Prenatal psychological state assessment method and system for pregnant woman

Abstract

The invention discloses a pregnant woman prenatal psychological state assessment method and system, and relates to the technical field of psychological state assessment. According to the system, the prenatal psychological state of the pregnant woman can be comprehensively and accurately evaluated by comprehensively collecting related information of various ways such as field interview, questionnaires, medical records, wearable equipment data, social software data and related personnel inquiry; moreover, the collected data can be cleaned, preprocessed and standardized, then an evaluation model is constructed through a deep learning model, and weighted distribution is performed according to the importance of different data types, so that a relatively accurate evaluation result is obtained, the prenatal psychological state of the pregnant woman can be accurately predicted, problems can be timely found, and the accuracy of the prenatal psychological state of the pregnant woman can be improved. The assessment report displays the current psychological state overall score, specific problem diagnosis, psychological state change trend analysis and main psychological risk factors of the pregnant woman in a visual chart form, and provides intervention suggestions for the pregnant woman and family members thereof.

Description

Technical Field

[0001] The present invention relates to the technical field of psychological state assessment, and in particular to a method and system for assessing the psychological state of pregnant women before childbirth. Background Art

[0002] Pregnancy is a special period in a woman's life. Along with the great changes in her body, she also faces many psychological challenges. The psychological state of pregnant women before delivery not only affects their own physical and mental health, but is also closely related to the development of the fetus and the future mother-child relationship.

[0003] However, the existing psychological assessment methods for pregnant women have many shortcomings. Traditional questionnaire assessment methods are often limited to single, static surveys, which are difficult to fully reflect the dynamic changes in the psychological state of pregnant women throughout pregnancy. In addition, the questionnaire results are easily affected by subjective factors of pregnant women, such as their emotional state at the time and their understanding of the problem, resulting in limited assessment accuracy. In addition, there is a lack of comprehensive analysis of multi-dimensional data of pregnant women, and the inherent connection between physiological indicators, living environment, social interaction and other information and psychological state cannot be fully integrated, making it impossible to provide pregnant women with personalized and accurate psychological intervention and health management programs.

[0004] Based on the above reasons, the present invention proposes a method and system for assessing the psychological state of pregnant women before delivery to solve the above problems. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the shortcomings of the prior art, the present invention can comprehensively and accurately evaluate the prenatal psychological state of pregnant women by comprehensively collecting relevant information from multiple channels including on-site interviews, questionnaires, medical records, wearable device data, social software data and inquiries from relevant personnel; and the present invention will clean, preprocess and standardize the collected data to ensure the accuracy and consistency of the data, and then construct an evaluation model through a deep learning model, and perform weighted distribution according to the importance of different data types, so as to obtain a more accurate evaluation result, so that the prenatal psychological state of pregnant women can be accurately predicted and problems can be discovered in a timely manner. Then the evaluation report will show the overall score of the current psychological state of the pregnant woman, specific problem diagnosis, psychological state change trend analysis and major psychological risk factors in the form of intuitive charts, and provide detailed intervention suggestions for pregnant women and their families; the evaluation system of the present invention can classify the psychological state of pregnant women and propose different intervention measures to ensure psychological health during pregnancy, from optimistic level to severe level, respectively propose family care, regular consultation with psychological counselors, and even emergency professional treatment suggestions, effectively prevent and deal with psychological problems during pregnancy, and ensure the safety of mothers and babies.

[0007] (II) Technical solution

[0008] To achieve the above object, the present invention provides the following technical solution: a method for assessing the psychological state of a pregnant woman before childbirth, comprising the following steps:

[0009] S1: Collect information related to pregnant women from multiple sources and establish an independent data set for pregnant women;

[0010] S2: Preprocess and integrate the collected data, and build an evaluation model based on the preprocessed and integrated data;

[0011] S3: Input keywords based on the constructed evaluation model, and use the evaluation model to evaluate the prenatal psychological state of pregnant women under the keywords;

[0012] S4: Generate assessment results and intervention recommendations, and output an assessment report based on the assessment results and intervention recommendations.

