CN119028512B - Obstetrical real-time nursing optimization method based on big data - Google Patents
Obstetrical real-time nursing optimization method based on big data Download PDFInfo
- Publication number
- CN119028512B CN119028512B CN202411510173.8A CN202411510173A CN119028512B CN 119028512 B CN119028512 B CN 119028512B CN 202411510173 A CN202411510173 A CN 202411510173A CN 119028512 B CN119028512 B CN 119028512B
- Authority
- CN
- China
- Prior art keywords
- data
- health
- time
- physiological
- mother
- 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.)
- Active
Links
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- 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
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)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
本发明公开了一种基于大数据的产科实时护理优化方法，涉及人工智能技术领域，包括：实时采集母体和胎儿的生理数据，并将母体和胎儿的生理数据与历史健康数据融合预处理，形成多维度的健康数据集；构建个性化动态健康模型，实时分析母体和胎儿的生理变化，预测未来的健康趋势；将预测未来的健康趋势与胎儿心电、母体心电及环境数据融合，识别出潜在的健康风险；根据风险评估结果对异常事件进行分类，生成个性化护理方案，并对生成的个性化护理方案进行自动优化；本发明通过智能反馈机制，系统能生成并动态优化个性化护理方案，实时调整护理路径，显著提升了产科护理的精确性和可靠性。
The present invention discloses a real-time obstetric care optimization method based on big data, which relates to the field of artificial intelligence technology, including: real-time collection of maternal and fetal physiological data, and pre-processing of the maternal and fetal physiological data by fusing them with historical health data to form a multi-dimensional health data set; constructing a personalized dynamic health model, analyzing the physiological changes of the mother and fetus in real time, and predicting future health trends; fusing the predicted future health trends with fetal electrocardiogram, maternal electrocardiogram and environmental data to identify potential health risks; classifying abnormal events according to risk assessment results, generating personalized care plans, and automatically optimizing the generated personalized care plans; through the intelligent feedback mechanism of the present invention, the system can generate and dynamically optimize personalized care plans, adjust the care path in real time, and significantly improve the accuracy and reliability of obstetric care.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an obstetrical real-time nursing optimization method based on big data.
Background
Along with the rapid development of big data technology, internet of things and artificial intelligence, the medical field, particularly obstetrical nursing, is gradually changed to an intelligent and personalized direction. Traditional obstetric nursing mode mainly relies on regular clinical examination and experience judgment of doctors, full-time monitoring of pregnant women and fetuses cannot be achieved, and particularly in late pregnancy, the physical condition of the pregnant women changes frequently, and the health condition of fetuses can be affected by a plurality of factors.
However, existing technical means generally only provide physiological data monitoring in a single dimension, and fail to fully utilize historical health data and multimodal data for comprehensive health trend analysis. In addition, the existing system in the aspects of abnormality detection and care scheme formulation can only rely on preset rules, lacks the ability of dynamic adjustment and individuation, and is difficult to cope with complex and changeable clinical situations.
Disclosure of Invention
The present invention has been made in view of the above-described problems occurring in the prior art.
Therefore, the invention provides a real-time obstetrical nursing optimizing method based on big data, which solves the problem that the traditional obstetrical nursing cannot fuse multidimensional data in real time, forecast health trend and dynamically optimize nursing scheme in personalized way.
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, the embodiment of the invention provides a real-time obstetrical nursing optimization method based on big data, which comprises the steps of collecting physiological data of a mother and a fetus in real time, and fusing and preprocessing the physiological data of the mother and the fetus with historical health data to form a multi-dimensional health data set;
Constructing a personalized dynamic health model, analyzing physiological changes of a mother and a fetus in real time, and predicting future health trend;
fusing the predicted future health trend with fetal electrocardio, maternal electrocardio and environmental data, and identifying potential health risks;
and classifying the abnormal events according to the risk assessment result, generating a personalized care scheme, and automatically optimizing the generated personalized care scheme.
As a preferred scheme of the real-time obstetrical nursing optimizing method based on big data, physiological data of the parent body comprise heart rate, blood pressure, blood sugar, body temperature, respiratory frequency and blood oxygen saturation;
the physiological data of the fetus includes fetal electrocardiosignals, fetal movement frequency and uterine contraction intensity.
