CN119132579A - An intelligent early warning system for respiratory medicine based on data fusion - Google Patents
An intelligent early warning system for respiratory medicine based on data fusion Download PDFInfo
- Publication number
- CN119132579A CN119132579A CN202411594957.3A CN202411594957A CN119132579A CN 119132579 A CN119132579 A CN 119132579A CN 202411594957 A CN202411594957 A CN 202411594957A CN 119132579 A CN119132579 A CN 119132579A
- Authority
- CN
- China
- Prior art keywords
- data
- physiological
- characteristic data
- physiological characteristic
- early warning
- 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.)
- Granted
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 47
- 230000000241 respiratory effect Effects 0.000 title claims abstract description 41
- 239000003814 drug Substances 0.000 title 1
- 230000036541 health Effects 0.000 claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000007499 fusion processing Methods 0.000 claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 29
- 239000011159 matrix material Substances 0.000 claims description 18
- 201000010099 disease Diseases 0.000 claims description 15
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 2
- 230000006403 short-term memory Effects 0.000 claims description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 8
- 229910052760 oxygen Inorganic materials 0.000 description 8
- 239000001301 oxygen Substances 0.000 description 8
- 239000008280 blood Substances 0.000 description 6
- 210000004369 blood Anatomy 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000036760 body temperature Effects 0.000 description 3
- 208000017667 Chronic Disease Diseases 0.000 description 2
- 206010035664 Pneumonia Diseases 0.000 description 2
- 208000006673 asthma Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 210000002345 respiratory system Anatomy 0.000 description 2
- 208000023504 respiratory system disease Diseases 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 208000006545 Chronic Obstructive Pulmonary Disease Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 241000135164 Timea Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000000172 allergic effect Effects 0.000 description 1
- 208000010668 atopic eczema Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000004199 lung function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- 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
-
- 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)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an intelligent early warning system for a respiratory department based on data fusion. The method comprises the steps of monitoring and collecting multi-source physiological data of a patient to obtain original physiological data, preprocessing the original physiological data to obtain preprocessed physiological data, performing intelligent fusion processing on the preprocessed physiological data to obtain comprehensive physiological characteristic data, performing anomaly detection analysis on the comprehensive physiological characteristic data to obtain an analysis result of a respiratory state, performing risk classification based on the analysis result of the respiratory state, and formulating medical advice based on the risk classification. The technical problems that the existing multisource physiological data fusion is inaccurate and the accuracy of judging the health condition of a patient is low in the implementation process of the intelligent early warning of the respiratory department of the current respiratory monitoring system are solved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent early warning system for a respiratory department based on data fusion.
Background
With the development of medical technology and the increasing attention of people to health, the application of intelligent health monitoring systems in the management of various chronic diseases, especially in the prevention and early intervention of respiratory diseases, is gradually increasing. Respiratory diseases, including Chronic Obstructive Pulmonary Disease (COPD), asthma, pneumonia, etc., are a worldwide type of disease with high morbidity and mortality, early symptoms are usually not apparent, and the disease is rapidly worsening and symptoms are rapid. Therefore, the intelligent system capable of monitoring the respiratory physiological data in real time, accurately identifying abnormal changes, rapidly early warning and providing coping advice has important significance in improving prognosis of patients and relieving medical burden. Most of the current respiratory monitoring systems rely on single or limited sensor data (such as blood oxygen monitoring, heart rate monitoring and the like), mainly pay attention to setting of static thresholds, are difficult to adapt to individual differences and dynamic physiological changes, and the traditional single threshold setting method often causes false alarm and false alarm, which is not beneficial to long-term monitoring and management of chronic diseases.
In summary, in the implementation process of the intelligent early warning of the respiratory department, the technology has the technical problems that the fusion of the multisource physiological data is inaccurate and the judgment accuracy of the health condition of the patient is low.
Disclosure of Invention
The invention provides a respiratory department intelligent early warning system based on data fusion, which aims to solve the technical problems that the current respiratory monitoring system is inaccurate in fusion of multisource physiological data and low in judgment accuracy on the health condition of a patient in the implementation process of respiratory department intelligent early warning.
The invention discloses a respiratory department intelligent early warning system based on data fusion, which specifically comprises the following technical scheme:
a respiratory department intelligent early warning method based on data fusion comprises the following steps:
s1, monitoring and collecting multi-source physiological data of a patient to obtain original physiological data, preprocessing the original physiological data to obtain preprocessed physiological data, and performing intelligent fusion processing on the preprocessed physiological data to obtain comprehensive physiological characteristic data;
s2, performing anomaly detection analysis on the comprehensive physiological characteristic data to obtain an analysis result of the respiratory state, performing risk classification based on the analysis result of the respiratory state, and formulating medical advice based on the risk classification.
Preferably, the S1 specifically includes:
and carrying out intelligent fusion processing on the preprocessed physiological data by a data fusion algorithm based on multistage dynamic weighting and hierarchical feature extraction to obtain comprehensive physiological feature data, wherein the preprocessed physiological data is a data set containing time sequence attributes.