[0013] Preferably, the method of collecting information related to pregnant women includes on-site interview data collection, questionnaire data collection, medical data collection, data collection based on wearable devices, social software data collection and inquiries from relevant personnel.

[0014] Preferably, the information collected about pregnant women includes the pregnant woman's age, occupation, education level, marital status, family economic status, living environment, gestational age, whether there are pregnancy complications, major life experiences, composition of family members, cognition and expectations of childbirth and the fetus, prenatal examination data, real-time physical condition data, social browsing and speech data, and the understanding of the pregnant woman's personality by people around her or relatives and friends.

[0015] Preferably, the preprocessing operation on the collected data includes the following operations:

[0016] Clean the questionnaire data, check and remove invalid answers, and mark suspected erroneous data to facilitate confirmation operations;

[0017] Use outlier detection algorithms to identify abnormal data points caused by equipment failure or measurement errors, and directly extract accurate physiological-related medical abnormal data, make timely reminders, and supplement missing data during the next prenatal checkup or real-time collection process;

[0018] Classify the data generated by pregnant women on social software, clean the same or similar data, and obtain accurate social data information;

[0019] The data obtained from inquiries from relevant personnel are compared and confirmed, and the data that is consistent based on multiple inquiries or conforms to the actual situation is retained, and abnormal or erroneous data is directly removed.

[0020] Preferably, the construction of the evaluation model comprises the following steps:

[0021] S11: extracting the preprocessed and integrated data, and assigning weights based on the data collected by different collection methods;

[0022] S12: Input the extracted data into a deep learning model, and construct a basic model based on multiple deep learning models, including a random forest model and a deep neural network model;

[0023] S13: Multiple basic models after deep learning are stacked and fused, and the prediction results of the basic models are used as new data features for re-training and prediction to build an assessment model for the prenatal psychological state of pregnant women.

[0024] Preferably, in the process of constructing the evaluation model, the weight allocated to the questionnaire data is 0.2, the weight allocated to the medical data is 0.35, the weight allocated to the social data of pregnant women is 0.4, the weight allocated to inquiries from relevant personnel is 0.05, and the different data types in each item of data will be weighted again according to the actual situation.

[0025] Preferably, the content of the assessment report covers the overall score of the pregnant woman's current psychological state, diagnosis of specific psychological problems, analysis of psychological state change trends, identification of major psychological risk factors, and comprehensive analysis conclusions based on multi-dimensional data. The report content is presented in intuitive and easy-to-understand charts as much as possible, and intervention recommendations are generated based on the content of the assessment report.

[0026] The system for assessing the psychological status of pregnant women before childbirth includes:

[0027] The multi-source data collection module collects various data of pregnant women based on multiple methods, including interview collection unit, questionnaire collection unit, medical acquisition unit, social collection unit and inquiry unit;

[0028] The multi-source data processing module performs unified cleaning and standardization operations on the collected multi-source data and extracts meaningful and accurate data for subsequent model building and analysis operations, including a data preprocessing unit, a feature extraction unit, and a model training unit;

[0029] The evaluation model module is used to construct the evaluation model and input keywords, and to evaluate the prenatal psychological state of pregnant women based on the keywords to achieve the classification of the prenatal psychological state of pregnant women;

[0030] The result output module is used to output the evaluation results of the evaluation model module and display the evaluation results in intuitive charts and other formats;

[0031] The intervention suggestion module proposes corresponding intervention suggestions based on the evaluation results and follows up on the progress of the implementation of the intervention suggestions.

[0032] Preferably, the classification and suggestions for the antenatal mental state of pregnant women include:

[0033] Optimistic level: indicates that the pregnant woman is in a positive and optimistic mental state and does not need any external psychological intervention. It is recommended that the pregnant woman continue to maintain this state.