As a preferred scheme of the obstetrical real-time nursing optimizing method based on big data, the invention fuses and preprocesses physiological data of a mother and a fetus and historical health data to form a multi-dimensional health data set, and the method comprises the following steps:
Constructing a data integration platform, and performing data cleaning, format conversion and time stamp synchronous processing on physiological data of a mother and a fetus from different devices;
Combining the processed data with the historical health record to form a multi-dimensional health data set.
As a preferable scheme of the obstetrical real-time nursing optimizing method based on big data, the invention constructs a personalized dynamic health model, analyzes physiological changes of a mother and a fetus in real time, predicts future health trend, and comprises the following steps:
Inputting physiological data of a mother and a fetus into a long-short-time memory network in deep learning, extracting time sequence characteristics by analyzing the trend of the physiological data along with time, analyzing the frequency components of the physiological signals to extract frequency domain characteristics, analyzing the fluctuation amplitude and the change rate of the physiological parameters to extract abnormal characteristics, and capturing the dependency relationship between the mother of the mother and the fetus to extract correlation characteristics;
And predicting future health trend according to the analysis result, wherein the expression is as follows:
;
Wherein, Is the moment of timeIs a function of the health prediction value of (1),Is the firstThe physiological data is at the momentIs used as a reference to the value of (a),Is the firstThe mean value of the seed physiological data,Is the firstThe standard deviation of the seed physiological data,Is an index of the physiological data and,Is the firstThe weight of the seed physiological data,Is thatThe state of health at the moment of time,Is the current time of day and,Is a time constant which is a function of the time constant,Is the amount of physiological data.
As a preferred scheme of the obstetrical real-time nursing optimizing method based on big data, the method for fusing the predicted future health trend with fetal electrocardio, maternal electrocardio and environmental data, and identifying potential health risks comprises the following steps:
collecting fetal electrocardiogram, maternal electrocardiogram and environmental data in real time, and extracting the characteristics of each mode data;
dynamically adjusting the weight according to the contribution of each mode data to the health state in the past period, wherein the expression is as follows:
;
Wherein, Is the firstThe weight of the particular modality data,Is an index of data of a particular modality,Is the number of particular modes that are to be selected,Is the firstThe historical contribution of the particular modality data,Is the degree of contribution to traversing all of the modality data,Is the firstHistorical contribution of the particular modality data;
and (3) weighting and fusing the modal data according to the weight to obtain multi-modal comprehensive data, wherein the expression is:
;
Wherein, Is the moment of timeIs used for the multi-modal integrated data of the (a),Is the moment of timeIs the first of (2)The actual value of the individual modality data,Is an index of the modal data,Is the number of modality data;
Integrating the variable self-encoder and the convolutional neural network, and capturing global and local characteristics of each mode data;
Learning historical normal data by using a variable-score-based self-encoder, generating potential distribution of each mode data, encoding the mode data input in real time by using the variable-score-based self-encoder, comparing the potential distribution with the potential distribution of the historical normal data, and calculating the deviation degree;
extracting local features from the modal data by using a convolutional neural network, and detecting whether local abnormal signals exist;
Calculating the abnormal score of the current multi-mode comprehensive data through an abnormal scoring mechanism based on KL divergence, wherein the expression is as follows:
;
Wherein, Is at the momentIs used for the abnormal scoring of (a),Is the moment of timeIs used for the multi-modal integrated data of the (a),Is the moment of timeCurrent distribution of multi-modal integrated dataIs the firstNormal distribution of the integrated data calculated from the multi-modal data,Is the moment of timeIs a current distribution of the health prediction values of (a),Is the moment of timeIs a function of the health prediction value of (1),Is the firstA normal distribution of health predictors for the individual modality data,Is a time-influencing factor which is a factor of the influence of time,Is an asymmetric measure that is used to measure the difference between two probability distributions.
As a preferable scheme of the obstetrical real-time nursing optimizing method based on big data, the abnormal events are classified according to the risk assessment result, and the personalized nursing scheme is generated by the following steps:
the abnormal events are classified into low risk, medium risk and high risk according to the magnitude of the abnormal scores;
When a low risk is detected, no immediate intervention is required, providing personalized advice to the pregnant woman;
When medium risk is detected, automatically sending a notice to a doctor to provide current abnormal details, suggesting that the doctor observe and further monitor relevant physiological data through a remote monitoring platform, providing nursing guidance, pushing an abnormal report to a pregnant woman, and suggesting that the pregnant woman performs clinical examination regularly;
When the high risk abnormality is detected, the doctor is immediately notified and the pregnant woman is advised to go to the hospital immediately, the frequency of fetal heart monitoring is automatically increased, physiological signals of the fetus and the mother are tracked in real time, an alarm is sent through the emergency notification platform, and an emergency care scheme is started.
