influence on the final clustering results. In this embodiment, since the follow-up data with screening results are clustered, the initial cluster centers are selected based on the screening results, thereby improving the efficiency and effect of clustering.

[0055] (2) Assignment: Assign each data point to the nearest cluster center

[0056] For each data point in the dataset, calculate its distance from each cluster center and assign it to the nearest cluster center. This step typically uses the Euclidean distance as the distance metric, and the calculation formula is as follows:

[0057]

[0058] where x is the data point, c i is the i-th cluster center, d is the dimension of the data, x j and c ij are the values of x and c i on the j-th dimension respectively.

[0059] (3) Update: Recalculate the center of each cluster

[0060] For each cluster, recalculate its cluster center. The new cluster center is the mean of all data points within the cluster, and the calculation formula is as follows:

[0061]

[0062] where S i is the set of data points in the i-th cluster, and |S i | is the number of data points in this set.

[0063] (4) Iteration: Repeat the assignment and update steps until the termination condition is met

[0064] Repeat the assignment and update steps until a certain termination condition is met. Common termination conditions include: The cluster centers no longer change significantly: that is, the distance between the new cluster center and the old cluster center is less than a preset threshold. Reaching the maximum number of iterations: To avoid the algorithm falling into an infinite loop, a maximum number of iterations is usually set as the termination condition. During the iteration process, the algorithm continuously optimizes the clustering result, making the objects within each cluster more compact and the objects between different clusters more dispersed. Finally, when the termination condition is met, the algorithm stops iterating and outputs the final clustering result. It should be noted that in this embodiment, the specific clustering analysis steps for the follow-up data can refer to the conventional steps of the K-means clustering algorithm, which will not be elaborated here one by one.

[0065] In this embodiment, after obtaining a large amount of follow-up data through the cohort follow-up system, a clustering analysis method is applied to analyze the data expression of different early autism regular phenomena, so as to more accurately find the model groups with similar expressions, facilitating researchers to more accurately locate the clinical problems of early autism screening, helping researchers quickly locate the required correlation information from a large amount of clinical data, and providing accurate data support for researchers to better analyze and study the inducing factors of autism.

[0066] A cohort follow-up system for early autism screening provided in this embodiment. The present invention simplifies the operation of the cohort follow-up mode, overcomes the problem of high data missing rate in the traditional cohort follow-up mode, improves the data collection rate, analyzes the follow-up data through a machine learning model, improves the accuracy of the screening results of the follow-up data, realizes accurate and efficient autism screening, and at the same time, through clustering analysis of the screening results, more accurately finds the model groups with similar expressions, so as to help researchers quickly locate the required correlation information from a large amount of clinical data and provide accurate data support for researchers to better analyze and study the inducing factors of autism.

[0067] Please refer to Figure 3 , based on the same inventive concept, a cohort follow-up method for early autism screening proposed in the second embodiment of the present invention includes:

[0068] Timely push follow-up questionnaires to follow-up users according to the user type, and receive follow-up data from the follow-up users;

[0069] Perform data processing on the follow-up data, and store the processed follow-up data;

[0070] Obtain the stored follow-up data, and analyze and calculate the follow-up data by using a decision model constructed based on the decision tree algorithm to obtain the screening results of the follow-up users.

[0071] Further, the step of timely pushing follow-up questionnaires to follow-up users and receiving follow-up data from the follow-up users includes:

[0072] Timely push follow-up questionnaires to follow-up users, and after a preset duration, determine whether the follow-up data corresponding to the follow-up questionnaire is received. If so, mark the follow-up questionnaire as stage-completed. If not, resend the follow-up questionnaire.

[0073] Further, the step of performing data processing on the follow-up data includes:

[0074] Calculating the standardized distance between the follow-up data and a preset data average value, and determining whether the standardized distance is within a preset range, if so, storing the follow-up data, otherwise, discarding the follow-up data;

[0075] The standardized distance is expressed by the following formula:

[0076]

[0077] In the formula, x represents the follow-up data, μ represents the mean value of the data, and σ represents the standard deviation of the data.

[0078] Furthermore, after the step of obtaining the screening result of the follow-up user, the method further includes:

[0079] Based on the screening results, a cluster analysis algorithm is used to perform cluster analysis on the follow-up data, and the obtained classification results are stored to achieve classification retrieval.

[0080] The technical features and technical effects of the cohort follow-up method for early screening of autism proposed in the embodiment of the present invention are the same as those of the system proposed in the embodiment of the present invention, and are not described in detail here. Each module in the above-mentioned cohort follow-up system for early screening of autism can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0081] In addition, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0082] See also Figure 4, the internal structure diagram of a computer device in an embodiment. The computer device can specifically be a terminal or a server. The computer device includes a processor, a memory, a network interface, a display, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a cohort follow-up method for early screening of autism. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0083] Those of ordinary skill in the art can understand that Figure 4 the structure shown in

[0084] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computing device may include more or fewer components than those shown in the figure, or combine some components, or have the same component arrangement.

