CN117038079A - Child heart disease risk assessment and early warning system based on neural network - Google Patents
Child heart disease risk assessment and early warning system based on neural network Download PDFInfo
- Publication number
- CN117038079A CN117038079A CN202311031097.8A CN202311031097A CN117038079A CN 117038079 A CN117038079 A CN 117038079A CN 202311031097 A CN202311031097 A CN 202311031097A CN 117038079 A CN117038079 A CN 117038079A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- assessment
- model
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 53
- 208000019622 heart disease Diseases 0.000 title claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000012795 verification Methods 0.000 claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 26
- 230000036541 health Effects 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 20
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000013524 data verification Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 230000008676 import Effects 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000003862 health status Effects 0.000 claims description 2
- 230000000747 cardiac effect Effects 0.000 claims 1
- 230000006870 function Effects 0.000 abstract description 4
- 230000003449 preventive effect Effects 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 28
- 238000013210 evaluation model Methods 0.000 description 16
- 230000000694 effects Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000005189 cardiac health Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Biophysics (AREA)
Abstract
The application discloses a child heart disease risk assessment and early warning system based on a neural network, and particularly relates to the technical field of medical assessment. According to the risk assessment method, the accuracy and the credibility of the risk assessment are improved by training the selected machine learning model. The system can learn and establish accurate association relation from a large amount of data, and meanwhile, the correctness of the case data is ensured through verification and check functions. The comprehensive technical scheme enables the system to provide more accurate and reliable risk assessment results and helps doctors and patients to make better decisions and preventive measures.
Description
Technical Field
The application relates to the technical field of medical evaluation, in particular to a children heart disease risk evaluation and early warning system based on a neural network.
Background
The risk assessment and early warning of the heart disease of the children by using the neural network is to evaluate the risk of the heart disease of the children patients by using a neural network model and provide corresponding early warning. At present, some assessment scales and early warning models are designed according to potential risk factors and disease characteristics of heart diseases of children, heart disease risks of the children are assessed by filling out questionnaires or inputting related information, but the filling out of the questionnaires or the providing of the related information often depends on subjective willingness and memory of parents or patients, and problems such as inaccurate memory, information omission or subjective bias can exist. This may lead to inaccuracy of the evaluation result, so that the practical applicability of this evaluation method in the actual use process is not high, and therefore we provide a neural network-based risk evaluation and early warning system for heart disease of children.
Disclosure of Invention
The application provides a child heart disease risk assessment and early warning system based on a neural network for solving the defects existing in the prior art.
In order to achieve the above purpose, the present application adopts the following technical scheme:
the system for assessing and early warning heart disease risk of children based on the neural network comprises an acquisition and preprocessing module, a data analysis module and a data analysis module, wherein the acquisition and preprocessing module is configured to collect health data of children, the acquisition and preprocessing module comprises a data collection module configured to collect health data of children from different data sources, a data cleaning module configured to clean the acquired data to remove abnormal values, missing values and error values, and a data preprocessing module configured to perform data conversion, normalization and feature coding operations on the cleaned data;
the device comprises a feature extraction selection module, a feature conversion module and a feature extraction module, wherein the feature extraction selection module is configured to perform feature extraction and selection on preprocessed data by using a neural network method, and comprises a feature extraction module configured to extract meaningful and related features from original data, a feature selection module configured to select the extracted features to select feature data with larger influence on a target task, and a feature conversion module configured to convert the selected features into a form suitable for a machine learning algorithm;
a risk assessment module configured to assess heart disease risk of a child using a trained neural network model, the risk assessment module comprising a risk identification module configured to identify health status of the child based on existing characteristic data and predefined risk indicators, an assessment model module configured to conduct an assessment test by bringing child profile data into the assessment model, and a visualization reporting module configured to generate a risk assessment report and a visualization result from the assessment model;
the early warning suggestion module is configured to give corresponding early warning and suggestion based on a risk assessment result, and comprises an early warning triggering module configured to monitor output of the assessment model and judge whether to trigger early warning according to a set threshold or rule, an early warning processing module configured to generate corresponding early warning information and processing suggestion for data triggering early warning, and a feedback updating module configured to collect and record information fed back by the early warning processing module and update and improve the early warning processing module according to actual conditions.