As a preferred scheme of the obstetrical real-time nursing optimizing method based on big data, the automatic optimizing of the generated personalized nursing scheme comprises the following steps:
periodically collecting new multimodal data and user feedback;
Evaluating the effect of the current care regimen based on the new data and user feedback;
And adding personalized suggestions according to the evaluation result, improving user experience, and forming an optimized nursing scheme.
In a second aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, implements any of the steps of the big data based obstetrical real time care optimization method as described in the first aspect of the present invention.
In a third aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which when executed by a processor implements any of the steps of the big data based real-time obstetric care optimization method of the first aspect of the present invention.
The intelligent health care system has the beneficial effects that physiological data of a mother and a fetus are collected in real time and are fused with historical health data for preprocessing to form a multi-dimensional health data set, so that the comprehensive monitoring of the pregnant woman and the fetus is realized, a personalized dynamic health model is built, physiological changes are analyzed in real time, health trends are predicted, the early warning capability of the system is improved, a prediction result is fused with the electrocardio of the fetus, the electrocardio of the mother and environmental data, a multi-mode self-adaptive weighted fusion method and a convolution neural network are adopted, potential health risks are identified, abnormal events are classified, the system automatically selects a feedback mechanism according to the risk level and adopts corresponding intervention measures, the timeliness and the effectiveness of nursing are ensured, the intelligent feedback mechanism is adopted, the system can generate and dynamically optimize a personalized nursing scheme, the nursing path is adjusted in real time, the accuracy and the reliability of obstetrical nursing are remarkably improved, the potential health risks are reduced, and the safety of the mother and the infant is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for 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 invention, 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 flowchart of the obstetrical real-time care optimization method based on big data in example 1.
Fig. 2 is a flowchart of anomaly scoring in example 1.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Embodiment 1, referring to fig. 1 and 2, is a first embodiment of the present invention, which provides a real-time obstetrical care optimization method based on big data, comprising the steps of:
S1, acquiring physiological data of a mother and a fetus in real time, and fusing and preprocessing the physiological data of the mother and the fetus with historical health data to form a multi-dimensional health data set, wherein the method comprises the following steps of:
The physiological data of the mother body comprises heart rate, blood pressure, blood sugar, body temperature, respiratory frequency and blood oxygen saturation, the physiological data of the fetus comprises fetal electrocardiosignals, fetal movement frequency and uterine contraction intensity, a data integration platform is constructed, data from different devices are subjected to data cleaning, format conversion and time stamp synchronous processing, and the processed data are combined with a historical health record to form a multi-dimensional health data set.
It should be noted that by collecting various physiological data of the mother and the fetus, including heart rate, blood pressure, blood sugar, body temperature, respiratory rate, blood oxygen saturation, fetal electrocardiosignals, fetal movement frequency and uterine contraction intensity, comprehensive monitoring of the health status of the mother and the fetus is realized, for example, heart rate and blood pressure can reflect the health status of the cardiovascular system, blood sugar can reflect the metabolic status, body temperature and blood oxygen saturation can reflect the whole health status of the body, fetal electrocardiosignals and fetal movement frequency can reflect the health status of the fetus, uterine contraction intensity can reflect the preparation status before delivery, potential health problems can be found in early stage by multi-dimensional data collection, intervention measures can be timely taken, health risk of mother and infant is reduced, and personalized health assessment can be realized by fusing historical health data. For example, if a pregnant woman has a history of hypertension, the system may be more concerned with changes in blood pressure data and discover potential hypertension risks in time. The genetic data can provide genetic information to help identify the risk of genetic diseases, and the fusion of the historical health data enables the system to perform long-term trend analysis and find the change trend of the health state. For example, by analyzing the health records of past pregnancy, the long-term change rule of certain physiological parameters can be found, the basis is provided for future health management and prevention, and short-term fluctuation and noise in the data can be eliminated through data smoothing processing, so that the data is more stable and reliable. This helps to reduce false positives and false negatives, and to improve the accuracy of the health assessment. For example, heart rate data may be affected by short-term activity, short-term fluctuations may be filtered out by smoothing to better reflect the actual physiological state, and noise reduction may remove interference signals from the data to improve the quality of the data. This is particularly important for physiological data, as physiological signals are often subject to interference from a variety of factors, such as environmental noise, device noise, and the like. The noise reduction treatment can improve the signal-to-noise ratio of the data, so that the subsequent analysis is more accurate, and the standardized treatment can convert different types of physiological data into the same dimension, thereby facilitating the comparison and analysis. This helps to eliminate dimensional differences between different data, improving consistency and comparability of the data. For example, the heart rate and the blood pressure are different in data units, and can be converted into the same dimension through standardized processing, so that comprehensive analysis is facilitated.