[0085] In summary, a cohort follow-up system, method, device, and medium for early screening of autism proposed in the embodiments of the present invention. The system includes a timing push unit, a data storage unit, and an analysis and decision-making unit. The timing push unit is configured to push follow-up questionnaires to follow-up users at regular intervals according to the user type, receive follow-up data from the follow-up users, and send the follow-up data to the data storage unit. The data storage unit is configured to perform data processing on the follow-up data, store the processed follow-up data, receive screening results from the analysis and decision-making unit, and store the screening results. The analysis and decision-making unit is configured to extract the follow-up data from the data storage unit, analyze and calculate the follow-up data using a decision model constructed based on the decision tree algorithm, obtain the screening results of the follow-up users, and send the screening results to the data storage unit. The present invention simplifies the operation of the cohort follow-up mode, overcomes the problem of a relatively high data missing rate in the traditional cohort follow-up mode, improves the data collection rate, analyzes the follow-up data through a machine learning model, improves the accuracy of the screening results of the follow-up data, realizes accurate and efficient autism screening, and at the same time performs cluster analysis on the screening results to more accurately find model groups with similar expressions, thereby helping researchers quickly locate the required correlation information from a large amount of clinical data and providing accurate data support for researchers to better analyze and study the inducing factors of autism.

[0086] Each embodiment in this specification is described in a progressive manner. For parts that are the same or similar in each embodiment, they can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. It should be noted that the above technical features of the embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the above technical features in the embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0087] The above embodiments only represent several preferred implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the technical principle of the present invention, several improvements and substitutions can still be made, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the protection scope of the claims.

Claims

1. A cohort follow-up system for early screening of autism, characterized in that, include: Timing push unit, data storage unit and analysis and decision-making unit; The timing push unit is used to regularly push the follow-up questionnaire to the follow-up user according to the user type, receive the follow-up data from the follow-up user, and send the follow-up data to the data storage unit; The data storage unit is used to process the follow-up data and store the processed follow-up data, and receive the screening result from the analysis and decision-making unit and store the screening result; The analysis and decision unit is used to extract the follow-up data from the data storage unit, and use a decision model constructed based on a decision tree algorithm to analyze and calculate the follow-up data to obtain the screening results of the follow-up users, and send the screening results to the data storage unit.

2. The cohort follow-up system for early screening of autism according to claim 1, wherein, The timing push unit is also used to regularly push the follow-up questionnaire to the follow-up user, and after a preset time period, determine whether the follow-up data corresponding to the follow-up questionnaire is received, if so, mark the follow-up questionnaire as completed in stages, if not, resend the follow-up questionnaire.

3. The cohort follow-up system for early screening of autism according to claim 1, wherein, The data storage unit is further used to calculate the standardized distance between the follow-up data and a preset data average value, and determine whether the standardized distance is within a preset range. If so, the follow-up data is stored; otherwise, the follow-up data is discarded; The standardized distance is expressed by the following formula: In the formula, x represents the follow-up data, μ represents the mean value of the data, and σ represents the standard deviation of the data.

4. The cohort follow-up system for early screening of autism according to claim 1, characterized in that, The system also includes a clustering retrieval module; The cluster retrieval module is used to extract the follow-up data and the corresponding screening results from the data storage unit, perform cluster analysis on the follow-up data based on the screening results using a cluster analysis algorithm, and store the obtained classification results in the data storage unit to achieve classification retrieval.

5. A cohort follow-up method for early screening of autism, characterized in that, The method is applied to the system according to any one of claims 1 to 4, comprising: According to the user type, regularly push the follow-up questionnaire to the follow-up user, and receive the follow-up data from the follow-up user; Processing the follow-up data, and storing the processed follow-up data; The stored follow-up data is obtained, and a decision model constructed based on a decision tree algorithm is used to analyze and calculate the follow-up data to obtain a screening result of the follow-up user.

6. The cohort follow-up method for early screening of autism according to claim 5, wherein The step of regularly pushing the follow-up questionnaire to the follow-up user and receiving the follow-up data from the follow-up user comprises: Follow-up questionnaires are pushed to the follow-up users at regular intervals, and after a preset time, it is determined whether the follow-up data corresponding to the follow-up questionnaire is received. If so, the follow-up questionnaire is marked as completed in stages; if not, the follow-up questionnaire is resent.

7. The cohort follow-up method for early screening of autism according to claim 5, wherein The step of processing the follow-up data comprises: Calculating the standardized distance between the follow-up data and a preset data average value, and determining whether the standardized distance is within a preset range, if so, storing the follow-up data, otherwise, discarding the follow-up data; The standardized distance is expressed by the following formula: Wherein, x represents the follow-up data, μ represents the data average value, and σ represents the data standard deviation.

8. The cohort follow-up method for early screening of autism according to claim 5, characterized in that, After the step of obtaining the screening result of the follow-up user, it further includes: Based on the screening result, the clustering analysis algorithm is used to perform clustering analysis on the follow-up data, and the obtained classification result is stored to achieve classified retrieval.

9. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 5 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 5 to 8 are implemented.

Images