Preferably, the S1 specifically includes:
In the implementation process of a data fusion algorithm based on multistage dynamic weighting and hierarchical feature extraction, feature extraction is carried out on the preprocessed physiological data to obtain physiological feature data, and a time sequence correlation coefficient is introduced, wherein the formula is as follows:
,
Wherein, Is a time-series correlation coefficient; Is the length of the entire time series; Is the first Individual physiological characteristic data are inA value of time of day; Is the first A mean value of the individual physiological characteristic data over a time sequence; Is the first Individual physiological characteristic data are inA value of time of day; Is the first A mean value of the individual physiological characteristic data over a time sequence;
and obtaining an initial weighting weight of the physiological characteristic data based on the time sequence correlation coefficient and the change rate of the physiological characteristic data, and obtaining an initial weighting weight matrix based on the initial weighting weight of the physiological characteristic data.
Preferably, the S1 specifically includes:
Performing multi-feature weighted fusion processing on the physiological feature data based on the initial weighted weight matrix to obtain comprehensive physiological feature data Any one element of (3)The calculation formula of (2) is as follows:
,
Wherein, Is the firstInitial weighting weights of the individual physiological characteristic data; Is the first Self-adaptive coefficients of the individual physiological characteristic data; Is the first Individual physiological characteristic data; Is the first A periodic parameter of the individual physiological characteristic data;
Introducing a feature function which dynamically changes along with time, and expanding the comprehensive physiological feature data into time sequence dynamic data.
Preferably, the S1 specifically includes:
And dynamically adjusting the initial weighting weight of the physiological characteristic data based on the correction coefficient of the physiological characteristic data to obtain the adjusted weight of the physiological characteristic data.
Preferably, the S1 specifically includes:
Based on the current comprehensive physiological characteristic data, introducing a historical data memory matrix, and performing self-adaptive optimization on the weight adjusted by each physiological characteristic data to obtain the final optimized weight, wherein the self-adaptive optimization formula is as follows:
,
Wherein, To the final optimized firstWeights of the individual physiological characteristic data represent the final optimized weights; Is the first The weight of the physiological characteristic data after adjustment; Is the learning rate; is a memory window period; Is the first Individual physiological characteristic data are inA value of time of day; Is the comprehensive physiological characteristic data A value of time of day;
and recalculating the comprehensive physiological characteristic data based on the finally optimized weight.
Preferably, the S2 specifically includes:
Performing feature processing and anomaly detection analysis on the comprehensive physiological feature data through a combined model based on a convolutional neural network and a long-term and short-term memory network to obtain health risk scores; based on the health risk score, a personalized self-adaptive threshold generation algorithm is introduced, and a personalized dynamic threshold is dynamically generated.
Preferably, the S2 specifically includes:
In the implementation process of the personalized self-adaptive threshold generation algorithm, historical health risk scores of patients and individual characteristic data are introduced, a basic threshold is calculated, the basic threshold is dynamically adjusted based on the basic threshold by combining the current health risk scores of the patients, and a personalized dynamic threshold is generated, wherein the dynamic adjustment formula is as follows:
,
Wherein, Is a personalized dynamic threshold; Is a base threshold; Is the influence coefficient of control self-adaption; is the total number of disease history in the individual characteristic data; Is the first Weight coefficients of individual disease-related physiological characteristic data; Is the first Physiological characteristic values associated with individual diseases; Is the current time Is a health risk score for (1); Is a smoothing factor.
Preferably, the S2 specifically includes:
The health risk score is compared with the personalized dynamic threshold value to obtain an analysis result of the breathing state, when the health risk score is smaller than the personalized dynamic threshold value, the patient is in a normal breathing state, when the health risk score is larger than or equal to the personalized dynamic threshold value, the analysis result of the breathing state is abnormal, when the analysis result of the breathing state is abnormal, risk classification is carried out by calculating the difference value between the current health risk score of the patient and the personalized dynamic threshold value, and hierarchical medical advice is generated based on the risk classification.
A respiratory department intelligent early warning system based on data fusion comprises the following parts:
The system comprises a data acquisition module, a data preprocessing module, a multi-source data fusion module, an abnormality detection and judgment module and an early warning and suggestion module;
The data acquisition module monitors and acquires multi-source physiological data of a patient to obtain original physiological data;
The data preprocessing module is used for preprocessing the original physiological data to obtain preprocessed physiological data, and sending the preprocessed physiological data to the multi-source data fusion module;
The multisource data fusion module is used for carrying out intelligent fusion processing on the preprocessed physiological data to obtain comprehensive physiological characteristic data;
the abnormality detection and judgment module is used for carrying out abnormality detection analysis on the comprehensive physiological characteristic data to obtain an analysis result of the breathing state;
the early warning and suggestion module is used for carrying out risk classification based on the analysis result of the breathing state and making medical suggestions based on the risk classification.
The technical scheme of the invention has the beneficial effects that:
1. The invention utilizes preprocessing technologies such as data cleaning, data denoising, data standardization, abnormal value monitoring and rejecting and the like, and realizes intelligent fusion of multi-source data based on a data fusion algorithm of multistage dynamic weighting and hierarchical feature extraction. By introducing advanced methods such as time sequence correlation, frequency fluctuation analysis and the like, comprehensive physiological characteristic data are generated, so that the reliability and consistency of the physiological characteristic data are ensured, and a high-precision physiological data basis is provided for abnormality detection.