S2, constructing a personalized dynamic health model, analyzing physiological changes of a mother body and a fetus in real time, and predicting future health trend, wherein the method comprises the following steps:
Inputting physiological data of a mother and a fetus into a long-short-time memory network in deep learning, extracting time sequence characteristics by analyzing the trend of the physiological data along with time, analyzing the frequency components of the physiological signals to extract frequency domain characteristics, analyzing the fluctuation amplitude and the change rate of the physiological parameters to extract abnormal characteristics, and capturing the dependency relationship between the mother of the mother and the fetus to extract correlation characteristics;
And predicting future health trend according to the analysis result, wherein the expression is as follows:
;
Wherein, Is the moment of timeIs a function of the health prediction value of (1),Is the firstThe physiological data is at the momentIncluding heart rateBlood pressureFrequency of fetal movementFetal electrocardiosignalAnd uterine contraction intensity,Is the firstThe mean value of the seed physiological data,Is the firstThe standard deviation of the seed physiological data,Is an index of the physiological data and,Is the firstThe weight of the physiological data is set according to the influence degree of the physiological data on the whole health, and the weight is set as follows, fetal electrocardiosignalsUterine contraction intensity =0.3Frequency of fetal movement =0.25Mother heart rate =0.2=0.15, Maternal blood pressure=0.1,Is thatIs thatThe health state at the moment is in the numerical range of 0-0≤1,Is the current time of day and,Is a time constant for adjusting the decay rate of the history data effects,Is the amount of physiological data, and the type of the physiological data used is flexibly adjusted according to the specific situation so as to more comprehensively capture the health condition of the mother and the fetus.
Still further, the method further comprises the steps of,Is a real number when the value range of (a)When >0, it indicates that the health state is good, the larger the value, the more stable the physiological state of the mother and fetus is, whenWhen the pressure is approximately equal to 0, the health state is critical, and further observation and monitoring are needed, whenAnd when the number is <0, indicating that the health risk exists, and the smaller the number is, the larger the risk is, and the system should give early warning in time.
It should be noted that by analyzing the multidimensional dataset by using a long and short term memory network (LSTM) in deep learning, key features are extracted, and accurate capturing of maternal and fetal physiological changes is realized. The LSTM network can effectively process time series data and capture long-time dependency relationship, so that the most representative characteristics are extracted from complex physiological data. The method not only improves the efficiency of data processing, but also provides high-quality input data for the subsequent health prediction model, and ensures the accuracy and reliability of prediction. Finally, by extracting key features, the system can more accurately identify potential health risks, provide scientific basis for early intervention, and by constructing a personalized health prediction model, the system can predict future health trends according to analysis results. The model is based on the time sequence modeling capability of the LSTM network, and can capture the dynamic change rule of the physiological data of the mother and the fetus, so that the future health state can be predicted. The personalized prediction model is built, so that the health condition of each pregnant woman can be evaluated and predicted in a targeted manner, and the accuracy and applicability of prediction are improved. In addition, by predicting future health trends, the system can send out early warning in advance before potential health problems occur, and precious time windows are provided for doctors and pregnant women, so that timely intervention measures are taken, and health risks are effectively prevented.