[0034] Mild level: It indicates that the pregnant woman has certain psychological problems in some aspects, but it has little impact on the entire pregnancy. It is recommended to be counseled by family members or consulted by a professional psychological counselor once a week;

[0035] Moderate level: indicates that the pregnant woman has too much worry about the pregnancy process, and has a high degree of worry about the outside world and herself. It is recommended to ensure that at least one family member is accompanying her for 24 hours, and to receive consultation guidance from a professional psychological counselor three times a week and at least one hospital intervention treatment;

[0036] Severe level: It means that the pregnant woman has developed mental illness such as depression during pregnancy. The emergency psychological crisis intervention plan should be activated immediately and she should be transferred to a professional mental health medical institution for inpatient treatment. A medical team composed of professional psychiatrists, psychotherapists and nurses should provide 24-hour comprehensive monitoring and treatment for the pregnant woman.

[0037] (III) Beneficial effects

[0038] Compared with the prior art, the present invention provides a method and system for assessing the prenatal psychological state of pregnant women, which has the following beneficial effects: the present invention can comprehensively and accurately assess the prenatal psychological state of pregnant women by comprehensively collecting relevant information from multiple channels including on-site interviews, questionnaires, medical records, wearable device data, social software data and inquiries from relevant personnel; and the present invention will clean, preprocess and standardize the collected data to ensure the accuracy and consistency of the data, and then construct an assessment model through a deep learning model, and perform weighted allocation according to the importance of different data types, so as to obtain a more accurate assessment result, so that the prenatal psychological state of pregnant women can be accurately predicted and problems can be discovered in a timely manner, and then the assessment report will display the overall score of the current psychological state of pregnant women, specific problem diagnosis, psychological state change trend analysis and major psychological risk factors in the form of intuitive charts, and provide detailed intervention suggestions for pregnant women and their families; the assessment system of the present invention can propose different intervention measures according to the psychological state classification of pregnant women to ensure psychological health during pregnancy, from optimistic level to severe level, respectively propose family care, regular consultation by psychological counselors, and even emergency professional treatment suggestions, effectively prevent and deal with psychological problems during pregnancy, and ensure the safety of mothers and babies. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of the method for assessing the prenatal psychological state of a pregnant woman of the present invention;

[0040] Figure 2 This is a structural diagram of the system for assessing the prenatal psychological state of pregnant women according to the present invention. DETAILED DESCRIPTION

[0041] In order to better understand the purpose, structure and function of the present invention, in order to achieve accurate assessment of the prenatal psychological state of pregnant women, the present invention can comprehensively and accurately assess the prenatal psychological state of pregnant women by comprehensively collecting relevant information from multiple channels including on-site interviews, questionnaires, medical records, wearable device data, social software data and inquiries from relevant personnel; and the present invention will clean, preprocess and standardize the collected data to ensure the accuracy and consistency of the data, and then build an evaluation model through a deep learning model, and perform weighted distribution according to the importance of different data types, so as to obtain a more accurate evaluation result, so that the prenatal psychological state of pregnant women can be accurately predicted and problems can be discovered in time, and then the evaluation report will show the overall score of the current psychological state of pregnant women, specific problem diagnosis, psychological state change trend analysis and major psychological risk factors in the form of intuitive charts, and provide detailed intervention suggestions for pregnant women and their families; the evaluation system of the present invention can classify the psychological state of pregnant women and propose different intervention measures to ensure psychological health during pregnancy, from optimistic level to severe level, respectively propose family care, regular consultation by psychological counselors, and even emergency professional treatment suggestions, effectively prevent and deal with psychological problems during pregnancy, and ensure the safety of mothers and babies. The method and system for assessing the prenatal psychological state of pregnant women of the present invention are described in further detail.

[0042] refer to Figure 1 The present invention: a method for assessing the psychological state of a pregnant woman before childbirth, comprising the following steps:

[0043] S1: Collect information related to pregnant women from multiple sources and establish an independent data set for pregnant women;

[0044] Specifically, the methods for collecting information related to pregnant women include on-site interview data collection, questionnaire data collection, medical data collection, data collection based on wearable devices, social software data collection and inquiries from relevant personnel.

[0045] Furthermore, the information collected about pregnant women includes the pregnant woman's age, occupation, education level, marital status, family economic status, living environment, gestational age, whether there are pregnancy complications, major life experiences, composition of family members, cognition and expectations of childbirth and the fetus, prenatal examination data, real-time physical condition data, social browsing and speech data, and the understanding of the pregnant woman's personality by people around her or relatives and friends.

[0046] S2: Preprocess and integrate the collected data, and build an evaluation model based on the preprocessed and integrated data;

[0047] Specifically, the preprocessing operation on the collected data includes the following operations:

[0048] Clean the questionnaire data, check and remove invalid answers, and mark suspected erroneous data to facilitate confirmation operations;

[0049] Use outlier detection algorithms to identify abnormal data points caused by equipment failure or measurement errors, and directly extract accurate physiological-related medical abnormal data, make timely reminders, and supplement missing data during the next prenatal checkup or real-time collection process;

[0050] Classify the data generated by pregnant women on social software, clean the same or similar data, and obtain accurate social data information;

[0051] The data obtained from inquiries from relevant personnel are compared and confirmed, and the data that is consistent based on multiple inquiries or conforms to the actual situation is retained, and abnormal or erroneous data is directly removed.

[0052] S3: Input keywords based on the constructed evaluation model, and use the evaluation model to evaluate the prenatal psychological state of pregnant women under the keywords;

[0053] Specifically, the construction of the evaluation model includes the following steps:

[0054] S11: extracting the preprocessed and integrated data, and assigning weights based on the data collected by different collection methods;

[0055] Furthermore, in the process of constructing the evaluation model, the weight allocated to the questionnaire data is 0.2, the weight allocated to the medical data is 0.35, the weight allocated to the social data of pregnant women is 0.4, the weight allocated to inquiries from relevant personnel is 0.05, and the different data types in each item of data will be weighted again according to the actual situation.

[0056] S12: Input the extracted data into a deep learning model, and construct a basic model based on multiple deep learning models, including a random forest model and a deep neural network model;

[0057] Furthermore, the random forest model is composed of multiple decision trees, and the generalization ability and noise resistance of the model are improved by integrated learning. The construction of the decision tree is based on information gain or Gini index and other criteria to split the features. Each tree independently classifies the sample, and finally the psychological state category of the sample is determined by a voting mechanism. When constructing the random forest model, the number of decision trees (, the depth of the tree, the number of features considered when the node is split, and other parameters are adjusted, and a cross-validation method is used to observe the performance of the model on the training set and the test set under different parameter settings to determine the optimal parameter configuration; the deep neural network (DNN) model: includes an input layer, multiple hidden layers and an output layer. The input layer receives the multi-source data feature vector after feature engineering, and the hidden layer uses different numbers of neurons (such as 32, 64, 128, etc.) and activation functions (such as ReLU function) , automatically learn complex patterns and feature representations in data through multi-layer nonlinear transformations. The output layer uses a softmax activation function to output the probability distribution of different psychological state categories. When building a DNN model, the back propagation algorithm is used to update parameters and train the model. Set appropriate hyperparameters such as learning rate (such as 0.001-0.01), batch size (BatchSize, such as 32-128) and number of training rounds (Epochs, such as 100-500). Use the early stopping method to prevent overfitting, that is, monitor the performance of the model on the validation set during training, and stop training when the performance no longer improves. At the same time, regularization techniques (such as L1 and L2 regularization) are combined to constrain model parameters, reduce the complexity of the model, and improve generalization ability. Through multiple tests of different hyperparameter combinations, the model parameter settings with the best performance on the test set are selected.

[0058] S13: Multiple basic models after deep learning are stacked and fused, and the prediction results of the basic models are used as new data features for re-training and prediction to build an assessment model for the prenatal psychological state of pregnant women.