2. A personalized self-adaptive threshold generation algorithm is introduced, and a personalized dynamic threshold adapting to individual differences is generated according to the historical health risk scores and the individual characteristic data of the patient, so that the personalized adaptation capacity of the respiratory intelligent early warning system is enhanced, the early warning result is more targeted, and the false alarm and missing alarm phenomena are effectively reduced.
Drawings
FIG. 1 is a diagram of a respiratory intelligent early warning system based on data fusion according to the invention;
fig. 2 is a flow chart of a respiratory intelligent early warning method based on data fusion.
Detailed Description
In order to further illustrate the technical means and effects adopted by the present invention to achieve the preset purpose, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scheme of the respiratory department intelligent early warning system based on data fusion provided by the invention is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a structural diagram of an intelligent early warning system for respiratory department based on data fusion according to an embodiment of the present invention is shown, where the system includes the following parts:
The system comprises a data acquisition module, a data preprocessing module, a multi-source data fusion module, an abnormality detection and judgment module and an early warning and suggestion module;
The data acquisition module monitors and acquires multi-source physiological data of a patient to obtain original physiological data;
The original physiological data comprise parameters such as respiration rate, blood oxygen saturation, heart rate, body temperature and the like;
The data preprocessing module is used for preprocessing the original physiological data to obtain preprocessed physiological data, and sending the preprocessed physiological data to the multi-source data fusion module;
The multisource data fusion module is used for carrying out intelligent fusion processing on the preprocessed physiological data to obtain comprehensive physiological characteristic data;
the abnormality detection and judgment module is used for carrying out abnormality detection analysis on the comprehensive physiological characteristic data to obtain an analysis result of the breathing state;
and the early warning and suggestion module is used for carrying out risk classification based on the analysis result of the breathing state, and making medical suggestions based on the risk classification so as to realize intelligent early warning of the respiratory department based on data fusion.
Referring to fig. 2, a flowchart of a respiratory intelligent early warning method based on data fusion according to an embodiment of the present invention is shown, where the method includes the following steps:
s1, monitoring and collecting multi-source physiological data of a patient to obtain original physiological data, preprocessing the original physiological data to obtain preprocessed physiological data, and performing intelligent fusion processing on the preprocessed physiological data to obtain comprehensive physiological characteristic data;
Based on the health requirement of a patient, a plurality of sensors are selected by using an expert experience method to monitor real-time physiological parameters to obtain original physiological data, wherein the sensors comprise a respiration sensor, a blood oxygen sensor, a heart rate sensor, a body temperature sensor and the like, and the original physiological data comprise parameters such as respiration rate, blood oxygen saturation, heart rate, body temperature and the like.
Further, the original physiological data is subjected to periodic preprocessing (such as data cleaning, data denoising, data standardization, outlier detection and rejection, and data format conversion) to obtain preprocessed physiological data, wherein the preprocessing adopts the technology which is well known in the art and is not described herein.
Wherein, for a certain time (recordThe time series length) of the time series attribute, and the obtained preprocessed physiological data is also a data set containing the time series attribute.
And the data fusion algorithm based on the multi-stage dynamic weighting and layered feature extraction gradually forms comprehensive physiological feature data with strong comprehensiveness and high precision by introducing multi-stage processing of self-adaptive weight, time sequence correlation and frequency fluctuation analysis. The specific implementation process is as follows:
Firstly, carrying out feature extraction on the preprocessed physiological data by utilizing the existing feature engineering technology to obtain physiological feature data;
Further, introducing a time sequence correlation coefficient The time sequence correlation among the physiological characteristic data is represented, and the calculation formula is as follows:
,
Wherein, Is a time sequence correlation coefficient representing the firstPhysiological characteristic data and the firstA degree of temporal correlation between the physiological characteristic data (e.g., respiration rate and blood oxygen saturation); Is the number of time points, i.e. the length of the entire time sequence; Is the first Individual physiological characteristic data are inA value of time of day; Is the first A mean value of the individual physiological characteristic data over a time sequence; Is the first Individual physiological characteristic data are inA value of time of day; Is the first The mean of the individual physiological characteristic data over time. The calculation of the time sequence correlation coefficient can ensure that the time sequence correlation among physiological characteristic data can be fully considered in the subsequent fusion process;
further, an initial weighting weight of the physiological characteristic data is formed by utilizing the time sequence correlation coefficient and the change rate of the physiological characteristic data, wherein a calculation formula of the initial weighting weight of the physiological characteristic data is as follows:
,
Wherein, Is the firstInitial weighting weights of the individual physiological characteristic data; Is the first The sum of all time-series correlation coefficients of the individual physiological characteristic data, i.e.;Is the firstThe change rate of the individual physiological characteristic data reflects the change degree of each physiological characteristic data in a specific time; Is the first Personal physiological characteristic dataStandard deviation of (1) for describing the firstThe magnitude of the volatility of the individual physiological characteristic data; Is the total number of physiological characteristic data; Is the first The sum of all time-series correlation coefficients of the individual physiological characteristic data, i.e.;Is the firstThe rate of change of the individual physiological characteristic data; Is the first Personal physiological characteristic dataFurther, obtaining an initial weighting weight matrix based on the initial weighting weights of the physiological characteristic data;Is the firstInitial weighting of the individual physiological characteristic data.