S3, fusing the predicted future health trend with fetal electrocardio, maternal electrocardio and environmental data, and identifying potential health risks, wherein the method comprises the following steps of:
collecting fetal electrocardiogram, maternal electrocardiogram and environmental data in real time, and extracting the characteristics of each mode data;
dynamically adjusting the weight according to the contribution of each mode data to the health state in the past period, wherein the expression is as follows:
;
Wherein, Is the firstThe weight of the particular modality data,Is an index of data of a particular modality,Is the number of particular modes that are to be selected,Is the firstThe historical contribution of the particular modality data,Is the degree of contribution to traversing all of the modality data,Is the firstHistorical contribution of the particular modality data;
and (3) weighting and fusing the modal data according to the weight to obtain multi-modal comprehensive data, wherein the expression is:
;
Wherein, Is the moment of timeIs used for the multi-modal integrated data of the (a),Is the moment of timeIs the first of (2)The actual value of the individual modality data,Is an index of the modal data,Is the number of modality data;
Selecting a set model based on a variation self-encoder and a convolutional neural network, and capturing global and local characteristics of each mode data;
Learning historical normal data by using a variable-score-based self-encoder, generating potential distribution of each mode data, encoding the mode data input in real time by using the variable-score-based self-encoder, comparing the potential distribution with the potential distribution of the historical normal data, and calculating the deviation degree;
Extracting local features from the modal data by using a convolutional neural network, and detecting whether local abnormal signals (such as burst abnormality in maternal electrocardiosignals, abnormal fluctuation in fetal electrocardiosignals and the like) exist;
Calculating the abnormal score of the current multi-mode comprehensive data through an abnormal scoring mechanism based on KL divergence, wherein the expression is as follows:
;
Wherein, Is at the momentIs used for the abnormal scoring of (a),Is the moment of timeIs used for the multi-modal integrated data of the (a),Is the moment of timeIs provided with a current distribution of multi-modal integrated data,Is the firstNormal distribution of the integrated data calculated from the multi-modal data,Is the current distribution of the health prediction values at time t,Is the moment of timeIs a function of the health prediction value of (1),Is the firstA normal distribution of health predictors for the individual modality data,Is a time-influencing factor which is a factor of the influence of time,Is an asymmetric measure that is used to measure the difference between two probability distributions.
It should be noted that Fetal Electrocardiograms (FECG), maternal Electrocardiograms (MECG), and environmental data (e.g., temperature, humidity, noise level) are acquired in real-time by wearable devices and medical-grade monitoring instruments. Feature extraction is carried out on each mode data, such as heart rate variability, R-R interval, blood pressure fluctuation and the like, so that physiological changes of a mother and a fetus can be reflected in time, and the sensitivity and accuracy of monitoring are improved. The method is characterized in that the method is used for extracting key information from complex data, facilitating subsequent analysis and modeling, quickly finding potential health problems, improving early warning capability, timely taking intervention measures to ensure the safety of the mother and the infant, capturing the influence of different modal data on the health state better by dynamically adjusting weights, improving the accuracy and reliability of health risk identification by means of a model, comprehensively utilizing information from different sources by means of modal data fusion, improving the comprehensiveness and the comprehensiveness of the model, better reflecting the overall health condition of the mother and the fetus, realizing accurate identification and classification of the potential health risks by means of multi-modal data fusion and deep learning models, improving the sensitivity and accuracy of early warning, and timely taking intervention measures.
S4, classifying the abnormal events according to the risk assessment result, generating a personalized care scheme, and automatically optimizing the generated personalized care scheme, wherein the method comprises the following steps:
the abnormal events are classified into low risk, medium risk and high risk according to the magnitude of the abnormal scores;
When a low risk is detected, no immediate intervention is required, providing personalized advice to the pregnant woman;
When medium risk is detected, automatically sending a notice to a doctor to provide current abnormal details, suggesting that the doctor observe and further monitor relevant physiological data through a remote monitoring platform, providing nursing guidance, pushing an abnormal report to a pregnant woman, and suggesting that the pregnant woman performs clinical examination regularly;
When the high risk abnormality is detected, immediately informing a doctor and suggesting that the pregnant woman immediately goes to a hospital, automatically increasing the frequency of fetal heart monitoring, tracking physiological signals of the fetus and the mother in real time, sending an alarm through an emergency informing platform and starting an emergency nursing scheme;
periodically collecting new multimodal data and user feedback;
Evaluating the effect of the current care regimen based on the new data and user feedback;
And adding personalized suggestions according to the evaluation result, improving user experience, and forming an optimized nursing scheme.
Further, an abnormality classification low risk threshold is set asA high risk threshold ofThe abnormal event classification criteria are as follows:
when 0< ≤When the abnormal score is low, and the abnormal score belongs to low risk<≤When it indicates that there is a medium risk, when>When this indicates a high risk.