[0059] S4: Generate evaluation results and intervention recommendations, and output evaluation reports based on the evaluation results and intervention recommendations;

[0060] Specifically, the assessment report covers the overall score of the pregnant woman's current mental state, diagnosis of specific psychological problems, analysis of mental state change trends, identification of major psychological risk factors, and comprehensive analysis conclusions based on multi-dimensional data. The report content is presented in intuitive and easy-to-understand charts as much as possible, and intervention recommendations are generated based on the content of the assessment report.

[0061] refer to Figure 2 , the prenatal psychological status assessment system for pregnant women, including:

[0062] The multi-source data collection module collects various data of pregnant women based on multiple methods, including interview collection unit, questionnaire collection unit, medical acquisition unit, social collection unit and inquiry unit;

[0063] The multi-source data processing module performs unified cleaning and standardization operations on the collected multi-source data and extracts meaningful and accurate data for subsequent model building and analysis operations, including a data preprocessing unit, a feature extraction unit, and a model training unit;

[0064] The evaluation model module is used to construct the evaluation model and input keywords, and to evaluate the prenatal psychological state of pregnant women based on the keywords to achieve the classification of the prenatal psychological state of pregnant women;

[0065] The result output module is used to output the evaluation results of the evaluation model module and display the evaluation results in intuitive charts and other formats;

[0066] The intervention suggestion module proposes corresponding intervention suggestions based on the evaluation results and follows up on the progress of the implementation of the intervention suggestions.

[0067] Specifically, the classification and suggestions for the antenatal mental state of pregnant women include:

[0068] Optimistic level: indicates that the pregnant woman is in a positive and optimistic mental state and does not need any external psychological intervention. It is recommended that the pregnant woman continue to maintain this state.

[0069] Mild level: It indicates that the pregnant woman has certain psychological problems in some aspects, but it has little impact on the entire pregnancy. It is recommended to be counseled by family members or consulted by a professional psychological counselor once a week;

[0070] Moderate level: indicates that the pregnant woman has too much worry about the pregnancy process, and has a high degree of worry about the outside world and herself. It is recommended to ensure that at least one family member is accompanying her for 24 hours, and to receive consultation guidance from a professional psychological counselor three times a week and at least one hospital intervention treatment;

[0071] Severe level: It means that the pregnant woman has developed mental illness such as depression during pregnancy. The emergency psychological crisis intervention plan should be activated immediately and she should be transferred to a professional mental health medical institution for inpatient treatment. A medical team composed of professional psychiatrists, psychotherapists and nurses should provide 24-hour comprehensive monitoring and treatment for the pregnant woman.

[0072] It is to be understood that the present invention is described by some embodiments, and it is known to those skilled in the art that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the scope of protection of the present invention.

Claims

1. A method for assessing the psychological state of pregnant women before childbirth, characterized in that: The following steps are involved: S1: Collect information related to pregnant women from multiple sources and establish an independent data set for pregnant women; S2: Preprocess and integrate the collected data, and build an evaluation model based on the preprocessed and integrated data; S3: Input keywords based on the constructed evaluation model, and use the evaluation model to evaluate the prenatal psychological state of pregnant women under the keywords; S4: Generate assessment results and intervention recommendations, and output an assessment report based on the assessment results and intervention recommendations.

2. The method for assessing the prenatal psychological state of a pregnant woman according to claim 1, characterized in that: The methods for collecting information related to pregnant women include on-site interview data collection, questionnaire data collection, medical data collection, data collection based on wearable devices, social software data collection and inquiries from relevant personnel.

3. The method for assessing the prenatal psychological state of a pregnant woman according to claim 2, characterized in that: The information collected about pregnant women includes the pregnant woman's age, occupation, education level, marital status, family economic status, living environment, gestational age, whether there are pregnancy complications, major life experiences, composition of family members, cognition and expectations of childbirth and the fetus, prenatal examination data, real-time physical condition data, social browsing and speech data, and the understanding of the pregnant woman's personality by people around her or relatives and friends.