Further, the physiological characteristic data is subjected to multi-characteristic weighted fusion processing to form comprehensive physiological characteristic data, and the comprehensive physiological characteristic data is based on an initial weighted weight matrixThe physiological characteristic data are overlapped and nonlinear combined to generate comprehensive physiological characteristic dataAny one element of (3)The calculation formula of (2) is as follows:
,
Wherein, Is the firstThe self-adaptive coefficient of each physiological characteristic data is used for controlling the influence of each physiological characteristic data in nonlinear transformation; Is the first Individual physiological characteristic data; Is the first A mean value of the individual physiological characteristic data over a time sequence; Is the first The processing ensures that different physiological characteristic data can realize complex fusion on a uniform scale, thereby obtaining comprehensive physiological characteristic data with stronger comprehensiveness。
In the process of obtaining comprehensive physiological characteristic dataThen, in order to enhance the time sequence expressive property of the comprehensive physiological characteristic data, a characteristic function which dynamically changes along with time is further generated so as to endow the comprehensive physiological characteristic data with higher time sensitivity, namely, the comprehensive physiological characteristic data is expanded into time sequence dynamic data. Characteristic functionThe specific formula of (2) is as follows:
,
Wherein, Representing an adaptive frequency for controlling a dynamic change speed; Is a time variable and is used for reflecting the time sensitivity of the comprehensive physiological characteristic data; Represent the first Individual physiological characteristic data; And the sum of absolute values of the physiological characteristic data is used for controlling the amplitude of the dynamic gain. The feature function gives comprehensive physiological feature data With time-varying characteristics, to integrate physiological characteristic dataCan reflect the physiological change of the patient in real time.
In order to further improve the self-adaptive capacity of physiological characteristic data in the long-time monitoring process, the initial weighting weights of different physiological characteristic data are dynamically adjusted, and the influence of each physiological characteristic data is dynamically corrected by introducing a historical data memory matrix, so that the specific implementation process is as follows:
first, a correction coefficient is calculated for each physiological characteristic data To reflect the difference between the physiological characteristic data and the integrated physiological characteristic data, the formula is as follows:
,
Wherein, Is the firstThe correction coefficient of the individual physiological characteristic data reflects the deviation of the physiological characteristic data and the comprehensive physiological characteristic data; To monitor the total duration; representing integrated physiological characteristic data in A value of time of day; Represent the first Individual physiological characteristic data are inA value of time of day; Representing integrated physiological characteristic data Standard deviation of (2). The correction coefficient of the physiological characteristic data forms self-adaptive feedback information according to the deviation degree between the physiological characteristic data and the comprehensive physiological characteristic data so as to adjust an initial weighting matrix in a subsequent step;
Further, the initial weighting weight of the physiological characteristic data is dynamically adjusted based on the correction coefficient of the physiological characteristic data, so as to obtain the adjusted weight of the physiological characteristic data, wherein the specific formula is as follows:
,
Wherein, Is the firstThe weight of the physiological characteristic data after adjustment; Is the first Correction coefficients of the individual physiological characteristic data; Is the first Correction coefficients of the individual physiological characteristic data; For adaptively adjusting the index for controlling the update rate; Is the first Initial weighting of the individual physiological characteristic data. Based on the adjusted weights of the physiological characteristic data, the constructed adjusted weight matrixIs used for recalculating the comprehensive physiological characteristic data so that the stability and accuracy of the comprehensive physiological characteristic data are further improved, whereinRepresent the firstAnd the weight of the physiological characteristic data after adjustment.
Furthermore, in order to improve the accuracy of the weight after the physiological characteristic data is adjusted, a historical data memory matrix is introducedFor recording the lapse of a certain period of timeThe comprehensive physiological characteristic data and weight adjustment conditions in the system provide reference basis for self-adaptive learning optimization, wherein the historical data are from an existing database. Historical data memory matrixRecording time periodIntegrated physiological characteristic data withinAnd the weight change over each time step, the formula is as follows:
,
Wherein, For synthesizing physiological characteristic dataA value of time of day; for synthesizing physiological characteristic data A value of time of day; Is that The weight matrix after the adjustment of the moment; Is that The weight matrix after the adjustment of the moment; And the process of intelligent fusion processing of the current physiological characteristic data is optimized for memorizing the window period and is used for referencing the historical physiological characteristic data in the subsequent optimization. Through the history data memory matrix, the history data can be invoked to further optimize the accuracy of intelligent fusion of the current physiological characteristic data.
Memory matrix based on historical dataAnd current integrated physiological characteristic dataPerforming self-adaptive optimization on the weights after the adjustment of the physiological characteristic data to obtain final optimized weights, wherein the self-adaptive optimization formula is as follows:
,
Wherein, To the final optimized firstWeights of individual physiological characteristic data, i.e. the final optimized weights, by applying to the firstWeights after adjustment of individual physiological characteristic dataPerforming self-adaptive optimization to obtain the self-adaptive optimization; For learning rate, for controlling the adjustment rate; Is the first Periodic parameters of the physiological characteristic data for controlling sinusoidal fluctuations; Is the first Personal physiological characteristic dataA value of time of day; Is the comprehensive physiological characteristic data A value of the time of day. The self-adaptive optimization formula takes the difference between the current comprehensive physiological characteristic data and the historical data in the historical data memory matrix as feedback information, and automatically corrects the weight of the physiological characteristic data, so that each physiological characteristic data can be better adapted to the individual physiological change of a patient. And in a certain period, the finally optimized weight is used for recalculating the comprehensive physiological characteristic data, so that the stability and accuracy of the comprehensive physiological characteristic data are further improved.