It should be noted that by calculating the abnormal scores, the abnormal events are classified into low risk, medium risk and high risk, so that the system can take different intervention measures according to risks of different levels, a one-time management mode is avoided, the precision and effectiveness of nursing are improved, reasonable allocation of resources is ensured, excessive intervention is avoided under low risk conditions, timely monitoring and guidance are performed under medium risk conditions, emergency measures are rapidly taken under high risk conditions, so that the efficiency and safety of overall nursing are improved, personalized health suggestions such as reasonable diet, proper motion and the like are generated according to physiological data and historical health records of the pregnant women, the health of the pregnant women is better managed in daily life, potential health problems are prevented, self-management capacity of the pregnant women is enhanced, unnecessary medical intervention is reduced, the quality and satisfaction of the pregnant women are improved, doctors monitor physiological data of the pregnant women and the fetus in real time through a remote monitoring platform, professional nursing guidance is provided, and abnormal reports are pushed to the pregnant women, clinical examination is performed, the health conditions of the pregnant women can be rapidly taken under the high risk conditions, the necessary emergency treatment and the emergency treatment is rapidly started, the safety of the emergency treatment platform is further improved, the emergency treatment is rapidly responded to the emergency treatment is rapidly and the emergency treatment is improved, the emergency treatment is rapidly started, the emergency treatment is rapidly is improved, the emergency treatment is rapidly is accelerated, the emergency treatment is well is prevented, and the emergency treatment is rapidly is well has been improved, the harm of high risk events to pregnant women and fetuses is reduced to the greatest extent, and the success rate of first aid is improved.
The embodiment also provides computer equipment, which is suitable for the situation of the obstetrical real-time nursing optimizing method based on big data, and comprises a memory and a processor, wherein the memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions to realize the obstetrical real-time nursing optimizing method based on big data, which is provided by the embodiment.
The computer device may be a terminal comprising a processor, a memory, a communication interface, a display screen and input means connected by a system bus. Wherein the processor of the computer device is configured 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 computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
The present embodiment also provides a storage medium having a computer program stored thereon, which when executed by a processor implements the obstetric real-time care optimization method based on big data as proposed in the above embodiment, the storage medium may be implemented by any type of volatile or non-volatile storage device or combination thereof, such as a static random access Memory (Static Random Access Memory, SRAM for short), an electrically erasable Programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM for short), an erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM for short), a Programmable Read-Only Memory (ROM for short), a magnetic Memory, a flash Memory, a magnetic disk or an optical disk.
In summary, physiological data of a mother and a fetus are collected in real time and are fused with historical health data for preprocessing, a multi-dimensional health data set is formed, comprehensive monitoring of the mother and the fetus is achieved, a personalized dynamic health model is built, physiological changes are analyzed in real time, health trends are predicted, early warning capacity of a system is improved, a prediction result is fused with fetal electrocardio, maternal electrocardio and environment data, a multi-mode self-adaptive weighted fusion method and a convolution neural network are adopted, potential health risks are identified, abnormal events are classified, the system automatically selects a feedback mechanism according to risk levels, corresponding intervention measures are adopted, timeliness and effectiveness of nursing are guaranteed, the system can generate and dynamically optimize a personalized nursing scheme through the intelligent feedback mechanism, nursing paths are adjusted in real time, accuracy and reliability of nursing of the mother and the infant are remarkably improved, potential health risks are reduced, and safety of the mother and the infant is guaranteed.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (5)
1. An obstetrical real-time nursing optimizing method based on big data, which is characterized by comprising the following steps:
physiological data of a mother and a fetus are collected in real time, and are fused and preprocessed with historical health data to form a multi-dimensional health data set;
Constructing a personalized dynamic health model, analyzing physiological changes of a mother and a fetus in real time, and predicting future health trend;
fusing the predicted future health trend with fetal electrocardio, maternal electrocardio and environmental data, and identifying potential health risks;
Classifying the abnormal events according to the risk assessment result, generating a personalized care scheme, and automatically optimizing the generated personalized care scheme;
Physiological data of the parent includes heart rate, blood pressure, blood glucose, body temperature, respiratory rate, and blood oxygen saturation;
the physiological data of the fetus comprise fetal electrocardiosignals, fetal movement frequency and uterine contraction intensity;
fusing and preprocessing physiological data of a mother and a fetus with historical health data to form a multi-dimensional health data set, wherein the method comprises the following steps of:
Constructing a data integration platform, and performing data cleaning, format conversion and time stamp synchronous processing on physiological data of a mother and a fetus from different devices;