4. The method for assessing the prenatal psychological state of a pregnant woman according to claim 3, characterized in that: The preprocessing operation on the collected data includes the following operations: Clean the questionnaire data, check and remove invalid answers, and mark suspected erroneous data to facilitate confirmation operations; Use outlier detection algorithms to identify abnormal data points caused by equipment failure or measurement errors, and directly extract accurate physiological-related medical abnormal data, make timely reminders, and supplement missing data during the next prenatal checkup or real-time collection process; Classify the data generated by pregnant women on social software, clean the same or similar data, and obtain accurate social data information; The data obtained from inquiries from relevant personnel are compared and confirmed, and the data that is consistent based on multiple inquiries or conforms to the actual situation is retained, and abnormal or erroneous data is directly removed.

5. The method for assessing the prenatal psychological state of a pregnant woman according to claim 4, characterized in that: The construction of the evaluation model includes the following steps: S11: extracting the preprocessed and integrated data, and assigning weights based on the data collected by different collection methods; S12: Input the extracted data into a deep learning model, and construct a basic model based on multiple deep learning models, including a random forest model and a deep neural network model; S13: Multiple basic models after deep learning are stacked and fused, and the prediction results of the basic models are used as new data features for re-training and prediction to build an assessment model for the prenatal psychological state of pregnant women.

6. The method for assessing the prenatal psychological state of a pregnant woman according to claim 5, characterized in that: In the process of constructing the evaluation model, the weight allocated to the questionnaire data is 0.2, the weight allocated to the medical data is 0.35, the weight allocated to the social data of pregnant women is 0.4, the weight allocated to the inquiries from relevant personnel is 0.05, and the different data types in each item of data will be weighted again according to the actual situation.

7. The method for assessing the prenatal psychological state of a pregnant woman according to claim 6, characterized in that: The assessment report covers the overall score of the pregnant woman's current mental state, diagnosis of specific psychological problems, analysis of mental state change trends, identification of major psychological risk factors, and comprehensive analysis conclusions based on multi-dimensional data. The report content is presented in intuitive and easy-to-understand charts as much as possible, and intervention recommendations are generated based on the content of the assessment report.

8. The system for assessing the psychological state of pregnant women before childbirth is characterized by: include: The multi-source data collection module collects various data of pregnant women in a variety of ways, including interview collection unit, questionnaire collection unit, medical acquisition unit, social collection unit and inquiry unit; The multi-source data processing module performs unified cleaning and standardization operations on the collected multi-source data and extracts meaningful and accurate data for subsequent model building and analysis operations, including a data preprocessing unit, a feature extraction unit, and a model training unit; The evaluation model module is used to construct the evaluation model and input keywords, and to evaluate the prenatal psychological state of pregnant women based on the keywords to achieve the classification of the prenatal psychological state of pregnant women; The result output module is used to output the evaluation results of the evaluation model module and display the evaluation results in intuitive charts and other formats; The intervention suggestion module proposes corresponding intervention suggestions based on the evaluation results and follows up on the progress of the implementation of the intervention suggestions.

9. The system for assessing the prenatal psychological state of pregnant women according to claim 8, characterized in that: The classification and recommendations for the antenatal psychological state of pregnant women include: Optimistic level: indicates that the pregnant woman is in a positive and optimistic mental state and does not need any external psychological intervention. It is recommended that the pregnant woman continue to maintain this state. Mild level: It indicates that the pregnant woman has certain psychological problems in some aspects, but it has little impact on the entire pregnancy. It is recommended to be counseled by family members or consulted by a professional psychological counselor once a week. Moderate level: indicates that the pregnant woman has too much worry about the pregnancy process, and has a high degree of worry about the outside world and herself. It is recommended to ensure that at least one family member is accompanying her for 24 hours, and to receive consultation guidance from a professional psychological counselor three times a week and at least one hospital intervention treatment; Severe level: It means that the pregnant woman has developed mental illness such as depression during pregnancy. The emergency psychological crisis intervention plan should be activated immediately and she should be transferred to a professional mental health institution for inpatient treatment. A medical team composed of professional psychiatrists, psychotherapists and nurses should provide 24-hour comprehensive monitoring and treatment for the pregnant woman.

Images