The application is further provided with: the assessment model module includes a model selection module configured to select an appropriate assessment model to perform risk assessment on data, a model training module configured to train the selected model to improve assessment accuracy, a data import module configured to import data related to child health into the risk assessment system, a model verification module configured to verify the results of the trained model assessment, an output determination module configured to determine risk of the child based on the model output results, a data verification module configured to receive unrecognizable data and verify with illness data, a data verification module configured to receive verification success data and verify with patient data, a case database module configured to store verification failure case data, and a data populating module configured to correlate the assessment results with patient data and generate a final risk assessment report.
By adopting the technical scheme: the system can select a proper evaluation model according to the data characteristics through the model selection module so as to improve the accuracy of evaluation. Meanwhile, the model training module trains by utilizing a large amount of data, and continuously optimizes the model, so that the accuracy and reliability of evaluation are improved.
The application is further provided with: the data collection module collects and records the related health data of children from different data sources and transmits the data to the data cleaning module to carry out cleaning operation on the collected data, the data preprocessing module carries out further processing and conversion storage on the data subjected to the cleaning operation, the feature extraction module extracts useful features from the data subjected to preprocessing, and the feature selection module selects the most relevant or representative feature subset from the extracted feature set.
By adopting the technical scheme: the data collection module of the system can acquire the health data related to the child from different data sources, and record and transmit the health data to the data cleaning module. The data cleaning module can clean the collected data, remove noise, fill missing values and the like, and ensure the accuracy and the integrity of the data.
The application is further provided with: the feature conversion module converts and maps the original data features extracted by the feature extraction module, the risk identification module carries out risk identification and classification on the input data with the extracted features according to preset rules and algorithms, the assessment model module substitutes the data with the risk identification into the risk assessment module for risk assessment, and the assessment result is transmitted to the visual report module to generate a corresponding visual report.
By adopting the technical scheme: the feature conversion module of the system is capable of converting and mapping the raw data features obtained from the feature extraction module. This allows the raw data to be mapped to a more representative or more understandable feature space, improving the understanding and generalization of the model to the data.
The application is further provided with: the early warning triggering module is used for judging whether to trigger early warning by receiving the risk data transmitted by the risk assessment module for threshold comparison, the early warning processing module is used for processing the received early warning signal or notification and taking corresponding measures to cope with an early warning event, and the feedback updating module is used for receiving feedback information from the early warning processing module to update and optimize rules, algorithms or configuration of the early warning processing module.
By adopting the technical scheme: and an early warning triggering module of the system receives the risk data transmitted by the risk assessment module and judges whether to trigger early warning or not through threshold comparison. Therefore, the possible heart disease risk can be found and identified in time according to the set early warning rules and standards.
The application is further provided with: the model selection module selects an evaluation model according to the case type of which the risk evaluation is completed, the model training module trains the evaluation model selected by the model selection module so that the evaluation model can learn from training data and show expected prediction capability, the data importing module carries out risk evaluation by importing data for identifying risks into the evaluation model of which the risk is completed, and the model verification module carries out correctness verification on the risk data evaluated by the evaluation model.
By adopting the technical scheme: the model training module of the system is responsible for training the selected machine learning model so that it can learn from the training data and exhibit the desired predictive power. Through a large amount of heart disease data and related characteristics of children, an accurate association relationship can be established by training a model, so that the accuracy and the credibility of risk assessment are improved.
The application is further provided with: the model verification module transmits the verified data to the output judging module to compare the data of the case data with the data of the case, the output judging module transmits the case data which cannot be judged to the data checking module to check the illness state data of the patient, the data checking module transmits the case data which is checked by the illness state data to the data checking module to compare the personal data of the patient, and the data filling module automatically fills the correct case data which is judged to be finished in the output judging module and the data checking module with the filling data of the case data table.
By adopting the technical scheme: the data checking module receives the case data which is checked by the illness state data and transmits the case data to the data checking module for comparing personal data and data of the patient. By checking the personal data and the illness state data of the patient, the accuracy and the credibility of the evaluation result can be further ensured.
The application is further provided with: the data checking module stores the error case by transmitting the error-identified case data and the patient condition data to the case database module, and the data checking module transmits the error-identified patient data and the error-identified case data to the case database module for error case storage.
By adopting the technical scheme: the data checking module performs error case storage by transmitting the patient data and the case data which identify errors to the case database module. The function can help the system to timely detect and record errors or inconsistencies of personal data and case data of patients, and is beneficial to improving the requirements and monitoring of the system on the accuracy of the personal data of the patients.