S2, performing anomaly detection analysis on the comprehensive physiological characteristic data to obtain an analysis result of the respiratory state, performing risk classification based on the analysis result of the respiratory state, and formulating medical advice based on the risk classification.
The method comprises the steps of adopting the existing combined model based on the convolutional neural network and the long-period memory network to the comprehensive physiological characteristic data so as to realize characteristic processing and abnormality detection analysis, carrying out characteristic optimization on the comprehensive physiological characteristic data through the convolutional neural network to obtain representative physiological characteristic data, inputting the representative physiological characteristic data into the long-period memory network as output of the convolutional neural network, processing time series characteristics of the representative physiological characteristic data through the long-period memory network, capturing long-term dependence of the physiological characteristic data, obtaining health risk score, and comparing the health risk score with a personalized dynamic threshold to obtain an analysis result of a breathing state.
A personalized self-adaptive threshold generation algorithm is introduced, and a personalized dynamic threshold is dynamically generated based on health risk scores, historical health risk scores of patients and individual characteristic data (such as age, gender and disease history), wherein the specific implementation process is as follows:
Calculating a base threshold based on patient historical health risk scores and individual characteristic data (e.g., age, gender, disease history, etc.) :
,
Wherein, The basic threshold value is calculated according to the historical health risk score of the patient and the individual characteristic data and is used as a basis for generating the personalized dynamic threshold value; is the total number of patient historical health risk scores; Is the patient of Secondary historical health risk scores; is the average of the patient's historical health risk scores, used to measure the average health risk level; Is the standard deviation of the patient's historical health risk score, used to measure the degree of discretion of the patient's historical health risk score; Is an age factor; is an adjustment factor of the individual characteristic data and is used for controlling the influence of the individual characteristic data on the basic threshold value; is an adjustment factor for avoiding excessive impact of an age factor on a base threshold; is a sex-affecting factor for adjusting the influence of sex on the base threshold, Is sex, 1 is taken to mean male, 0 is taken to mean female.
Further, on the basis of the basic threshold, the basic threshold is dynamically adjusted by combining the current health risk score of the patient and the disease history in the individual characteristic data to generate a threshold which is adaptive to the current state of the patient, namely a personalized dynamic threshold, wherein the dynamic adjustment formula is as follows:
,
Wherein, Is a personalized dynamic threshold; is a control adaptive influence coefficient for adaptively adjusting the influence of the current health risk score on the personalized dynamic threshold; Is the total number of disease history; Is the first A weight coefficient of the individual disease-related physiological characteristic data for characterizing the weight of a particular disease in the health risk score; Is the first Individual disease-related physiological characteristic values, individual characteristic data derived from a patient (e.g., asthmaOtherwise);Is the current timeA health risk score representing a health status indicator measured in real-time; Is a smoothing factor for preventing health risk scoring The mutation causes the personalized dynamic threshold to fluctuate drastically.
Further, comparing the health risk score with the personalized dynamic threshold value to obtain an analysis result of the breathing state, wherein when the health risk score is larger than or equal to the personalized dynamic threshold value, the analysis result of the breathing state is abnormal, which indicates that the breathing state of the patient is abnormal, and when the health risk score is smaller than the personalized dynamic threshold value, which indicates that the patient is in a normal breathing state. When the analysis result of the breathing state is abnormal, generating a layered medical suggestion according to the current health risk score and the personalized dynamic threshold value of the patient, and according to the difference value of the health risk score and the personalized dynamic threshold valueThe risk classification is carried out, the severity degree of the abnormality is determined, and the risk classification is calculated as follows:
,
If it is Low risk ifRisk of apoplexy, ifThen there is a high risk.、Is a grading threshold set according to expert experience method and is used for controlling risk grading.
According to the risk level, making medical advice:
the low risk is that the patient is recommended to monitor and adjust the breathing state, so as to improve the rest and avoid excessive fatigue, and the daily breathing training is recommended to be added so as to enhance the endurance of the breathing system;
the risk of the patient is recommended to visit a doctor or to communicate with medical staff to check whether the respiratory tract is infected or not, oxygen can be considered for assisting the respiration, and possible allergic sources or respiratory tract stimulators are avoided;
high risk of suggesting immediate medical visits and receiving professional medical interventions, possibly with oxygen support or ventilator assistance, recommending further blood oxygen tests, lung function examinations, and considering causes of pneumonia, asthma attacks, etc. based on the patient's medical history.
In conclusion, the respiratory department intelligent early warning system based on data fusion is completed.
The sequence of the embodiments of the invention is merely for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing embodiments are merely for illustrating the technical solution of the present invention, but not for limiting the same, and although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solution described in the foregoing embodiments may be modified or substituted for some of the technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solution of the embodiments of the present invention and are intended to be included in the scope of the present invention.
Claims (10)
1. The respiratory department intelligent early warning method based on data fusion is characterized by comprising the following steps of:
s1, monitoring and collecting multi-source physiological data of a patient to obtain original physiological data, preprocessing the original physiological data to obtain preprocessed physiological data, and performing intelligent fusion processing on the preprocessed physiological data to obtain comprehensive physiological characteristic data;
s2, performing anomaly detection analysis on the comprehensive physiological characteristic data to obtain an analysis result of the respiratory state, performing risk classification based on the analysis result of the respiratory state, and formulating medical advice based on the risk classification.
2. The respiratory department intelligent early warning method based on data fusion according to claim 1, wherein the step S1 specifically comprises:
and carrying out intelligent fusion processing on the preprocessed physiological data by a data fusion algorithm based on multistage dynamic weighting and hierarchical feature extraction to obtain comprehensive physiological feature data, wherein the preprocessed physiological data is a data set containing time sequence attributes.
3. The respiratory department intelligent early warning method based on data fusion according to claim 2, wherein the step S1 specifically comprises:
In the implementation process of a data fusion algorithm based on multistage dynamic weighting and hierarchical feature extraction, feature extraction is carried out on the preprocessed physiological data to obtain physiological feature data, and a time sequence correlation coefficient is introduced, wherein the formula is as follows:
,
Wherein, Is a time-series correlation coefficient; Is the length of the entire time series; Is the first Individual physiological characteristic data are inA value of time of day; Is the first A mean value of the individual physiological characteristic data over a time sequence; Is the first Individual physiological characteristic data are inA value of time of day; Is the first A mean value of the individual physiological characteristic data over a time sequence;
and obtaining an initial weighting weight of the physiological characteristic data based on the time sequence correlation coefficient and the change rate of the physiological characteristic data, and obtaining an initial weighting weight matrix based on the initial weighting weight of the physiological characteristic data.
4. The respiratory department intelligent early warning method based on data fusion according to claim 3, wherein the step S1 specifically comprises:
Performing multi-feature weighted fusion processing on the physiological feature data based on the initial weighted weight matrix to obtain comprehensive physiological feature data Any one element of (3)The calculation formula of (2) is as follows:
,
Wherein, Is the firstInitial weighting weights of the individual physiological characteristic data; Is the first Self-adaptive coefficients of the individual physiological characteristic data; Is the first Individual physiological characteristic data; Is the first A periodic parameter of the individual physiological characteristic data;
Introducing a feature function which dynamically changes along with time, and expanding the comprehensive physiological feature data into time sequence dynamic data.
5. The respiratory intelligent early warning method based on data fusion according to claim 4, wherein the step S1 specifically comprises:
And dynamically adjusting the initial weighting weight of the physiological characteristic data based on the correction coefficient of the physiological characteristic data to obtain the adjusted weight of the physiological characteristic data.
6. The respiratory intelligent early warning method based on data fusion according to claim 5, wherein the step S1 specifically comprises:
Based on the current comprehensive physiological characteristic data, introducing a historical data memory matrix, and performing self-adaptive optimization on the weight adjusted by each physiological characteristic data to obtain the final optimized weight, wherein the self-adaptive optimization formula is as follows:
,
Wherein, To the final optimized firstWeights of the individual physiological characteristic data represent the final optimized weights; Is the first The weight of the physiological characteristic data after adjustment; Is the learning rate; is a memory window period; Is the first Individual physiological characteristic data are inA value of time of day; Is the comprehensive physiological characteristic data A value of time of day;
and recalculating the comprehensive physiological characteristic data based on the finally optimized weight.
7. The respiratory department intelligent early warning method based on data fusion according to claim 1, wherein the step S2 specifically comprises:
Performing feature processing and anomaly detection analysis on the comprehensive physiological feature data through a combined model based on a convolutional neural network and a long-term and short-term memory network to obtain health risk scores; based on the health risk score, a personalized self-adaptive threshold generation algorithm is introduced, and a personalized dynamic threshold is dynamically generated.
8. The respiratory intelligent early warning method based on data fusion according to claim 7, wherein the step S2 specifically comprises:
In the implementation process of the personalized self-adaptive threshold generation algorithm, historical health risk scores of patients and individual characteristic data are introduced, a basic threshold is calculated, the basic threshold is dynamically adjusted based on the basic threshold by combining the current health risk scores of the patients, and a personalized dynamic threshold is generated, wherein the dynamic adjustment formula is as follows:
,
Wherein, Is a personalized dynamic threshold; Is a base threshold; Is the influence coefficient of control self-adaption; is the total number of disease history in the individual characteristic data; Is the first Weight coefficients of individual disease-related physiological characteristic data; Is the first Physiological characteristic values associated with individual diseases; Is the current time Is a health risk score for (1); Is a smoothing factor.
9. The respiratory intelligent early warning method based on data fusion according to claim 8, wherein the step S2 specifically comprises:
The health risk score is compared with the personalized dynamic threshold value to obtain an analysis result of the breathing state, when the health risk score is smaller than the personalized dynamic threshold value, the patient is in a normal breathing state, when the health risk score is larger than or equal to the personalized dynamic threshold value, the analysis result of the breathing state is abnormal, when the analysis result of the breathing state is abnormal, risk classification is carried out by calculating the difference value between the current health risk score of the patient and the personalized dynamic threshold value, and hierarchical medical advice is generated based on the risk classification.
10. The respiratory department intelligent early warning system based on data fusion is applied to the respiratory department intelligent early warning method based on data fusion as claimed in claim 1, and is characterized by comprising the following parts:
The system comprises a data acquisition module, a data preprocessing module, a multi-source data fusion module, an abnormality detection and judgment module and an early warning and suggestion module;
The data acquisition module monitors and acquires multi-source physiological data of a patient to obtain original physiological data;
The data preprocessing module is used for preprocessing the original physiological data to obtain preprocessed physiological data, and sending the preprocessed physiological data to the multi-source data fusion module;
The multisource data fusion module is used for carrying out intelligent fusion processing on the preprocessed physiological data to obtain comprehensive physiological characteristic data;
the abnormality detection and judgment module is used for carrying out abnormality detection analysis on the comprehensive physiological characteristic data to obtain an analysis result of the breathing state;
the early warning and suggestion module is used for carrying out risk classification based on the analysis result of the breathing state and making medical suggestions based on the risk classification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411594957.3A CN119132579B (en) | 2024-11-11 | 2024-11-11 | Department of respiration intelligent early warning system based on data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411594957.3A CN119132579B (en) | 2024-11-11 | 2024-11-11 | Department of respiration intelligent early warning system based on data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119132579A true CN119132579A (en) | 2024-12-13 |
| CN119132579B CN119132579B (en) | 2025-04-22 |
Family
ID=93748566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411594957.3A Active CN119132579B (en) | 2024-11-11 | 2024-11-11 | Department of respiration intelligent early warning system based on data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119132579B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119418953A (en) * | 2025-01-08 | 2025-02-11 | 广州源古纪科技有限公司 | A respiratory monitoring and analysis method and system based on multiple sensors |
| CN119517384A (en) * | 2025-01-21 | 2025-02-25 | 吉林大学 | Intelligent diagnosis assistance system and method for children's respiratory diseases |
| CN119694572A (en) * | 2024-12-17 | 2025-03-25 | 北京大学人民医院 | A risk prediction and management system for incontinence-related dermatitis based on data analysis |
| CN119742055A (en) * | 2025-02-28 | 2025-04-01 | 苏州大学附属儿童医院 | Intelligent monitoring method and system for children's bronchial asthma symptoms based on multi-source data |
| CN119811619A (en) * | 2025-03-11 | 2025-04-11 | 湖南艾瑞特生物医疗科技有限公司 | A personalized health monitoring method based on multi-instrument data fusion |
| CN119818052A (en) * | 2025-01-09 | 2025-04-15 | 中国人民解放军总医院第一医学中心 | Method for predicting risk of apnea syndrome attack mode |
| CN119903463A (en) * | 2025-03-28 | 2025-04-29 | 北京紫云智能科技有限公司 | A method for constructing a comprehensive intelligent early warning system for trauma patients |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021184641A1 (en) * | 2020-03-17 | 2021-09-23 | 平安国际智慧城市科技股份有限公司 | Intelligent sleep staging method and apparatus, electronic device, and computer readable storage medium |
| WO2022141118A1 (en) * | 2020-12-29 | 2022-07-07 | 深圳迈瑞生物医疗电子股份有限公司 | Respiration information obtaining method, apparatus, monitor, and computer readable storage medium |
| CN115376638A (en) * | 2022-08-22 | 2022-11-22 | 中国电子科技集团公司第二十八研究所 | Physiological characteristic data analysis method based on multi-source health perception data fusion |
| CN117612725A (en) * | 2024-01-23 | 2024-02-27 | 南通大学附属医院 | A ventilator alarm management method and system for intensive care units |
| CN117630758A (en) * | 2024-01-24 | 2024-03-01 | 国能大渡河检修安装有限公司 | Method and system for monitoring health state of power station transformer |
| CN117672532A (en) * | 2024-01-31 | 2024-03-08 | 吉林大学 | Hospitalized patient nursing risk assessment early warning monitoring system and method |
| CN117854739A (en) * | 2024-03-05 | 2024-04-09 | 天津市第二人民医院（天津市传染病医院） | Intelligent internal medicine nursing monitoring system |
| CN118230936A (en) * | 2024-03-05 | 2024-06-21 | 中南大学 | A health diagnosis system integrated with intelligent medical equipment |
| CN118692705A (en) * | 2024-08-23 | 2024-09-24 | 义乌市江东街道社区卫生服务中心 | Physical health status monitoring method and system based on big data |
| US20240321451A1 (en) * | 2023-03-20 | 2024-09-26 | Bruce Wayne FallHowe | System And Method For Diagnostic Coding |
-
2024
- 2024-11-11 CN CN202411594957.3A patent/CN119132579B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021184641A1 (en) * | 2020-03-17 | 2021-09-23 | 平安国际智慧城市科技股份有限公司 | Intelligent sleep staging method and apparatus, electronic device, and computer readable storage medium |
| WO2022141118A1 (en) * | 2020-12-29 | 2022-07-07 | 深圳迈瑞生物医疗电子股份有限公司 | Respiration information obtaining method, apparatus, monitor, and computer readable storage medium |
| CN115376638A (en) * | 2022-08-22 | 2022-11-22 | 中国电子科技集团公司第二十八研究所 | Physiological characteristic data analysis method based on multi-source health perception data fusion |
| US20240321451A1 (en) * | 2023-03-20 | 2024-09-26 | Bruce Wayne FallHowe | System And Method For Diagnostic Coding |
| CN117612725A (en) * | 2024-01-23 | 2024-02-27 | 南通大学附属医院 | A ventilator alarm management method and system for intensive care units |
| CN117630758A (en) * | 2024-01-24 | 2024-03-01 | 国能大渡河检修安装有限公司 | Method and system for monitoring health state of power station transformer |
| CN117672532A (en) * | 2024-01-31 | 2024-03-08 | 吉林大学 | Hospitalized patient nursing risk assessment early warning monitoring system and method |
| CN117854739A (en) * | 2024-03-05 | 2024-04-09 | 天津市第二人民医院（天津市传染病医院） | Intelligent internal medicine nursing monitoring system |
| CN118230936A (en) * | 2024-03-05 | 2024-06-21 | 中南大学 | A health diagnosis system integrated with intelligent medical equipment |
| CN118692705A (en) * | 2024-08-23 | 2024-09-24 | 义乌市江东街道社区卫生服务中心 | Physical health status monitoring method and system based on big data |
Non-Patent Citations (2)
| Title |
|---|
| WALEED SALIH ET AL: "Merging Two Models of One-Dimensional Convolutional Neural Networks to Improve the Differential Diagnosis between Acute Asthma and Bronchitis in Preschool Children", DIAGNOSTICS, vol. 14, 12 March 2024 (2024-03-12), pages 1 - 15 * |
| 荆斌;张鹏;李巍;查玉华;周双勤;尚学义;: "基于智能算法睡眠呼吸暂停监测系统设计", 中国医学装备, no. 09, 30 September 2011 (2011-09-30), pages 21 - 24 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119694572A (en) * | 2024-12-17 | 2025-03-25 | 北京大学人民医院 | A risk prediction and management system for incontinence-related dermatitis based on data analysis |
| CN119418953A (en) * | 2025-01-08 | 2025-02-11 | 广州源古纪科技有限公司 | A respiratory monitoring and analysis method and system based on multiple sensors |
| CN119818052A (en) * | 2025-01-09 | 2025-04-15 | 中国人民解放军总医院第一医学中心 | Method for predicting risk of apnea syndrome attack mode |
| CN119517384A (en) * | 2025-01-21 | 2025-02-25 | 吉林大学 | Intelligent diagnosis assistance system and method for children's respiratory diseases |
| CN119742055A (en) * | 2025-02-28 | 2025-04-01 | 苏州大学附属儿童医院 | Intelligent monitoring method and system for children's bronchial asthma symptoms based on multi-source data |
| CN119742055B (en) * | 2025-02-28 | 2025-05-13 | 苏州大学附属儿童医院 | Childhood bronchial asthma symptom intelligent monitoring method and system based on multi-source data |
| CN119811619A (en) * | 2025-03-11 | 2025-04-11 | 湖南艾瑞特生物医疗科技有限公司 | A personalized health monitoring method based on multi-instrument data fusion |
| CN119903463A (en) * | 2025-03-28 | 2025-04-29 | 北京紫云智能科技有限公司 | A method for constructing a comprehensive intelligent early warning system for trauma patients |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119132579B (en) | 2025-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119132579B (en) | Department of respiration intelligent early warning system based on data fusion | |
| JP5388580B2 (en) | Residue-based management of human health | |
| Mohammed et al. | A novel predictive analysis to identify the weather impacts for congenital heart disease using reinforcement learning | |
| WO2018090304A1 (en) | Mental stress evaluation method and device | |
| WO2022093707A1 (en) | Cardiopulmonary health monitoring using thermal camera and audio sensor | |
| JP2013099507A (en) | Sleep assessment system and sleep assessment apparatus | |
| CN116019429B (en) | Health monitoring method, device, equipment and storage medium based on physiological index | |
| CN118072971A (en) | Smart elderly care service management method based on deep information integration | |
| CN118675741A (en) | Sensor monitoring-based geriatric surgery intelligent nursing system and method | |
| CN109935327B (en) | Cardiovascular risk layering evaluation method for hypertension patient based on intelligent decision support | |
| CN118379173B (en) | Comprehensive safety monitoring method based on digital aged care | |
| CN113744865A (en) | Regression analysis-based pressure damage risk prediction model correction method | |
| CN118571459A (en) | A blood pressure management system and analysis method for disabled elderly people | |
| WO2022183999A1 (en) | Evaluation of sleep data | |
| CN113936767A (en) | Health management method for asthma patient | |
| CN120145171B (en) | A consultation guidance system based on interactive data collection | |
| CN119896464B (en) | A heart rate detection method based on wearable sensor | |
| CN118486453B (en) | Disease early warning system based on artificial intelligence | |
| EP4390958A1 (en) | A computer implemented method for adaptive physiology-based monitoring of a subject | |
| CN118983097A (en) | A physiological parameter dynamic early warning method and device | |
| CN120413060A (en) | A respiratory disease risk assessment system and method | |
| CN119480157A (en) | Otolaryngology symptom monitoring method and system based on multimodal data fusion | |
| CN120413012A (en) | Chronic disease health monitoring method and system based on artificial intelligence | |
| CN120108627A (en) | A nursing plan auxiliary selection method and system for orthopedic patients | |
| CN119924842A (en) | A dynamic electrocardiogram early warning system based on artificial intelligence |
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 |