Individual differentiation discharge monitoring method and system for atrial fibrillation patients
By analyzing heart rate variability signals, dietary patterns, exercise data and spatial distribution information, an individualized atrial fibrillation analysis model was established, which solved the problem of failure to fully consider life factors in the existing technology, and improved the accuracy of discharge monitoring of patients with atrial fibrillation. Sex and personalization reduce recurrence rates.
Patent Information
- Application Number
- CN202411045955.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing monitoring methods for discharge of patients with atrial fibrillation do not fully consider the patient's living conditions, such as dietary and environmental factors, resulting in high recurrence rates and poor monitoring effects.
By acquiring heart rate variability signals, analyzing dietary patterns and exercise data, constructing diet-atrial fibrillation and exercise-atrial fibrillation impact parameters, and combining spatial distribution information to construct environmental-atrial fibrillation impact parameters, establishing an individualized atrial fibrillation analysis model, real-time Monitor heart rate variability signals and generate discharge monitoring reports.
It improves the accuracy and personalization of discharge monitoring of atrial fibrillation patients, predicts the risk of onset, formulates targeted treatment plans, reduces recurrence rates, and enhances patient safety.
Smart Images

Figure CN119033352A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of atrial fibrillation monitoring, and in particular to an individual differentiated discharge monitoring method for patients with atrial fibrillation. Background Art
[0002] Atrial fibrillation is a common arrhythmia, in which the atria lose their normal rhythm and are replaced by rapid and irregular tremors. Monitoring patients after discharge is crucial to managing their condition. The significance of individual differentiated discharge monitoring methods is to better adapt to the specific needs of each patient and provide more precise and personalized medical care.
[0003] At present, the discharge of patients with atrial fibrillation is generally based on continuous observation of the electrocardiogram of the patients and continuous observation of the patients' physical feedback. If the results are good, they can be discharged. The general observation method has limitations and does not take into account the living conditions of patients after discharge, such as the influence of diet and living environment. There are often more relapses after discharge, and even untimely treatment poses a threat to the patients' lives and property, resulting in poor discharge monitoring effects for patients with atrial fibrillation. Summary of the invention
[0004] In order to solve the above problems, the present invention provides an individual differentiated discharge monitoring method for patients with atrial fibrillation, which can improve the discharge monitoring effect of patients with atrial fibrillation.
[0005] In a first aspect, the present invention provides a method for monitoring individualized discharge of patients with atrial fibrillation, comprising:
[0006] Acquire a heart rate variability signal of an atrial fibrillation patient under normal conditions, extract a multi-scale signal from the heart rate variability signal, extract a signal feature of the multi-scale signal, and use the signal feature as a normal atrial fibrillation feature of the atrial fibrillation patient;
[0007] Collecting the dietary pattern of the atrial fibrillation patient, analyzing the influence of different dietary patterns on the heart rate variability signal, and constructing the diet-atrial fibrillation influence parameter of the atrial fibrillation patient based on the influence;
[0008] Collecting the motion data of the atrial fibrillation patient, analyzing the motion tolerance of the atrial fibrillation patient based on the motion data, and constructing the motion-atrial fibrillation influence parameter of the atrial fibrillation patient based on the motion tolerance;
[0009] Extracting sample data of the atrial fibrillation patient, identifying spatial distribution information of the sample patient in the sample data, constructing a spatial distribution map of the sample patient using the spatial distribution information, analyzing the spatial distribution correlation of the sample patient according to the spatial distribution map, performing spatial distribution division on the sample patient based on the spatial distribution correlation to obtain regionally distributed patients, querying environmental information of the regionally distributed patients, and constructing environment-atrial fibrillation influence parameters of the regionally distributed patients based on the environmental information;
[0010] The regionally distributed patients are regionally matched with the atrial fibrillation patients to obtain regionally matched patients, an atrial fibrillation analysis model for the atrial fibrillation patients is constructed based on the regionally matched patients and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influencing parameters, the exercise-atrial fibrillation influencing parameters and the environment-atrial fibrillation influencing parameters, the heart rate variability signal of the atrial fibrillation patients is collected in real time, and the atrial fibrillation analysis model is used to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result, and when the signal analysis result is excellent, a discharge monitoring report for the atrial fibrillation patient is constructed.
[0011] In a possible implementation manner of the first aspect, extracting the multi-scale signal from the heart rate variability signal includes:
[0012] Performing wavelet transform on the heart rate variability signal to obtain a wavelet transform signal;
[0013] Performing empirical mode decomposition on the wavelet transform signal to obtain a decomposed signal;
[0014] Calculating the multiscale entropy of the decomposed signal, and extracting the multiscale features of the decomposed signal based on the multiscale entropy;
[0015] Performing time-frequency analysis on the multi-scale features to obtain a multi-scale signal of the heart rate variability signal.
[0016] In a possible implementation of the first aspect, the analyzing the degree of influence of different modes in the dietary pattern on the heart rate variability signal includes:
[0017] constructing a diet list for the atrial fibrillation patient based on the diet pattern;
[0018] Collecting the normal heart rate variability signal of the atrial fibrillation patient, and collecting multiple groups of heart rate variability signals of the atrial fibrillation patient after eating the food corresponding to the diet list, to obtain multiple groups of eating signals;
[0019] Extracting a mean signal of the plurality of groups of edible signals;
[0020] The mean signal is compared with the normal heart rate variability signal to obtain a contrast difference between the mean signal and the normal heart rate variability signal, and based on the contrast difference, the degree of influence of different modes in the dietary pattern on the heart rate variability signal is determined.
[0021] In a possible implementation of the first aspect, analyzing the exercise tolerance of the atrial fibrillation patient based on the exercise data includes:
[0022] Collecting multiple groups of exercise heart rate variability signals under the exercise data;
[0023] Querying the multiple sets of exercise heart rate variability signals about the physical state of the atrial fibrillation patient, and extracting the set of the multiple sets of exercise heart rate variability signals corresponding to the normal physical state with the largest fluctuation signal to obtain the maximum fluctuation signal;
[0024] The heart beat frequency corresponding to the maximum fluctuation signal is used as the exercise tolerance of the atrial fibrillation patient.
[0025] In a possible implementation of the first aspect, constructing a spatial distribution map of the sample patient by using the spatial distribution information includes:
[0026] Based on the spatial distribution information, determining the distribution area of the sample patients;
[0027] Constructing a view framework of the sample patients according to the distribution area; identifying the geographical distribution information of the sample patients;
[0028] Based on the geographic distribution information, the view frame is annotated with geographic information to obtain an annotated view;
[0029] The annotated view is displayed in three dimensions to obtain a spatial distribution map.
[0030] In a possible implementation manner of the first aspect, analyzing the spatial distribution correlation of the sample patients according to the spatial distribution map includes:
[0031] Performing spatial division on the spatial distribution map to obtain divided spaces;
[0032] Calculate the spatial correlation index of the sample patient based on the divided space combination;
[0033] The spatial distribution correlation of the sample patients is analyzed according to the spatial correlation index.
[0034] In a possible implementation of the first aspect, constructing the environment-atrial fibrillation influence parameter of the regionally distributed patients based on the environmental information includes:
[0035] Based on the environmental information, determining the geographical ecological data of the patients distributed in the area;
[0036] Based on the geographic ecological data, construct multiple groups of geographic impact lists of patients distributed in the region;
[0037] Collecting heart rate variability signals of atrial fibrillation patients corresponding to the multiple groups of geographical influence lists to obtain multiple groups of geographical signals;
[0038] Extracting a mean signal of the plurality of groups of geographic signals, and performing signal comparison between the mean signal and a normal heart rate variability signal;
[0039] Based on the contrast difference of the signal contrast, an environment-atrial fibrillation influence parameter of the regionally distributed patient is determined.
[0040] In a possible implementation of the first aspect, constructing the atrial fibrillation analysis model for the atrial fibrillation patient based on the region-matched patient and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influence parameter, the exercise-atrial fibrillation influence parameter, and the environment-atrial fibrillation influence parameter includes:
[0041] Using the atrial fibrillation signal and heart rate variability signal of the atrial fibrillation patient, constructing an initial regression model of the atrial fibrillation patient;
[0042] After the performance of the initial regression model is stabilized, a regression model is obtained;
[0043] The diet-atrial fibrillation influence parameter, the exercise-atrial fibrillation influence parameter and the environment-atrial fibrillation influence parameter are used as variable parameters of the regression model to obtain a target regression model;
[0044] The target regression model is used as the atrial fibrillation analysis model for the atrial fibrillation patient.
[0045] In a possible implementation of the first aspect, the real-time acquisition of the heart rate variability signal of the atrial fibrillation patient, and the use of the atrial fibrillation analysis model to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result include:
[0046] Collecting the heart rate variability signal of the atrial fibrillation patient in real time to obtain a real-time signal;
[0047] Converting the real-time signal into a regression curve;
[0048] The atrial fibrillation analysis model is used to perform real-time analysis on the regression curve to obtain a signal analysis result.
[0049] In a second aspect, the present invention provides a system for monitoring individualized discharge of patients with atrial fibrillation, the system comprising:
[0050] A signal analysis module, used for acquiring a heart rate variability signal of an atrial fibrillation patient under normal conditions, extracting a multi-scale signal from the heart rate variability signal, extracting a signal feature of the multi-scale signal, and using the signal feature as a normal atrial fibrillation feature of the atrial fibrillation patient;
[0051] A diet impact analysis module, used for collecting the diet pattern of the atrial fibrillation patient, analyzing the influence of different patterns in the diet pattern on the heart rate variability signal, and constructing the diet-atrial fibrillation influence parameter of the atrial fibrillation patient based on the influence degree;
[0052] A motion impact module, used for collecting motion data of the atrial fibrillation patient, analyzing the motion tolerance of the atrial fibrillation patient based on the motion data, and constructing motion-atrial fibrillation impact parameters of the atrial fibrillation patient based on the motion tolerance;
[0053] An environmental impact module is used to extract sample data of the atrial fibrillation patient, identify spatial distribution information of the sample patient in the sample data, construct a spatial distribution map of the sample patient using the spatial distribution information, analyze the spatial distribution correlation of the sample patient according to the spatial distribution map, divide the sample patient into spatial distribution groups based on the spatial distribution correlation, obtain regionally distributed patients, query the environmental information of the regionally distributed patients, and construct the environment-atrial fibrillation impact parameters of the regionally distributed patients based on the environmental information;
[0054] A discharge analysis module is used to perform regional matching between the regionally distributed patients and the atrial fibrillation patients to obtain regionally matched patients, construct an atrial fibrillation analysis model for the atrial fibrillation patients based on the regionally matched patients and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influencing parameters, the exercise-atrial fibrillation influencing parameters and the environment-atrial fibrillation influencing parameters, collect the heart rate variability signal of the atrial fibrillation patients in real time, and use the atrial fibrillation analysis model to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result, and when the signal analysis result is excellent, construct a discharge monitoring report for the atrial fibrillation patient.
[0055] Compared with the prior art, the technical principle and beneficial effects of this solution are:
[0056] The embodiment of the present invention can obtain the heart rate variability signal of the atrial fibrillation patient under normal conditions as an early warning indicator to help predict the risk of cardiovascular disease, and collect the dietary pattern of the atrial fibrillation patient to understand the daily dietary habits of the atrial fibrillation patient, and then analyze the impact of the patient's daily diet on his or her atrial fibrillation. Furthermore, the embodiment of the present invention can collect the exercise data of the atrial fibrillation patient as a basis for analyzing the cardiac tolerance of the atrial fibrillation patient. Furthermore, the embodiment of the present invention can predict the risk of the atrial fibrillation patient by extracting the sample data of the atrial fibrillation patient, and then formulate relevant treatment plans, and according to the spatial distribution map, Analyzing the spatial distribution correlation of the sample patients can analyze the geographical connection between different sample patients. For example, the heart of patients in the plains is under less pressure, and the heart's pressure-bearing capacity is naturally smaller. The heart of patients in the plateau is under greater pressure, and the heart's pressure-bearing capacity is also greater. The regionally distributed patients are matched with the atrial fibrillation patients. The regionally matched patients can be divided into corresponding regions to facilitate the correlation analysis between the atrial fibrillation patients and their corresponding geographical environments. For example, a patient lives in a hospital in area a and needs to return to urban area b after discharge. Area a is a plain area and area b is a plateau. In this case, the impact of the geographical environment on the patient needs to be considered to determine whether the patient has the discharge conditions. The individual differentiated discharge monitoring method and system for atrial fibrillation patients proposed in the embodiment of the present invention can improve the discharge monitoring effect of atrial fibrillation patients. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0059] Figure 1 A schematic diagram of a flow chart of a method for individually differentiated discharge monitoring of atrial fibrillation patients provided by an embodiment of the present invention;
[0060] Figure 2 A schematic diagram of modules of a system for individually differentiated discharge monitoring of atrial fibrillation patients provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0061] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0062] The embodiment of the present invention provides an individual differentiated discharge monitoring method for patients with atrial fibrillation. The execution subject of the individual differentiated discharge monitoring method for patients with atrial fibrillation includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the individual differentiated discharge monitoring method for patients with atrial fibrillation can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.
[0063] See also Figure 1 FIG. 1 is a flow chart of a method for monitoring the discharge of atrial fibrillation patients according to an embodiment of the present invention. Figure 1 An approach to individualized discharge monitoring for patients with atrial fibrillation described in the literature includes:
[0064] S1. Acquire a heart rate variability signal of an atrial fibrillation patient under normal conditions, extract a multi-scale signal from the heart rate variability signal, extract a signal feature of the multi-scale signal, and use the signal feature as a normal atrial fibrillation feature of the atrial fibrillation patient.
[0065] The embodiment of the present invention can be used as an early warning indicator to help predict the risk of cardiovascular disease by obtaining the heart rate variability signal of atrial fibrillation patients under normal conditions. The heart rate variability signal refers to the change in the difference between successive heartbeat cycles, which reflects the regulatory effect of the autonomic nervous system on the cardiovascular system, including the regulation of the sinoatrial node by neurohumoral factors, and can be obtained through an electrocardiogram.
[0066] Furthermore, the embodiment of the present invention can analyze the heart rate variability signal from multiple scale spaces by extracting the multi-scale signal from the heart rate variability signal, thereby ensuring the accuracy of the analysis result.
[0067] As an embodiment of the present invention, the method of extracting the multi-scale signal from the heart rate variability signal includes: performing a wavelet transform on the heart rate variability signal to obtain a wavelet transform signal, performing empirical mode decomposition on the wavelet transform signal to obtain a decomposition signal, calculating the multi-scale entropy of the decomposition signal, extracting multi-scale features of the decomposition signal based on the multi-scale entropy, and performing time-frequency analysis on the multi-scale features to obtain the multi-scale signal of the heart rate variability signal.
[0068] Optionally, performing wavelet transform on the heart rate variability signal to obtain a wavelet transform signal refers to a time-frequency analysis method, which decomposes the signal into components of different frequencies and time scales, which can be operated by preconfigured wavelet basis functions, performing empirical mode decomposition on the wavelet transform signal to obtain a decomposed signal refers to a signal decomposition method, which is used to decompose a complex signal into a series of intrinsic mode functions, calculating the multi-scale entropy of the decomposed signal refers to analyzing the degree of confusion of the signal, which can be calculated by an approximate entropy function, extracting multi-scale features of the decomposed signal based on the multi-scale entropy can be extracted by short-time Fourier transform, and performing time-frequency analysis on the multi-scale features to obtain the multi-scale signal of the heart rate variability signal can be achieved by Hilbert-Huang transform technology.
[0069] Furthermore, the embodiment of the present invention can help users understand the signal condition of the heart rate variability signal of the atrial fibrillation patient under normal conditions, such as whether it is stable or the magnitude of the fluctuation, by extracting the signal features of the multi-scale signal and using the signal features as the normal atrial fibrillation features of the atrial fibrillation patient.
[0070] Optionally, the signal features of the multi-scale signal are extracted through a preconfigured support vector machine network.
[0071] S2. Collecting the dietary pattern of the atrial fibrillation patient, analyzing the influence of different dietary patterns on the heart rate variability signal, and constructing the diet-atrial fibrillation influence parameter of the atrial fibrillation patient based on the influence.
[0072] The embodiment of the present invention can understand the daily eating habits of the atrial fibrillation patient by collecting the dietary pattern of the atrial fibrillation patient, and then analyze the impact of the patient's daily diet on his or her atrial fibrillation. The dietary pattern refers to the dietary habits and food selection methods followed by an individual or group in daily life, such as the Mediterranean diet, DASH diet, fish, ω-3 polyunsaturated fatty acid diet, etc.
[0073] Furthermore, the embodiment of the present invention can understand the influence of different dietary habits of different patients on atrial fibrillation by analyzing the influence of different dietary patterns on the heart rate variability signal, and then perform parameterized analysis.
[0074] As an embodiment of the present invention, the analysis of the degree of influence of different modes in the dietary pattern on the heart rate variability signal includes: constructing a diet list for the atrial fibrillation patient based on the dietary pattern, collecting normal heart rate variability signals of the atrial fibrillation patient, and collecting multiple groups of heart rate variability signals of the atrial fibrillation patients after eating foods corresponding to the diet list to obtain multiple groups of consumption signals, extracting the mean signal of the multiple groups of consumption signals, comparing the mean signal with the normal heart rate variability signal to obtain the contrast difference between the mean signal and the normal heart rate variability signal, and determining the degree of influence of different modes in the dietary pattern on the heart rate variability signal based on the contrast difference.
[0075] It should be noted that the collection of multiple groups of heart rate variability signals of the atrial fibrillation patients after eating the foods in the diet list results in multiple groups of eating signals corresponding to more foods in different diet patterns, which are impossible for the patients to eat all at once, so multiple groups are collected and the average value is taken.
[0076] Furthermore, the embodiment of the present invention can quantify the impact of the diet under different modes in the dietary pattern on the atrial fibrillation patient by constructing the diet-atrial fibrillation impact parameter of the atrial fibrillation patient based on the impact degree, so as to facilitate scientific analysis, wherein the diet-atrial fibrillation impact parameter refers to the value of different diets on atrial fibrillation.
[0077] Optionally, based on the degree of influence, the diet-atrial fibrillation influence parameter of the atrial fibrillation patient is constructed by comparing the heart rate variability signals collected from different atrial fibrillation patients after they follow the corresponding dietary patterns with the normal signals, and taking the difference in the comparison as the diet-atrial fibrillation influence parameter.
[0078] S3. Collecting the motion data of the atrial fibrillation patient, analyzing the motion tolerance of the atrial fibrillation patient based on the motion data, and constructing the motion-atrial fibrillation influence parameter of the atrial fibrillation patient based on the motion tolerance.
[0079] In the embodiment of the present invention, the collected motion data of the atrial fibrillation patient can be used as a basis for analyzing the cardiac tolerance of the atrial fibrillation patient, wherein the motion data refers to the physical data of the atrial fibrillation patient during exercise, such as blood pressure, blood oxygen level, heart rate and other data.
[0080] Furthermore, the embodiment of the present invention can analyze the exercise tolerance of the atrial fibrillation patient based on the exercise data to determine the exercise capacity of the atrial fibrillation patient or the stress that the body can withstand. The exercise tolerance refers to the tolerance of the heart when it is under stress.
[0081] As an embodiment of the present invention, the analysis of the exercise tolerance of the atrial fibrillation patient based on the exercise data includes: collecting multiple groups of exercise heart rate variability signals under the exercise data, querying the physical state of the atrial fibrillation patient under the multiple groups of exercise heart rate variability signals, and extracting the group with the largest fluctuation signal from the multiple groups of exercise heart rate variability signals corresponding to the normal physical state, obtaining the maximum fluctuation signal, and using the heart beat frequency corresponding to the maximum fluctuation signal as the exercise tolerance of the atrial fibrillation patient.
[0082] Optionally, the querying of the physical state of the atrial fibrillation patient under the multiple sets of exercise heart rate variability signals is obtained by analyzing the physical measurement state of the atrial fibrillation patient after exercise, wherein the physical measurement state includes blood pressure, heartbeat, physiological response and the like.
[0083] Furthermore, the embodiment of the present invention can understand the cardiac stress tolerance range of the atrial fibrillation patient by constructing the exercise-atrial fibrillation influence parameter of the atrial fibrillation patient based on the exercise tolerance.
[0084] Optionally, the construction of the exercise-atrial fibrillation influence parameter for the atrial fibrillation patient based on the exercise tolerance may use the maximum fluctuation signal as the exercise-atrial fibrillation influence parameter for the atrial fibrillation patient.
[0085] S4. Extract the sample data of the atrial fibrillation patients, identify the spatial distribution information of the sample patients in the sample data, use the spatial distribution information to construct a spatial distribution map of the sample patients, analyze the spatial distribution correlation of the sample patients according to the spatial distribution map, divide the sample patients into spatial distribution groups based on the spatial distribution correlation, obtain regionally distributed patients, query the environmental information of the regionally distributed patients, and construct the environment-atrial fibrillation influence parameters of the regionally distributed patients based on the environmental information.
[0086] The embodiment of the present invention can predict the risk of atrial fibrillation patients by extracting the sample data of atrial fibrillation patients, and then formulate relevant treatment plans. The sample data refers to patients with atrial fibrillation with historical records, including basic information of the patients, treatment information, and discharge information, and the sample data can be obtained by querying the treatment database of the atrial fibrillation patients.
[0087] Furthermore, the embodiment of the present invention can understand the spatial distribution of patients with atrial fibrillation in the historical record by identifying the spatial distribution information of the sample patients in the sample data, and then perform spatial difference analysis. The spatial distribution information can be obtained by reading the location information of the patients with atrial fibrillation in the historical record in the sample data.
[0088] The embodiment of the present invention constructs a spatial distribution map of the sample patients by utilizing the spatial distribution information. According to the spatial distribution map, the distribution of the disease in different regions can be understood, and high-incidence areas can be discovered in time.
[0089] As an embodiment of the present invention, the use of the spatial distribution information to construct a spatial distribution map of the sample patients includes: determining the distribution area of the sample patients based on the spatial distribution information, constructing a view framework of the sample patients according to the distribution area, identifying the geographic distribution information of the sample patients, annotating the view framework with geographic information based on the geographic distribution information to obtain an annotated view, and displaying the annotated view in three dimensions to obtain a spatial distribution map.
[0090] The distribution area refers to the size of the distribution area, the view frame refers to the basic structure of the view such as size and hierarchy, and the geographic distribution information refers to information such as geographic name, location, climate, etc.
[0091] Optionally, the distribution area of the sample patients is determined based on the spatial distribution information by querying the geographic distribution interval of the sample patients, the view framework of the sample patients is constructed according to the distribution area by using a mysql tool to perform geometric scaling using the distribution area, the geographic distribution information of the sample patients is identified by a geographic view tool, the view framework is annotated with geographic information based on the geographic distribution information, the annotated view is annotated by a script constructed in java, the annotated view is displayed in three dimensions, and the spatial distribution map is displayed by GIS software.
[0092] The embodiment of the present invention can analyze the geographical connection between different sample patients by analyzing the spatial distribution correlation of the sample patients according to the spatial distribution map. For example, the heart of a patient in a plain is subjected to less pressure, and the heart's pressure-bearing capacity is naturally smaller; the heart of a patient in a plateau is subjected to greater pressure, and the heart's pressure-bearing capacity is also greater.
[0093] As an embodiment of the present invention, analyzing the spatial distribution correlation of the sample patients according to the spatial distribution map includes: spatially dividing the spatial distribution map to obtain a divided space, and calculating the spatial correlation index of the sample patients based on the divided space in combination with the following formula:
[0094]
[0095] Among them, δ represents the spatial correlation index, M represents the number of partitioned spaces, and β ij represents the weight matrix for partitioning space, A i represents the number of sample patients in the i-th partition space, A j represents the number of sample patients in the jth partition space, and A represents the average number of sample patients in the partition space;
[0096] The spatial distribution correlation of the sample patients is analyzed according to the spatial correlation index.
[0097] Optionally, the spatial distribution map is spatially divided to obtain the divided spaces by performing position division using the geographical locations corresponding to the spatial distribution map.
[0098] Furthermore, in another optional embodiment of the present invention, analyzing the spatial distribution correlation of the sample patients according to the spatial correlation index includes: calculating the correlation score value of the spatial correlation index using the following formula:
[0099]
[0100] Among them, S represents the correlation score value, δ represents the spatial correlation index, M represents the number of divided spaces, and T represents the spatial discreteness;
[0101] The spatial distribution correlation of the sample patients is analyzed according to the score values.
[0102] The correlation score value indicates the degree of spatial correlation. When the score value is 0.6, it indicates that the correlation is relatively strong. It can also be set according to the actual application scenario.
[0103] The embodiment of the present invention divides the sample patients into spatial distributions to obtain regionally distributed patients, and can associate and analyze the geographic location data of the sample patients with other environmental, demographic or geographical factors.
[0104] As an embodiment of the present invention, the spatial distribution of the sample patients is divided based on the spatial distribution correlation to obtain regionally distributed patients, including: identifying the spatial distribution characteristics of the sample patients according to the spatial distribution correlation, constructing a topological map of the sample patients based on the spatial distribution characteristics, and using the topological map to spatially divide the sample patients to obtain regionally distributed patients. Wherein, the spatial distribution specifically refers to the characteristics of the distribution of the sample patients in space, such as continuous type, dense type, etc., and the topological map refers to a graphical representation used to describe the connection relationship between elements in a system or network.
[0105] Optionally, the spatial distribution characteristics of the sample patients identified according to the spatial distribution correlation are set as similar classes whose correlations meet preset requirements, and the distribution characteristics of the similar classes are identified, and the topological map of the sample patients constructed based on the spatial distribution characteristics is obtained by connecting areas with the same distribution characteristics.
[0106] The embodiment of the present invention can find the correlation between the high-incidence areas of sinusitis and certain specific environmental factors by identifying the environmental conditions of the patients distributed in the region, so as to formulate relevant health policies and guidance.
[0107] Optionally, the environmental conditions where the regionally distributed patients are located are identified by querying the geographical environment information where the regionally distributed patients are located.
[0108] The embodiment of the present invention can evaluate the contribution of different environmental factors to atrial fibrillation of the atrial fibrillation patient by constructing the environment-atrial fibrillation impact parameter of the regionally distributed patients based on the environmental information, optimize the prevention and control strategy of atrial fibrillation patients, etc. Among them, the environment-atrial fibrillation impact parameter refers to a numerical value used to represent the degree of influence of environmental factors on atrial fibrillation.
[0109] As an embodiment of the present invention, the construction of the environment-atrial fibrillation influence parameters of the regionally distributed patients based on the environmental information includes: determining the geographical ecological data of the regionally distributed patients based on the environmental information, constructing multiple groups of geographical influence lists of the regionally distributed patients based on the geographical ecological data, and collecting heart rate variability signals of the atrial fibrillation patients corresponding to the multiple groups of geographical influence lists to obtain multiple groups of geographical signals, extracting the mean signal of the multiple groups of geographical signals, comparing the mean signal with the normal heart rate variability signal, and determining the environment-atrial fibrillation influence parameters of the regionally distributed patients based on the contrast difference of the signal comparison.
[0110] Optionally, based on the environmental information, the geographic ecological data of the regionally distributed patients is determined, the geographic area where the regionally distributed patients are located is identified through the environmental information, and the geographic ecological data of the geographic area is queried; based on the geographic ecological data, a plurality of groups of geographic influence lists of the regionally distributed patients are constructed through a table generated by java; the signal comparison between the mean signal and the normal heart rate variability signal can be obtained by performing vector conversion between the mean signal and the heart rate variability signal to obtain the mean and heart rate vectors, and calculating the vector difference between the mean and the heart rate vector; the environment-atrial fibrillation influence parameters of the regionally distributed patients are determined based on the contrast difference of the signal comparison, and the vector difference can be used as the environment-atrial fibrillation influence parameters of the regionally distributed patients.
[0111] S5. Perform regional matching between the regionally distributed patients and the atrial fibrillation patients to obtain regionally matched patients, construct an atrial fibrillation analysis model for the atrial fibrillation patients based on the regionally matched patients and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influencing parameters, the exercise-atrial fibrillation influencing parameters and the environment-atrial fibrillation influencing parameters, collect the heart rate variability signal of the atrial fibrillation patients in real time, and use the atrial fibrillation analysis model to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result, and when the signal analysis result is excellent, construct a discharge monitoring report for the atrial fibrillation patients.
[0112] The embodiment of the present invention performs regional matching on the regionally distributed patients and the atrial fibrillation patients to obtain regionally matched patients, and the atrial fibrillation patients can be divided into corresponding regions, so as to facilitate the association analysis between the atrial fibrillation patients and their corresponding geographical environments. For example, if a patient lives in a hospital in area a and needs to return to urban area b after discharge, area a is a plain area and area b is a plateau, the impact of the geographical environment on the patient needs to be considered to determine whether the patient has the discharge conditions.
[0113] Furthermore, the embodiment of the present invention can quickly and effectively analyze whether the atrial fibrillation of the atrial fibrillation patient is abnormal or meets the discharge criteria by constructing the atrial fibrillation analysis model of the atrial fibrillation patient based on the regional matching patient and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influence parameter, the exercise-atrial fibrillation influence parameter and the environment-atrial fibrillation influence parameter. Among them, the atrial fibrillation analysis model refers to a mathematical model for analyzing the atrial fibrillation changes of the atrial fibrillation patient.
[0114] As an embodiment of the present invention, the atrial fibrillation analysis model of the atrial fibrillation patient is constructed based on the regional matching patient and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influence parameter, the exercise-atrial fibrillation influence parameter and the environment-atrial fibrillation influence parameter, including: using the atrial fibrillation signal and heart rate variability signal of the atrial fibrillation patient to construct an initial regression model of the atrial fibrillation patient, after the performance of the initial regression model is stable, obtaining a regression model, using the diet-atrial fibrillation influence parameter, the exercise-atrial fibrillation influence parameter and the environment-atrial fibrillation influence parameter as variable parameters of the regression model, to obtain a target regression model, wherein the target regression model can be expressed by the following formula:
[0115] y=γ0+γ1x1+γ2x2+…+γ n x n +φ1+φ2+φ3
[0116] Among them, y represents the regression result, γ0, γ1, γ2, γ n represents the regression coefficient, x1, x2, x n represents the independent variable, φ1 represents the diet-AF influence parameter, φ2 represents the exercise-AF influence parameter, φ3 represents the environment-AF influence parameter,
[0117] The target regression model is used as the atrial fibrillation analysis model for the atrial fibrillation patient.
[0118] Optionally, the atrial fibrillation signal and heart rate variability signal of the atrial fibrillation patient are used to construct an initial regression model of the atrial fibrillation patient through a linear regression function, wherein the atrial fibrillation signal is the dependent variable of the linear regression function, and the heart rate variability signal is the independent variable of the linear regression function. After the performance of the initial regression model is stabilized, the regression model is obtained by performing multiple fitting training on the linear regression function, and when the fitting value of the fitting training reaches a preset threshold, the regression model is obtained.
[0119] Furthermore, the embodiment of the present invention collects the heart rate variability signal of the atrial fibrillation patient in real time, and uses the atrial fibrillation analysis model to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result, which can be used to analyze and observe in real time whether the atrial fibrillation patient is likely to develop atrial fibrillation, and whether the patient tends to be in a stable state after treatment and is less likely to develop atrial fibrillation.
[0120] As an embodiment of the present invention, the real-time acquisition of the heart rate variability signal of the atrial fibrillation patient and the use of the atrial fibrillation analysis model to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result include: real-time acquisition of the heart rate variability signal of the atrial fibrillation patient to obtain a real-time signal, converting the real-time signal into a regression curve, and using the atrial fibrillation analysis model to perform real-time analysis on the regression curve to obtain a signal analysis result.
[0121] Optionally, the real-time signal is converted into a regression curve using a multivariate regression function, and the process of performing real-time analysis on the regression curve using the atrial fibrillation analysis model to obtain a signal analysis result is: comparing and analyzing the regression curve with a baseline curve in the atrial fibrillation analysis model, observing the slope difference between the real-time curve change of the regression curve and the baseline curve, and recording the slope difference, and using the slope difference as the analysis result.
[0122] It should be noted that when the signal analysis result is excellent, constructing the discharge monitoring report for the atrial fibrillation patient means that the difference in the slope difference is less than the preset value of 0.05 (which can also be set according to the actual application scenario), indicating that the atrial fibrillation of the atrial fibrillation patient has stabilized and the patient can be discharged without any accidents, thereby generating a discharge monitoring report for the atrial fibrillation patient.
[0123] like Figure 2 Shown is a functional module diagram of an individual differentiated discharge monitoring system for atrial fibrillation patients according to the present invention.
[0124] The individualized differentiated discharge monitoring system 200 for atrial fibrillation patients of the present invention can be installed in an electronic device. According to the functions to be implemented, the individualized differentiated discharge monitoring system for atrial fibrillation patients can include a signal analysis module 201, a diet impact analysis module 202, an exercise impact module 203, an environmental impact module 204, and a discharge analysis module 205. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0125] In the embodiment of the present invention, the functions of each module / unit are as follows:
[0126] The signal analysis module 201 is used to obtain a heart rate variability signal of an atrial fibrillation patient under normal conditions, extract a multi-scale signal from the heart rate variability signal, extract a signal feature of the multi-scale signal, and use the signal feature as a normal atrial fibrillation feature of the atrial fibrillation patient;
[0127] The diet impact analysis module 202 is used to collect the diet pattern of the atrial fibrillation patient, analyze the influence of different patterns in the diet pattern on the heart rate variability signal, and construct the diet-atrial fibrillation influence parameter of the atrial fibrillation patient based on the influence degree;
[0128] The exercise impact module 203 is used to collect the exercise data of the atrial fibrillation patient, analyze the exercise tolerance of the atrial fibrillation patient based on the exercise data, and construct the exercise-atrial fibrillation influence parameter of the atrial fibrillation patient based on the exercise tolerance;
[0129] The environmental impact module 204 is used to extract the sample data of the atrial fibrillation patient, identify the spatial distribution information of the sample patient in the sample data, construct a spatial distribution map of the sample patient using the spatial distribution information, analyze the spatial distribution correlation of the sample patient according to the spatial distribution map, divide the sample patient into spatial distribution groups based on the spatial distribution correlation, obtain regional distribution patients, query the environmental information of the regional distribution patients, and construct the environment-atrial fibrillation impact parameters of the regional distribution patients based on the environmental information;
[0130] The discharge analysis module 205 is used to perform regional matching between the regionally distributed patients and the atrial fibrillation patients to obtain regionally matched patients, construct an atrial fibrillation analysis model for the atrial fibrillation patients based on the regionally matched patients and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influencing parameters, the exercise-atrial fibrillation influencing parameters and the environment-atrial fibrillation influencing parameters, collect the heart rate variability signal of the atrial fibrillation patients in real time, and use the atrial fibrillation analysis model to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result, and when the signal analysis result is excellent, construct a discharge monitoring report for the atrial fibrillation patient.
[0131] In detail, each module in the scene modeling system 200 for realizing intelligent transportation based on digital twins described in the embodiment of the present invention is used in the same manner as described above. Figure 1 The technical means described in the text is the same as the scene modeling method for smart transportation based on digital twins, and can produce the same technical effects, so I will not go into details here.
[0132] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
Claims
1. A method for monitoring individualized discharge of patients with atrial fibrillation, characterized in that: The method comprises: Acquire a heart rate variability signal of an atrial fibrillation patient under normal conditions, extract a multi-scale signal from the heart rate variability signal, extract a signal feature of the multi-scale signal, and use the signal feature as a normal atrial fibrillation feature of the atrial fibrillation patient; Collecting the dietary pattern of the atrial fibrillation patient, analyzing the influence of different dietary patterns on the heart rate variability signal, and constructing the diet-atrial fibrillation influence parameter of the atrial fibrillation patient based on the influence; Collecting the motion data of the atrial fibrillation patient, analyzing the motion tolerance of the atrial fibrillation patient based on the motion data, and constructing the motion-atrial fibrillation influence parameter of the atrial fibrillation patient based on the motion tolerance; Extracting sample data of the atrial fibrillation patient, identifying spatial distribution information of the sample patient in the sample data, constructing a spatial distribution map of the sample patient using the spatial distribution information, analyzing the spatial distribution correlation of the sample patient according to the spatial distribution map, performing spatial distribution division on the sample patient based on the spatial distribution correlation to obtain regionally distributed patients, querying environmental information of the regionally distributed patients, and constructing environment-atrial fibrillation influence parameters of the regionally distributed patients based on the environmental information; The regionally distributed patients are regionally matched with the atrial fibrillation patients to obtain regionally matched patients, an atrial fibrillation analysis model for the atrial fibrillation patients is constructed based on the regionally matched patients and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influencing parameters, the exercise-atrial fibrillation influencing parameters and the environment-atrial fibrillation influencing parameters, the heart rate variability signal of the atrial fibrillation patients is collected in real time, and the atrial fibrillation analysis model is used to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result, and when the signal analysis result is excellent, a discharge monitoring report for the atrial fibrillation patient is constructed.
2. The method according to claim 1, characterized in that The extracting of the multi-scale signal from the heart rate variability signal comprises: Performing wavelet transform on the heart rate variability signal to obtain a wavelet transform signal; Performing empirical mode decomposition on the wavelet transform signal to obtain a decomposed signal; Calculating the multiscale entropy of the decomposed signal, and extracting the multiscale features of the decomposed signal based on the multiscale entropy; Performing time-frequency analysis on the multi-scale features to obtain a multi-scale signal of the heart rate variability signal.
3. The method according to claim 1, characterized in that: The analyzing the influence of different modes in the dietary pattern on the heart rate variability signal includes: constructing a diet list for the atrial fibrillation patient based on the diet pattern; Collecting the normal heart rate variability signal of the atrial fibrillation patient, and collecting multiple groups of heart rate variability signals of the atrial fibrillation patient after eating the food corresponding to the diet list, to obtain multiple groups of eating signals; Extracting a mean signal of the plurality of groups of edible signals; The mean signal is compared with the normal heart rate variability signal to obtain a contrast difference between the mean signal and the normal heart rate variability signal, and based on the contrast difference, the degree of influence of different modes in the dietary pattern on the heart rate variability signal is determined.
4. The method according to claim 1, characterized in that: The step of analyzing the exercise tolerance of the atrial fibrillation patient based on the exercise data comprises: Collecting multiple groups of exercise heart rate variability signals under the exercise data; Querying the multiple sets of exercise heart rate variability signals about the physical state of the atrial fibrillation patient, and extracting the set of the multiple sets of exercise heart rate variability signals corresponding to the normal physical state with the largest fluctuation signal to obtain the maximum fluctuation signal; The heart beat frequency corresponding to the maximum fluctuation signal is used as the exercise tolerance of the atrial fibrillation patient.
5. The method according to claim 1, characterized in that The step of constructing a spatial distribution map of the sample patients by using the spatial distribution information includes: Based on the spatial distribution information, determining the distribution area of the sample patients; Constructing a view framework of the sample patients according to the distribution area; identifying the geographical distribution information of the sample patients; Based on the geographic distribution information, the view frame is annotated with geographic information to obtain an annotated view; The annotated view is displayed in three dimensions to obtain a spatial distribution map.
6. The method according to claim 1, characterized in that Analyzing the spatial distribution correlation of the sample patients according to the spatial distribution map includes: Performing spatial division on the spatial distribution map to obtain divided spaces; Calculate the spatial correlation index of the sample patient based on the divided space combination; The spatial distribution correlation of the sample patients is analyzed according to the spatial correlation index.
7. The method according to claim 1, characterized in that The step of constructing the environment-atrial fibrillation impact parameters of the regionally distributed patients based on the environmental information includes: Collecting heart rate variability signals of atrial fibrillation patients corresponding to the multiple groups of geographical influence lists to obtain multiple groups of geographical signals; Extracting a mean signal of the plurality of groups of geographic signals, and performing signal comparison between the mean signal and a normal heart rate variability signal; Based on the contrast difference of the signal contrast, an environment-atrial fibrillation influence parameter of the regionally distributed patient is determined.
8. The method according to claim 1, characterized in that The constructing of the atrial fibrillation analysis model for the atrial fibrillation patient based on the region-matched patient and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influence parameter, the exercise-atrial fibrillation influence parameter and the environment-atrial fibrillation influence parameter comprises: Using the atrial fibrillation signal and heart rate variability signal of the atrial fibrillation patient, constructing an initial regression model of the atrial fibrillation patient; After the performance of the initial regression model is stabilized, a regression model is obtained; The diet-atrial fibrillation influence parameter, the exercise-atrial fibrillation influence parameter and the environment-atrial fibrillation influence parameter are used as variable parameters of the regression model to obtain a target regression model; The target regression model is used as the atrial fibrillation analysis model for the atrial fibrillation patient.
9. The method according to claim 1, characterized in that: The real-time acquisition of the heart rate variability signal of the atrial fibrillation patient and the use of the atrial fibrillation analysis model to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result include: Collecting the heart rate variability signal of the atrial fibrillation patient in real time to obtain a real-time signal; Converting the real-time signal into a regression curve; The atrial fibrillation analysis model is used to perform real-time analysis on the regression curve to obtain a signal analysis result.
10. An individualized differentiated discharge monitoring system for patients with atrial fibrillation, characterized in that: The system comprises: A signal analysis module, used for acquiring a heart rate variability signal of an atrial fibrillation patient under normal conditions, extracting a multi-scale signal from the heart rate variability signal, extracting a signal feature of the multi-scale signal, and using the signal feature as a normal atrial fibrillation feature of the atrial fibrillation patient; A diet impact analysis module, used for collecting the diet pattern of the atrial fibrillation patient, analyzing the influence of different patterns in the diet pattern on the heart rate variability signal, and constructing the diet-atrial fibrillation influence parameter of the atrial fibrillation patient based on the influence degree; A motion impact module, used for collecting motion data of the atrial fibrillation patient, analyzing the motion tolerance of the atrial fibrillation patient based on the motion data, and constructing motion-atrial fibrillation impact parameters of the atrial fibrillation patient based on the motion tolerance; An environmental impact module is used to extract sample data of the atrial fibrillation patient, identify spatial distribution information of the sample patient in the sample data, construct a spatial distribution map of the sample patient using the spatial distribution information, analyze the spatial distribution correlation of the sample patient according to the spatial distribution map, divide the sample patient into spatial distribution groups based on the spatial distribution correlation, obtain regionally distributed patients, query the environmental information of the regionally distributed patients, and construct the environment-atrial fibrillation impact parameters of the regionally distributed patients based on the environmental information; A discharge analysis module is used to perform regional matching between the regionally distributed patients and the atrial fibrillation patients to obtain regionally matched patients, construct an atrial fibrillation analysis model for the atrial fibrillation patients based on the regionally matched patients and the normal atrial fibrillation characteristics, the diet-atrial fibrillation influencing parameters, the exercise-atrial fibrillation influencing parameters and the environment-atrial fibrillation influencing parameters, collect the heart rate variability signal of the atrial fibrillation patients in real time, and use the atrial fibrillation analysis model to perform continuous signal analysis on the heart rate variability signal to obtain a signal analysis result, and when the signal analysis result is excellent, construct a discharge monitoring report for the atrial fibrillation patient.