The beneficial effects of the application are as follows: according to the risk assessment method, the accuracy and the credibility of the risk assessment are improved by training the selected machine learning model. The system can learn and establish accurate association relation from a large amount of data, and meanwhile, the correctness of the case data is ensured through verification and check functions. The comprehensive technical scheme enables the system to provide more accurate and reliable risk assessment results, helps doctors and patients to make better decisions and preventive measures, and improves the practicability of the system in the actual use process.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a system according to the present application.
FIG. 2 is a schematic diagram of a portion of a system flow of an evaluation model module according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Example 1
As shown in fig. 1, the system for assessing and early warning of heart disease of children based on the neural network comprises an acquisition and preprocessing module configured to collect relevant health data of children, a feature extraction selection module configured to perform feature extraction and selection on the preprocessed data by using a neural network method, a risk assessment module configured to assess heart disease risk of children by using a trained neural network model, and an early warning suggestion module configured to give corresponding early warning and suggestion based on a risk assessment result;
the collecting and preprocessing module comprises a data collecting module configured to collect children related health data from different data sources, a data cleaning module configured to clean the collected data to remove abnormal values, missing values and error values, a data preprocessing module configured to perform data conversion, normalization and feature coding operations on the cleaned data, and a feature extraction selection module comprising a feature extraction module configured to extract meaningful and relevant features from the original data, a feature selection module configured to select the extracted features to select feature data with larger influence on a target task, and a feature conversion module configured to convert the selected features into a form suitable for use by a machine learning algorithm;
the risk assessment module comprises a risk identification module configured to identify the health condition of the child according to the existing characteristic data and the predefined risk index, an assessment model module configured to carry out assessment test by bringing child data into an assessment model, and a visual report module configured to generate a risk assessment report and a visual result according to the assessment model, wherein the early warning suggestion module comprises an early warning trigger module configured to monitor the output of the risk assessment model and judge whether to trigger early warning according to a set threshold or rule, an early warning processing module configured to generate corresponding early warning information and processing suggestion for the data triggering early warning, and a feedback update module configured to collect and record feedback information of early warning and update and improve the pre-processing alarm module according to actual conditions;
the data collection module is used for collecting the related health data of children from different data sources, recording the data and transmitting the data to the data cleaning module to clean the collected data, the data preprocessing module is used for further processing, converting and storing the data of the data cleaning module, the feature extraction module is used for extracting useful features from the data preprocessing module for the data which is preprocessed, and the feature selection module is used for selecting the most related or representative feature subset from the feature extraction module for the extracted feature set;
the feature conversion module is responsible for converting and mapping the original data features extracted by the feature extraction module, the risk identification module is responsible for carrying out risk identification and classification on the input data with extracted features according to the existing knowledge, rules and algorithms, and the evaluation module carries out risk evaluation by substituting the data with the identified risk identification module into the risk evaluation module and transmits the evaluation result to the visual report module to generate a corresponding report;
the early warning triggering module is used for judging whether to trigger early warning by receiving the risk data transmitted by the risk assessment module, the early warning processing module is responsible for processing the received early warning signal or notification and taking corresponding measures to cope with the early warning event, and the feedback updating module is responsible for receiving the feedback information from the early warning processing module to update and optimize the rule, algorithm or configuration of the early warning processing module.
In the above embodiments, the system converts data into a form suitable for use by a machine learning algorithm by collecting child-related health data and performing data cleansing and preprocessing. Next, the system extracts meaningful and relevant features from the preprocessed data and selects a subset of features that have a greater impact on the target task by feature selection. On the basis, the system identifies and classifies the health condition of the children according to the existing characteristic data and the predefined risk indexes, evaluates the heart disease risk of the children through an evaluation model, generates a risk evaluation report and a visual result, and provides comprehensive evaluation of the heart disease risk of the children. Meanwhile, the system can also monitor the output of the risk assessment model in real time, trigger the early warning trigger module and finally generate corresponding early warning information and processing advice, thereby helping to take targeted measures in time. The feedback updating module is responsible for collecting and recording feedback information of the early warning, and updating and improving the early warning module according to actual conditions so as to continuously improve system performance. In conclusion, the system plays an important role in the aspects of heart disease risk assessment and early warning of children, provides scientific basis and decision support for health management, and ensures the healthy growth of children.
Through cooperation of the feature extraction and selection module and the risk identification module, the original data can be subjected to feature extraction and selection to obtain a feature representation with more representative and discrimination capability, and then the risk identification module classifies or identifies the data according to the existing risk identification. Therefore, the risk assessment and prediction can be realized, and the effect and accuracy of risk management are improved.
Through cooperation of the feature extraction module and the feature selection module, the original data can be subjected to feature extraction to obtain feature representation with more representative and discrimination capability, and then the feature selection module further screens out an optimal feature subset so as to improve the performance and effect of the machine learning model. The process of feature selection helps reduce redundant features and reduce data dimensionality while improving the interpretability and generalization ability of the model.
Example 2
As shown in fig. 1-2, the evaluation model module includes a model selection module configured to select an appropriate evaluation model to perform risk evaluation on data, a model training module configured to train the selected model to improve evaluation accuracy, a data importing module configured to import data related to child health into the risk evaluation system, a model verification module configured to verify the result of the trained model evaluation, an output decision module configured to decide risk of the child according to the model output result, a data check module configured to receive unrecognizable data and check with illness data, a data check module configured to transmit check-successful data to the data check module and check with patient data, a case database module configured to store check failure case data, and a data filling module configured to correlate the evaluation result with patient data and generate a final risk evaluation report;
the model selection module selects an evaluation model according to the case type of which the risk evaluation is completed, the model training module trains the evaluation model selected by the model selection module so that the evaluation model can learn from training data and show expected prediction capability, the data importing module carries out risk evaluation by importing data for identifying risks into the evaluation model of which the risk is completed, and the model verification module carries out correctness verification on the risk data evaluated by the evaluation model;
the model verification module is used for carrying out data comparison on case data and case data by transmitting the verified data to the output judging module, the output judging module is used for transmitting the case data which cannot be judged to the data checking module to check the patient condition data, the data checking module is used for carrying out personal data comparison on the patient by transmitting the case data which is checked by the condition data to the data checking module, and the data filling module is used for carrying out automatic filling on correct case data which is judged to be finished and case data table filling data by receiving the output judging module and the data checking module;
the data checking module performs error case storage by transmitting the error-identified case data and the patient condition data to the case database module, and the data checking module performs error case storage by transmitting the error-identified patient data and the case data to the case database module.
In the above embodiment, first, the model selection module classifies the data according to the risk identification module, and selects an appropriate evaluation model. The model training module then trains the selected assessment model so that it can learn from the data and has predictive capabilities. Next, the data import module imports data identifying risk into the trained assessment model for assessment. The model verification module is responsible for verifying the correctness of the evaluation result. The output judging module transmits the data which cannot be judged to the data checking module to compare with the case data. The data checking module transmits the verified illness state data to the data checking module to be compared with the personal data of the patient. The data filling module automatically fills correct data in the output judging module and the data checking module into the case data table. Meanwhile, the misidentified case data and patient profile data are stored in a case database module. Finally, the system correlates the assessment results with the patient profile and generates a final risk assessment report. Through the integration of the modules, the system can accurately evaluate the heart disease risk of the children and provide effective early warning.
The machine learning system can select and train a model with good performance through cooperation of the model selection module and the model training module so as to meet the requirements of specific tasks. The model selection module is responsible for evaluating and selecting candidate models, and the model training module is responsible for training and optimizing the selected models. They cooperate to promote the performance improvement of the machine learning system.
The machine learning system can complete preparation of data and evaluation of model performance through cooperation of the data importing module and the model verifying module. The data importing module is responsible for importing external data into the system, preprocessing and cleaning the data importing module, and providing available data for model verification. The model verification module uses the data to evaluate the performance of the model and provides the results of the evaluation index. Such cooperative relationships help the machine learning system ensure the quality of the data and accuracy of the model.
Working principle: when the application is used, the children heart disease risk assessment and early warning system based on the neural network extracts meaningful characteristics by collecting, cleaning and preprocessing children health data, and accurately assesses the children heart disease risk by using an assessment model. The system can generate a comprehensive assessment report to help medical professionals and parents to know the health condition of children.
In addition, the system has a real-time monitoring function, and can continuously observe the evaluation result and trigger early warning in time. Once a potential risk of heart disease occurs, the system will issue pre-warning information and provide corresponding treatment advice. These pre-warning information and advice may help doctors, parents, or other guardians take necessary measures in time to protect the heart health of the child.
In order to continuously improve the precision and effect of the early warning module, the system also collects early warning feedback information, and updates and optimizes the early warning processing module according to actual conditions. This helps to improve the ability of the system to identify and predict the risk of heart disease in children, thereby better protecting the child from healthy driving.
In summary, the neural network-based children heart disease risk assessment and early warning system provides a comprehensive and reliable tool for medical staff and parents by comprehensively utilizing technical means such as data processing, feature extraction, assessment model and real-time monitoring, and can help the medical staff and parents to timely identify and manage the children heart disease risk so as to promote the healthy growth of children.
In summary, although the present application has been described in terms of the preferred embodiments, the preferred embodiments are not limited to the above embodiments, and various modifications and changes can be made by one skilled in the art without departing from the spirit and scope of the application, and the scope of the application is defined by the appended claims.
Claims (8)
1. Child heart disease risk assessment and early warning system based on neural network, characterized by comprising:
the system comprises an acquisition and preprocessing module, a data acquisition module and a characteristic coding module, wherein the acquisition and preprocessing module is configured to collect health data of children, the acquisition and preprocessing module comprises a data acquisition module configured to collect health data of children from different data sources, a data cleaning module configured to clean the acquired data to remove abnormal values, missing values and error values, and a data preprocessing module configured to perform data conversion, normalization and characteristic coding operations on the cleaned data;
the device comprises a feature extraction selection module, a feature conversion module and a feature extraction module, wherein the feature extraction selection module is configured to perform feature extraction and selection on preprocessed data by using a neural network method, and comprises a feature extraction module configured to extract meaningful and related features from original data, a feature selection module configured to select the extracted features to select feature data with larger influence on a target task, and a feature conversion module configured to convert the selected features into a form suitable for a machine learning algorithm;
a risk assessment module configured to assess heart disease risk of a child using a trained neural network model, the risk assessment module comprising a risk identification module configured to identify health status of the child based on existing characteristic data and predefined risk indicators, an assessment model module configured to conduct an assessment test by bringing child profile data into the assessment model, and a visualization reporting module configured to generate a risk assessment report and a visualization result from the assessment model;
the early warning suggestion module is configured to give corresponding early warning and suggestion based on a risk assessment result, and comprises an early warning triggering module configured to monitor output of the assessment model and judge whether to trigger early warning according to a set threshold or rule, an early warning processing module configured to generate corresponding early warning information and processing suggestion for data triggering early warning, and a feedback updating module configured to collect and record information fed back by the early warning processing module and update and improve the early warning processing module according to actual conditions.
2. The neural network-based cardiac risk assessment and early warning system of children, according to claim 1, characterized in that the assessment model module comprises a model selection module configured to select an appropriate assessment model for risk assessment of data, a model training module configured to train the selected model to improve assessment accuracy, a data importing module configured to import data related to the health of children into the risk assessment system, a model verification module configured to verify the results of the trained model assessment, an output decision module configured to decide the risk of children based on the model output results, a data check module configured to receive unidentifiable data and check with illness data, a case database module configured to receive data that has been checked successfully and check with patient data, and a data populating module configured to correlate the assessment results with patient data and generate a final risk assessment report.
3. The system of claim 1, wherein the data collection module records data of related health of children by collecting data from different data sources and transmits the data to the data cleansing module to cleansing the collected data, the data preprocessing module further processes and stores the cleansing data, the feature extraction module extracts useful features from the preprocessed data, and the feature selection module selects the most relevant or representative feature subset from the extracted feature set.
4. The neural network-based child heart disease risk assessment and early warning system according to claim 1, wherein the feature conversion module converts and maps the original data features extracted by the feature extraction module, the risk identification module performs risk identification and classification on the input data with the extracted features according to preset rules and algorithms, and the assessment model module substitutes the data with the risk identification into the risk assessment module for risk assessment and transmits the assessment result to the visual report module to generate a corresponding visual report.
5. The system for assessing and warning heart disease risk of children based on neural network according to claim 1, wherein the warning trigger module performs threshold comparison by receiving risk data transmitted from the risk assessment module to determine whether to trigger warning, the warning processing module processes the received warning signal or notification and takes corresponding measures to cope with a warning event, and the feedback update module receives feedback information from the warning processing module to update and optimize rules, algorithms or configurations of the warning processing module.
6. The neural network-based system for risk assessment and early warning of heart disease in children according to claim 2, wherein the model selection module selects an assessment model according to the case type for which risk assessment is completed, the model training module trains the assessment model selected by the model selection module so that the assessment model can learn from training data and exhibit a desired prediction capability, the data importing module performs risk assessment by importing risk-identifying data into the assessment model for which risk assessment is completed, and the model verifying module performs correctness verification on the risk data assessed by the assessment model.
7. The system of claim 6, wherein the model verification module transmits the verified data to the output determination module to perform data comparison on the case data and the case data, the output determination module transmits the case data which cannot be determined to the data verification module to verify the patient condition data, the data verification module transmits the case data which is verified by the condition data to the data verification module to perform data comparison on the personal data of the patient, and the data filling module automatically fills the correct case data which is determined to be completed in the output determination module and the data verification module with the filling data of the case data table.
8. The neural network-based pediatric heart disease risk assessment and early warning system of claim 7, wherein the data verification module performs the error case storage by transmitting the error-identified case data and the patient condition data to the case database module, and the data verification module transmits the error-identified patient data and the case data to the case database module for the error case storage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311031097.8A CN117038079A (en) | 2023-08-16 | 2023-08-16 | Child heart disease risk assessment and early warning system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311031097.8A CN117038079A (en) | 2023-08-16 | 2023-08-16 | Child heart disease risk assessment and early warning system based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117038079A true CN117038079A (en) | 2023-11-10 |
Family
ID=88644547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311031097.8A Withdrawn CN117038079A (en) | 2023-08-16 | 2023-08-16 | Child heart disease risk assessment and early warning system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117038079A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117457169A (en) * | 2023-12-15 | 2024-01-26 | 深圳市尼罗河移动互联科技有限公司 | Pediatric postoperative health care management method and system |
-
2023
- 2023-08-16 CN CN202311031097.8A patent/CN117038079A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117457169A (en) * | 2023-12-15 | 2024-01-26 | 深圳市尼罗河移动互联科技有限公司 | Pediatric postoperative health care management method and system |
| CN117457169B (en) * | 2023-12-15 | 2024-03-05 | 深圳市尼罗河移动互联科技有限公司 | Pediatric postoperative health care management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102985211B (en) | For checking the method for the quality of pad | |
| CN112070239B (en) | Analysis method, system, medium, and device based on user data modeling | |
| CN117038079A (en) | Child heart disease risk assessment and early warning system based on neural network | |
| CN116344050B (en) | Evaluation method based on multidimensional health management model | |
| CN115714022B (en) | Neonatal jaundice health management system based on artificial intelligence | |
| CN118116525B (en) | Medicine clinical trial data processing system based on distributed units | |
| CN118014341A (en) | Chemical industry garden safety risk assessment system and device | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN112256754A (en) | Ultrasonic detection analysis system and method based on standard model | |
| CN117292836A (en) | Body measurement score monitoring method and system | |
| CN117129698B (en) | Abnormality alarm and retest system and method for full-automatic coagulation tester | |
| CN114864086A (en) | Disease prediction method based on lung function report template | |
| CN117076915B (en) | Intelligent fault attribution analysis method and system for FPSO crude oil process system | |
| CN117038091A (en) | Rapid diagnosis system and method for diabetic nephropathy through predictive model | |
| CN110455370B (en) | Flood-prevention drought-resisting remote measuring display system | |
| CN116738352A (en) | Method and device for classifying abnormal rod cells of retinal vascular occlusion disease | |
| CN101458738A (en) | Disease serious degree ordering method, system thereof and recording medium | |
| CN118553425B (en) | Construction method and system for medical health dynamic prediction model | |
| CN117633451B (en) | Intelligent cabin health data analysis method based on data mining and deep learning | |
| CN117084683B (en) | Method and system for monitoring and evaluating psychological states of technicians | |
| CN114724720B (en) | Prenatal electronic fetal heart monitoring automatic identification system based on deep learning | |
| CN118609844B (en) | Internet medical diagnosis method for generating large model based on retrieval | |
| CN118553425A (en) | Construction method and system for medical health dynamic prediction model | |
| CN118490190A (en) | Intelligent watch heart rate abnormality early warning method and system based on deep learning | |
| CN117408823A (en) | Health data design life insurance scheme system for real-time human body monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20231110 |