Combining the processed data with the historical health record to form a multi-dimensional health data set;
constructing a personalized dynamic health model, analyzing physiological changes of a mother and a fetus in real time, and predicting future health trend comprises the following steps:
Inputting physiological data of a mother and a fetus into a long-short-time memory network in deep learning, extracting time sequence characteristics by analyzing the trend of the physiological data along with time, analyzing the frequency components of the physiological signals to extract frequency domain characteristics, analyzing the fluctuation amplitude and the change rate of the physiological parameters to extract abnormal characteristics, and capturing the dependency relationship between the mother of the mother and the fetus to extract correlation characteristics;
And predicting future health trend according to the analysis result, wherein the expression is as follows:
;
Wherein, Is the moment of timeIs a function of the health prediction value of (1),Is the firstThe value of the seed physiological data at time t,Is the firstThe mean value of the seed physiological data,Is the firstThe standard deviation of the seed physiological data,Is an index of the physiological data and,Is the firstThe weight of the seed physiological data,Is thatThe state of health at the moment of time,Is the current time of day and,Is a time constant which is a function of the time constant,Is the amount of physiological data;
fusing the predicted future health trend with fetal, maternal and environmental data, identifying a potential health risk comprising the steps of:
collecting fetal electrocardiogram, maternal electrocardiogram and environmental data in real time, and extracting the characteristics of each mode data;
dynamically adjusting the weight according to the contribution of each mode data to the health state in the past period, wherein the expression is as follows:
;
Wherein, Is the firstThe weight of the particular modality data,Is an index of data of a particular modality,Is the number of particular modes that are to be selected,Is the firstThe historical contribution of the particular modality data,Is the degree of contribution to traversing all of the modality data,Is the historical contribution of the b-th specific modality data;
and (3) weighting and fusing the modal data according to the weight to obtain multi-modal comprehensive data, wherein the expression is:
;
Wherein, Is the moment of timeIs used for the multi-modal integrated data of the (a),Is the moment of timeIs the first of (2)The actual value of the individual modality data,Is an index of the modal data,Is the number of modality data;
Integrating the variable self-encoder and the convolutional neural network, and capturing global and local characteristics of each mode data;
Learning historical normal data by using a variable-score-based self-encoder, generating potential distribution of each mode data, encoding the mode data input in real time by using the variable-score-based self-encoder, comparing the potential distribution with the potential distribution of the historical normal data, and calculating the deviation degree;
extracting local features from the modal data by using a convolutional neural network, and detecting whether local abnormal signals exist;
Calculating the abnormal score of the current multi-mode comprehensive data through an abnormal scoring mechanism based on KL divergence, wherein the expression is as follows:
;
Wherein, Is at the momentIs used for the abnormal scoring of (a),Is the moment of timeIs used for the multi-modal integrated data of the (a),Is the moment of timeIs provided with a current distribution of multi-modal integrated data,Is the firstThe normal distribution of the integrated data calculated from the individual modality data,) Is the moment of timeIs a current distribution of the health prediction values of (a),Is the moment of timeIs a function of the health prediction value of (1),Is the firstA normal distribution of health predictors for the individual modality data,Is a time-influencing factor which is a factor of the influence of time,Is an asymmetric measure that is used to measure the difference between two probability distributions.
2. A real-time obstetrical care optimization method based on big data according to claim 1, wherein classifying the abnormal event according to the risk assessment result, generating a personalized care plan comprises the steps of:
the abnormal events are classified into low risk, medium risk and high risk according to the magnitude of the abnormal scores;
When a low risk is detected, no immediate intervention is required, providing personalized advice to the pregnant woman;
When medium risk is detected, automatically sending a notice to a doctor to provide current abnormal details, suggesting that the doctor observe and further monitor relevant physiological data through a remote monitoring platform, providing nursing guidance, pushing an abnormal report to a pregnant woman, and suggesting that the pregnant woman performs clinical examination regularly;
When the high risk abnormality is detected, the doctor is immediately notified and the pregnant woman is advised to go to the hospital immediately, the frequency of fetal heart monitoring is automatically increased, physiological signals of the fetus and the mother are tracked in real time, an alarm is sent through the emergency notification platform, and an emergency care scheme is started.
3. A real-time obstetrical care optimization method based on big data according to claim 2, wherein automatically optimizing the generated personalized care plan comprises the steps of:
periodically collecting new multimodal data and user feedback;
Evaluating the effect of the current care regimen based on the new data and user feedback;
And adding personalized suggestions according to the evaluation result, improving user experience, and forming an optimized nursing scheme.
4. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the big data based obstetric real time care optimization method of any of claims 1 to 3.
5. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the big data based obstetric real time care optimization method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411510173.8A CN119028512B (en) | 2024-10-28 | 2024-10-28 | Obstetrical real-time nursing optimization method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411510173.8A CN119028512B (en) | 2024-10-28 | 2024-10-28 | Obstetrical real-time nursing optimization method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119028512A CN119028512A (en) | 2024-11-26 |
| CN119028512B true CN119028512B (en) | 2025-02-18 |
Family
ID=93537613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411510173.8A Active CN119028512B (en) | 2024-10-28 | 2024-10-28 | Obstetrical real-time nursing optimization method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119028512B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119517316A (en) * | 2025-01-23 | 2025-02-25 | 吉林大学第一医院 | A psychological crisis early warning intervention system and method based on behavior analysis |
| CN119889727B (en) * | 2025-03-27 | 2025-07-04 | 西安医学院第二附属医院 | Obstetrical real-time nursing optimization method and system based on big data |
| CN119993437B (en) * | 2025-04-17 | 2025-11-21 | 西安医学院第二附属医院 | Delivery room and operating room nursing optimizing system based on data analysis |
| CN120260931B (en) * | 2025-06-04 | 2025-08-19 | 长春大学 | Fetal health classification method, system, device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107411736A (en) * | 2017-03-10 | 2017-12-01 | 孙彪 | Fetal ECG signal detection system |
| CN118553430A (en) * | 2024-07-30 | 2024-08-27 | 深圳大学 | Fetal future state prediction method based on multi-mode information fusion perception |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118098591A (en) * | 2024-03-08 | 2024-05-28 | 河海大学 | A treatment effect prediction system for SLE-ITP patients based on cost-sensitive neural network and variational autoencoder |
-
2024
- 2024-10-28 CN CN202411510173.8A patent/CN119028512B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107411736A (en) * | 2017-03-10 | 2017-12-01 | 孙彪 | Fetal ECG signal detection system |
| CN118553430A (en) * | 2024-07-30 | 2024-08-27 | 深圳大学 | Fetal future state prediction method based on multi-mode information fusion perception |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119028512A (en) | 2024-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119028512B (en) | Obstetrical real-time nursing optimization method based on big data | |
| Hossain et al. | A Medical Cyber-physical system for predicting maternal health in developing countries using machine learning | |
| CN116386869B (en) | Disease critical degree assessment method based on multiple variables | |
| US10912508B2 (en) | Method and system for assessing mental state | |
| US10265029B2 (en) | Methods and systems for calculating and using statistical models to predict medical events | |
| US11529105B2 (en) | Digital twin updating | |
| CN118969295B (en) | Early warning system and method for high-risk pregnant women | |
| CN119170182B (en) | Full-course follow-up management system and method for obstetrics and gynecology patients | |
| CN119442124B (en) | A method, apparatus, device, and storage medium for identifying abnormal electrocardiogram (ECG) data based on deep learning. | |
| KR102421172B1 (en) | Smart Healthcare Monitoring System and Method for Heart Disease Prediction Based On Ensemble Deep Learning and Feature Fusion | |
| CN120089386B (en) | Health degree assessment system and method for endocrine care | |
| US20210345915A1 (en) | Methods Circuits Devices Systems and Machine Executable Code for Glucose Monitoring Analysis and Remedy | |
| CN118645200A (en) | A method for spinal etiology analysis and risk prediction based on artificial intelligence modeling | |
| CN119791621B (en) | Multifunctional vital sign monitoring method and system | |
| CN118692705A (en) | Physical health status monitoring method and system based on big data | |
| CN119230104A (en) | A method for managing medical risks | |
| CN119581034A (en) | A remote monitoring and nursing early warning system based on deep learning | |
| CN113140323B (en) | Health portrait generation method, system, medium and server | |
| CN117653053A (en) | A way to predict health risks with smartwatches | |
| CN119380969B (en) | A safe diagnostic method for medical monitoring | |
| CN119385526B (en) | Intelligent diagnosis wearable device for acute myocardial infarction based on structural causal model | |
| Pugh et al. | Evaluating alarm classifiers with high-confidence data programming | |
| CN118766423A (en) | A critical care status alarm method and system based on big data monitoring | |
| CN118737459A (en) | bAVM rupture and bleeding risk prediction method, device, system and storage medium | |
| CN118352084A (en) | A method and system for predicting eclampsia in pregnant women based on data analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |