Data analysis method and system for health monitoring of brain pacemaker implanter

Abstract

The invention discloses a data analysis method and system for health monitoring of a brain pacemaker implanter, and belongs to the technical field of data monitoring. The system comprises a data acquisition module, a data analysis module, a security management module and a data storage module. The data acquisition module is used for acquiring sensing data, historical logs and equipment parameters; the data analysis module analyzes a historical log so as to establish a broken line graph and set sampling points, all the sampling points are screened and marked, and then prediction parameters are calculated; a simulation scene is constructed, a model is built, a three-dimensional temperature field is built by marking prediction parameters of sampling points, and therefore a time sequence demonstration model is built; the safety management module sets time nodes in the time sequence demonstration model, and calculates a risk coefficient of each time node and risk indexes of all the time nodes according to equipment parameters, so as to calculate an early warning distance and an early warning time length and generate an early warning notification; and the data storage module is used for displaying the early warning notice, generating an operation record and storing the operation record in a historical log.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and specifically to a data analysis method and system for the health monitoring of brain pacemaker implant recipients. Background Art

[0002] With the development of modern technology, intelligent terminals have become an indispensable tool in people's daily lives. However, the radio frequency electromagnetic fields generated by the antenna functions in intelligent terminals may generate thermal effects with surrounding biological tissues and implants, leading to thermal strain, further causing malfunction of the implants, and even physical displacement.

[0003] Brain pacemakers are widely used in the treatment of Parkinson's disease, epilepsy, and other neurological disorders. Since their implantation location is inside the human brain, when using an intelligent terminal, due to the short distance, the brain pacemaker is more vulnerable to the influence of radio frequency electromagnetic fields. The specific degree of influence is restricted by various factors, including the signal frequency of the intelligent terminal, the material distribution of the brain pacemaker, the duration of using the intelligent terminal, and the actual distance between the human brain and the intelligent terminal. These factors together constitute the influence of the radio frequency electromagnetic fields generated by the intelligent terminal on the brain pacemaker. Therefore, how to conduct a more detailed and comprehensive analysis of these influencing factors to predict the development trend of the influence degree in advance is particularly important. So at present, a more intelligent and efficient data analysis technical solution for the health monitoring of brain pacemaker implant recipients is needed to solve the above problems. Summary of the Invention

[0004] The purpose of the present invention is to provide a data analysis method and system for the health monitoring of brain pacemaker implant recipients to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides a data analysis method for the health monitoring of brain pacemaker implant recipients, including the following steps:

[0006] S100. When the subject uses an intelligent terminal, collect induction data, historical logs, and device parameters through the intelligent terminal.

[0007] S200. Analyze the historical logs to establish a line graph and set sampling points, screen and mark all sampling points, and then calculate prediction parameters. Construct a simulation scenario and build a model, and establish a three-dimensional temperature field through the prediction parameters of the marked sampling points. All the three-dimensional temperature fields are jointly formed into a time series demonstration model.

[0008] S300. Set time nodes in the time series demonstration model, calculate the risk coefficient of each time node and the risk index of all time nodes according to the device parameters, and then calculate the warning distance and warning duration and generate a warning notice.

[0009] S400. Display the warning notice through the visualization interface of the intelligent terminal, generate an operation record based on the sensing data collected by the intelligent terminal, and store it in the historical log.

[0010] In S100, the object refers to the implantee of the brain pacemaker, and the intelligent terminal refers to a device capable of data exchange, processing, and interaction through the Internet. The sensing data includes the sensing distance, signal frequency, and the software application currently in use. The sensing distance refers to the actual distance between the intelligent terminal and the object. The signal frequency refers to the radio frequency used when the intelligent terminal communicates with the base station.

[0011] When the object uses different software applications in the intelligent terminal, the change of the signal frequency is usually different. The main influencing factors include:

[0012] Application type: Real-time applications usually require low latency and high-frequency data transmission, so the signal frequency is higher. Non-real-time applications can tolerate higher latency, so the signal frequency is lower.

[0013] Hardware performance: The hardware performance of the device will affect the signal frequency during the operation of the application. High-performance devices can process more signals faster.

[0014] User behavior: The operation habits of the user in the application will also affect the signal frequency. The signal frequency may increase when the user is active in some applications.

[0015] Program design: The coding and design of the application determine how it interacts with the network. Some applications may use technologies such as data compression and delayed sending, thus affecting the signal frequency.

[0016] The historical log includes the operation logs of all software applications in the intelligent terminal. The operation log includes the operation records each time the software application is used. Each operation record includes the stay time period, and the changes in the sensing distance and signal frequency during the stay time period. The stay time period refers to the time period when the object stays on the interface after clicking on the software application to enter. The device parameters refer to the parameter information of the brain pacemaker worn by the object, including the three-dimensional stereogram, actual volume, composition materials, and the thermal expansion coefficient of each material.

[0017] The thermal expansion coefficient is used to describe the degree of change in the volume of the material when the temperature changes. Specifically, it refers to the proportion of the volume increase or decrease of the material per unit volume for each increase or decrease of one unit degree Celsius. The thermal expansion coefficients of different materials are different. Generally speaking, metals have larger thermal expansion coefficients, while ceramics and glass have smaller thermal expansion coefficients.

[0018] In S200, the specific steps are as follows:

[0019] S201. When the object clicks to enter the software application SW, obtain the current time TI nowAnd the operation log OR of the software application SW u 。Filter out the operation log OR u All operation records in it, calculate the midpoint time according to the stay time period of each operation record, and classify all operation records with the same midpoint time corresponding to the same day into the same category.

[0020] Analyze TI now The moment TI of the corresponding date in a day sk , set the error duration ac, and mark the operation records whose difference between the moment corresponding to the midpoint time within each category and TI sk is less than ac. Analyze the duration of the stay time period of each marked operation record, and calculate the average value of the durations of all marked operation records as the prediction duration.

[0021] S202. Obtain the marked operation record MR 1 The change situation of the induction distance and signal frequency within the stay time period in it. First, establish a distance line chart with time as the horizontal axis and induction distance as the vertical axis, and then establish a frequency line chart with time as the horizontal axis and signal frequency as the vertical axis, and establish a distance line chart and a frequency line chart for each marked operation record respectively.

[0022] Set the sampling duration ct, obtain the distance line charts and frequency line charts of all marked operation records, and set a sampling point every duration ct in each line chart. Take the standard deviation of the induction distance of the sampling point i in all distance line charts as the induction coefficient, and the standard deviation of the signal frequency in all distance line charts as the frequency coefficient.

[0023] S203. Calculate the induction coefficient and frequency coefficient of each sampling point respectively, set the induction coefficient threshold x and the frequency coefficient threshold y, and mark the sampling points with the induction coefficient less than x and the frequency coefficient less than y. Take the average value of the induction distance of the marked sampling points in all distance line charts as the predicted distance, and the average value of the signal frequency in all distance line charts as the predicted frequency.

[0024] Use COMSOL multi - physical field simulation software to construct a simulation scenario, build a human brain model and an intelligent terminal model, and build a brain pacemaker model in the human brain model according to the device parameters.

[0025] When an object uses an intelligent terminal, the radio - frequency electromagnetic field generated by the signal antenna will have a thermal effect on the brain pacemaker and brain tissue. During the heat conduction process of the brain tissue and the electrode, the increase in their temperatures will cause them to generate thermal strain, thereby changing their volumes. Different thermal strains of the electrode and brain tissue will lead to stress at the contact interface between the two, and further cause the electrode to displace. Limited by ethics, it is impossible to directly measure the thermal effect and displacement of the living brain tissue after implanting the electrode. Therefore, use COMSOL multi - physical field simulation software to construct a simulation scenario and build a model to realize the calculation and simulation of the three - dimensional temperature field.

[0026] S204. Obtain the marked sampling point CY v predicted distance JL v and predicted frequency PL v , simulate and analyze the temperature distribution of the brain pacemaker model when the distance between the human brain model and the intelligent terminal model is JL v and the intelligent terminal is operating at frequency PL v , so as to establish a three-dimensional temperature field for the marked sampling point CY v Establish a three-dimensional temperature field

[0027] When establishing a three-dimensional temperature field, the interval duration of the object's previous use of other software applications needs to be considered. When the interval duration is not sufficient to allow the temperature of the previously established three-dimensional temperature field to recover to the normal temperature when the intelligent terminal has not been used for a long time, the temperature cooling effect should also be considered according to the interval duration to improve the data accuracy of the three-dimensional temperature field

[0028] Establish a three-dimensional temperature field for each marked sampling point respectively, sort all marked sampling points in chronological order, and calculate the duration between two adjacent marked sampling points as the transition duration between the corresponding two three-dimensional temperature fields. Use the smooth transition technology to connect all three-dimensional temperature fields according to the transition duration, so as to construct a time series demonstration model

[0029] A time series demonstration model refers to a model that visualizes time series data in three-dimensional space. Such a model can help analyze and understand the trends, seasonality, periodicity and other characteristics of a certain phenomenon over time. Through three-dimensional visualization, users can more intuitively observe the relationship between data in time, space and other variables

[0030] In S300, the specific steps are as follows

[0031] S301. Set the detection duration fe, obtain the duration time of the time series demonstration model, divide time by fe and round up to get the total number of time nodes ur. Uniformly set ur time nodes in the time series demonstration model, and analyze the three-dimensional temperature field under each time node

[0032] S302. Obtain the three-dimensional temperature field under the time node JD h , analyze the volume ratio of various materials in the brain pacemaker model therein, calculate the average temperature of the region occupied by the volume of each material, and substitute it into the formula to calculate the risk coefficient FX h of the time node JD h :

[0033]

[0034] In the formula, pu is the number of all material types in the brain pacemaker model, ZNk is the coefficient of thermal expansion of the k-th material, is the average temperature of the volume occupancy region of the k-th material, is the standard temperature of the k-th material.

[0035] S303. Calculate the risk coefficient for each time node, count the number sg of all time nodes, sort the risk coefficients of all time nodes in chronological order, and substitute them into the formula to calculate the risk index FZ:

[0036]

[0037] In the formula, FX m is the risk coefficient of the m-th time node, FX n is the risk coefficient of the n-th time node, FX n-1 is the risk coefficient of the (n - 1)-th time node.

[0038] S304. Set the risk index threshold fl. When the risk index is greater than fl, reset the sensing distance and substitute it into the COMSOL multiphysics simulation software to build a scenario model, simulate and analyze the three-dimensional temperature field, and calculate the risk index again to determine whether it is greater than fl. After setting the sensing distance jc times, screen and combine to obtain the sensing distance interval where the risk index is not greater than fl, and select the minimum value of the sensing distance interval as the warning distance.

[0039] S305. Set the risk coefficient threshold XS, mark the time nodes with risk coefficients greater than XS, and screen out the earliest time node JD first , calculate the duration sc between the time node JD first and the initial time of the time series demonstration model as the warning duration; generate a warning notification based on the warning distance and warning duration.

[0040] In S400, display the warning notification through the intelligent terminal visualization interface, and prompt the object through the warning notification to control the usage duration of the software application within the warning duration and keep the distance from the intelligent terminal at least exceeding the warning distance.

[0041] Collect the stay time period of the object using the software application through the intelligent terminal, and generate an operation record based on the changes in the sensing distance and signal frequency during the stay time period, and store it in the operation log and historical log.

[0042] A data analysis system for the health monitoring of brain pacemaker implant patients, including a data acquisition module, a data analysis module, a security management module, and a data storage module.

[0043] The data acquisition module collects sensing data, historical logs, and device parameters through the intelligent terminal.

[0044] The data analysis module is used to analyze historical logs to establish a line chart and set sampling points, screen and mark all sampling points, and then calculate prediction parameters.

[0045] Build a simulation scenario and set up a model. Establish a three-dimensional temperature field by marking the prediction parameters of sampling points. All three-dimensional temperature fields together form a time series demonstration model.

[0046] The safety management module sets time nodes in the time series demonstration model, calculates the risk coefficient of each time node according to device parameters, as well as the risk index of all time nodes, so as to calculate the warning distance and warning duration and generate a warning notice.

[0047] The data storage module generates an operation record based on the sensing data collected by the intelligent terminal and stores it in the historical log.

[0048] The data acquisition module includes a sensing data acquisition unit, a device parameter acquisition unit, and a historical log acquisition unit.

[0049] The sensing data acquisition unit is used to collect sensing data through the intelligent terminal, specifically including the sensing distance, signal frequency, and the software application currently in use. The sensing distance refers to the actual distance between the intelligent terminal and the object.

[0050] The device parameter acquisition unit is used to collect the parameter information of the brain pacemaker, specifically including a three-dimensional stereogram, actual volume, constituent materials, and the thermal expansion coefficient of each material.

[0051] The historical log acquisition unit is used to collect the operation logs of all software applications in the intelligent terminal. The operation log includes the operation records each time the software application is used.

[0052] Each operation record includes the stay time period, and the changes in the sensing distance and signal frequency during the stay time period. The stay time period refers to the time period when the object stays on the interface after clicking on the software application.

[0053] The data analysis module includes a prediction analysis unit and a scenario construction unit.

[0054] The prediction analysis unit is used to calculate the prediction distance and prediction frequency.

[0055] First, obtain the current time TI now , screen out all operation records of the software application in use, calculate the midpoint time according to the stay time period of each operation record, and classify all operation records with the same midpoint time corresponding to the same day into the same category.

[0056] Analyze TI now The moment TI corresponding to the date in a day sk, set the error time duration ac, and mark the moment corresponding to the date of the midpoint time within each category and TI sk The operation records with the difference less than ac are analyzed, and the duration of the stay time period of each marked operation record is calculated. The average value of the durations of all marked operation records is calculated as the prediction duration.

[0057] Secondly, obtain the marked operation record MR 1 The changes in the sensing distance and signal frequency within the stay time period in MR are obtained. First, a distance line graph is established with time as the horizontal axis and sensing distance as the vertical axis, and then a frequency line graph is established with time as the horizontal axis and signal frequency as the vertical axis. A distance line graph and a frequency line graph are established for each marked operation record respectively.

[0058] Set the sampling time duration ct, obtain the distance line graphs and frequency line graphs of all marked operation records, and set a sampling point every duration ct in each line graph. The standard deviation of the sensing distance of the sampling point i in all distance line graphs is used as the sensing coefficient, and the standard deviation of the signal frequency in all distance line graphs is used as the frequency coefficient.

[0059] Finally, calculate the sensing coefficient and frequency coefficient of each sampling point respectively, set the sensing coefficient threshold x and the frequency coefficient threshold y, and mark the sampling points with the sensing coefficient less than x and the frequency coefficient less than y.

[0060] The average value of the sensing distance of the marked sampling points in all distance line graphs is used as the predicted distance, and the average value of the signal frequency in all distance line graphs is used as the predicted frequency.

[0061] The scenario construction unit is used to construct a time series demonstration model.

[0062] First, use COMSOL multi-physics simulation software to construct a simulation scenario, build a human brain model and an intelligent terminal model, and build a brain pacemaker model within the human brain model according to the device parameters.

[0063] Secondly, obtain the predicted distance JL v and the predicted frequency PL v of the marked sampling point CY v , simulate and analyze the temperature distribution of the brain pacemaker model when the distance between the human brain model and the intelligent terminal model is JL v and the intelligent terminal is operating at the frequency of PL v , so as to establish a three-dimensional temperature field for the marked sampling point CY v .

[0064] Finally, a three-dimensional temperature field is established for each marked sampling point, all marked sampling points are sorted in chronological order, and the time duration between two adjacent marked sampling points is calculated as the transition duration between the corresponding two three-dimensional temperature fields. All three-dimensional temperature fields are smoothly connected according to the transition duration, thereby constructing a time-series demonstration model.

[0065] The calculation process of the three-dimensional temperature field is as follows:

[0066] The temperature of the electrode part of the brain pacemaker model rises after absorbing the electromagnetic loss of the intelligent terminal antenna electromagnetic field, and the solid heat transfer is used to calculate the electrode temperature field:

[0067]

[0068] The above formula shows that the change in electrode temperature is determined by the electrode's heat conduction ability and external heat sources. Among them, T is the transient temperature, t is the influence duration, ρ is the density of the electrode material, c is the specific heat capacity of the electrode material, and K heat is the heat transfer coefficient of the electrode. Q e is the electromagnetic energy absorbed by the electrode, and its definition is as follows:

[0069]

[0070] The above formula shows that the amount of electromagnetic energy absorbed by the electrode depends on the electrical parameters of its material. Among them, J is the current density of the electrode, σ is the electrical conductivity of the electrode material, and E is the electric field strength.

[0071] The brain tissue part in the human brain model will also absorb electromagnetic energy, resulting in its own temperature rise. Considering the influence of metabolic heat sources and blood perfusion on the brain tissue temperature, the Penns transient bioheat transfer equation is used to calculate the brain tissue temperature field:

[0072]

[0073] Based on the solid heat transfer, the above formula considers the influence of blood flow and metabolic activities on the brain tissue temperature field. Among them, ρ b is the blood density, C b is the blood heat capacity, ω b is the blood perfusion rate, T b is the blood temperature, Q met is the metabolic heat source, Q' e is the electromagnetic energy absorbed by the brain tissue.

[0074] The safety management module includes a risk prediction unit and an early warning management unit.

[0075] The risk prediction unit is used to calculate the risk coefficient and the risk index.

[0076] First, set the detection duration fe, obtain the duration time of the time series demonstration model, and round up the result of dividing time by fe to get the total number of time nodes ur.

[0077] Secondly, evenly set ur time nodes in the time series demonstration model, and analyze to obtain the three-dimensional temperature field under each time node. Obtain the three-dimensional temperature field at time node JD h Under it, analyze the volume ratios of various materials in the internal brain pacemaker model, calculate the average temperature of the region occupied by each material's volume, and thus calculate the risk coefficient at time node JD h of.

[0078] Finally, calculate the risk coefficients of each time node respectively, count the total number of all time nodes, sort the risk coefficients of all time nodes in chronological order, and calculate the risk index based on the risk coefficients of all time nodes.

[0079] The early warning management unit is used to calculate the early warning distance and early warning duration and generate an early warning notice.

[0080] First, set the risk index threshold fl. When the risk index is greater than fl, reset the sensing distance and substitute it into the COMSOL multi-physics simulation software to construct a scenario building model, simulate and analyze the three-dimensional temperature field, and calculate the risk index again to determine whether it is greater than fl.

[0081] After setting the sensing distance jc times, screen and combine to obtain the sensing distance interval where the risk index is not greater than fl, and select the minimum value of the sensing distance interval as the early warning distance.

[0082] Then, set the risk coefficient threshold XS, mark the time nodes with risk coefficients greater than XS, and screen out the earliest time node JD in chronological order first , calculate the time node JD first The duration sc between it and the initial time of the time series demonstration model is used as the early warning duration. Generate an early warning notice based on the early warning distance and early warning duration.

[0083] The data storage module displays the early warning notice through the intelligent terminal visualization interface, and prompts the object through the early warning notice to control the software usage duration and the distance from the intelligent terminal. Generate an operation record based on the sensing data collected by the intelligent terminal and store it in the operation log and historical log.

[0084] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0085] Precise safety management: The present invention calculates the risk coefficient and risk index by setting time nodes and generates a warning notice. The adoption of an active risk management strategy is relatively rare in the prior art, which is often limited to passive monitoring, resulting in users lacking necessary countermeasures when potential risks occur.

[0086] Deep data visualization: The present invention can generate visual warning information to help users more easily understand their health status and potential risks. The prior art provides relatively little in terms of data visualization, increasing the difficulty of interpretation for users.

[0087] Enhanced simulation and model construction capabilities: The present invention can dynamically simulate the brain pacemaker and the human brain model through COMSOL multi-physics simulation software to obtain a more accurate temperature distribution, while traditional technologies usually lack such simulation and dynamic analysis capabilities.

[0088] In summary, through systematic module design and advanced data analysis and management means, this technical solution significantly improves the health monitoring efficiency and accuracy for brain pacemaker implant recipients. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0090] Figure 1 is a flowchart of the data analysis method for health monitoring of brain pacemaker implant recipients according to the present invention;

[0091] Figure 2 is a structural diagram of the data analysis system for health monitoring of brain pacemaker implant recipients according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0092] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0093] Please refer to Figure 1 , the present invention provides a data analysis method for health monitoring of brain pacemaker implant recipients, including the following steps:

[0094] S100. When the object uses the smart terminal, collect sensing data, historical logs, and device parameters through the smart terminal.

[0095] S200. Analyze historical logs to create a line chart and set sampling points. After screening and marking all sampling points, calculate prediction parameters. Construct a simulation scenario and build a model. Establish a three-dimensional temperature field based on the prediction parameters of the marked sampling points, and all the three-dimensional temperature fields together form a time-series demonstration model.

[0096] S300. Set time nodes in the time-series demonstration model. Calculate the risk coefficient for each time node and the risk index for all time nodes based on device parameters, so as to calculate the warning distance and warning duration and generate a warning notice.

[0097] S400. Display the warning notice through the visualization interface of the intelligent terminal, and generate an operation record based on the sensing data collected by the intelligent terminal and store it in the historical log.

[0098] In S100, the object refers to the implantee of the brain pacemaker, and the intelligent terminal refers to a device that can perform data exchange, processing, and interaction through the Internet. The sensing data includes the sensing distance, signal frequency, and the software application currently in use. The sensing distance refers to the actual distance between the intelligent terminal and the object. The signal frequency refers to the radio frequency used when the intelligent terminal communicates with the base station.

[0099] When the object uses different software applications in the intelligent terminal, the change of the signal frequency is usually different. The main influencing factors include:

[0100] Application type: Real-time applications usually require low latency and high-frequency data transmission, so the signal frequency is high. Non-real-time applications can tolerate higher latency, so the signal frequency is low.

[0101] Hardware performance: The hardware performance of the device will affect the signal frequency when the application runs. High-performance devices can process more signals faster.

[0102] User behavior: The operation habits of the user in the application will also affect the signal frequency. Some applications may increase the signal frequency when the user is active.

[0103] Program design: The coding and design of the application determine how it interacts with the network. Some applications may use technologies such as data compression and delayed sending, thus affecting the signal frequency.

[0104] The historical log includes the operation logs of all software applications in the intelligent terminal. The operation log includes the operation records each time the software application is used. Each operation record includes the stay time period, and the changes in the sensing distance and signal frequency during the stay time period. The stay time period refers to the time period when the object stays on the interface after clicking on the software application to enter. The device parameters refer to the parameter information of the brain pacemaker worn by the object, including the three-dimensional stereogram, actual volume, composition materials, and the thermal expansion coefficient of each material.

[0105] The coefficient of thermal expansion is used to describe the degree of change in the volume of a material when the temperature changes. Specifically, it refers to the ratio of the increase or decrease in volume per unit volume of the material for every one-degree Celsius increase or decrease in temperature. Different materials have different coefficients of thermal expansion. Generally speaking, metals have relatively large coefficients of thermal expansion, while ceramics and glass have relatively small coefficients of thermal expansion.

[0106] In S200, the specific steps are as follows:

[0107] S201. When the object clicks to enter the software application SW, obtain the current time TI now and the operation log OR of the software application SW u . Filter out all operation records in the operation log OR u . Calculate the midpoint time according to the stay time period of each operation record, and classify all operation records with the midpoint time corresponding to the same day into the same category.

[0108] Analyze TI now the moment of the corresponding date in a day, set the error duration ac, and mark the operation records whose difference between the moment corresponding to the midpoint time within each category and TI sk is less than ac. Analyze the duration of the stay time period of each marked operation record, and calculate the average value of the durations of all marked operation records as the predicted duration. sk 1

[0109] S202. Obtain the change situations of the sensing distance and signal frequency within the stay time period in the marked operation record MR 1 . First, establish a distance line graph with time as the horizontal axis and sensing distance as the vertical axis, and then establish a frequency line graph with time as the horizontal axis and signal frequency as the vertical axis, and establish a distance line graph and a frequency line graph for each marked operation record respectively.

[0110] Set the sampling duration ct, obtain the distance line graphs and frequency line graphs of all marked operation records, and set a sampling point every duration ct in each line graph. Take the standard deviation of the sensing distance of the sampling point i in all distance line graphs as the sensing coefficient, and the standard deviation of the signal frequency in all distance line graphs as the frequency coefficient.

[0111] S203. Calculate the sensing coefficient and frequency coefficient of each sampling point respectively, set the sensing coefficient threshold x and the frequency coefficient threshold y, and mark the sampling points with the sensing coefficient less than x and the frequency coefficient less than y. Take the average value of the sensing distance of the marked sampling points in all distance line graphs as the predicted distance, and the average value of the signal frequency in all distance line graphs as the predicted frequency.

[0112] COMSOL multi-physics field simulation software was used to construct a simulation scene, and a human brain model and an intelligent terminal model were built. A brain pacemaker model was built in the human brain model according to the device parameters.

[0113] When the subject uses the smart terminal, the radio frequency electromagnetic field generated by the signal antenna will produce thermal effects on the brain pacemaker and brain tissue. During the heat conduction process between the brain tissue and the electrode, the temperature increase of both will cause them to produce thermal strain, thereby changing their volume. The different thermal strains of the electrode and the brain tissue will cause stress at the contact interface between the two, which will cause the electrode to displace. Due to ethical restrictions, it is impossible to directly measure the thermal effect and displacement of living brain tissue after electrode implantation. Therefore, COMSOL multi-physics field simulation software is used to construct a simulation scene, and a model is built to realize the calculation and simulation of the three-dimensional temperature field.

[0114] S204, obtain the marked sampling point CY v The predicted distance JL v and the predicted frequency PL v , the distance between the simulated human brain model and the intelligent terminal model is JL v And the intelligent terminal is at the frequency PL v Temperature distribution of the brain pacemaker model during operation, thus marking the sampling point CY v Establish a three-dimensional temperature field.

[0115] When establishing a three-dimensional temperature field, it is necessary to consider the interval length between the object's previous use of other software applications. When the interval length is not sufficient to support the temperature of the previously established three-dimensional temperature field to recover to the normal temperature when the smart terminal has not been used for a long time, the temperature cooling effect should also be considered based on the interval length to improve the data accuracy of the three-dimensional temperature field.

[0116] A three-dimensional temperature field is established for each marked sampling point, all marked sampling points are sorted in chronological order, and the duration between two adjacent marked sampling points is calculated as the transition duration of the corresponding two three-dimensional temperature fields. All three-dimensional temperature fields are connected according to the transition duration using smooth transition technology to construct a time series demonstration model.

[0117] A time series demonstration model is a model that visualizes time series data in three-dimensional space. This model can help analyze and understand the trend, seasonality, and periodicity of a phenomenon over time. Through three-dimensional visualization, users can more intuitively observe the relationship between data in time, space, and other variables.

[0118] In S300, the specific steps are as follows:

[0119] S301. Set the detection duration fe, obtain the duration time of the time series demonstration model, round up the result of dividing time by fe to get the total number of time nodes ur. Uniformly set ur time nodes in the time series demonstration model, and analyze to obtain the three-dimensional temperature field at each time node.

[0120] S302. Obtain the three-dimensional temperature field at time node JD h , analyze the volume ratios of various materials in the endbrain pacemaker model, calculate the average temperature of the region occupied by the volume of each material, and substitute it into the formula to calculate the risk coefficient FX h at time node JD h :

[0121]

[0122] In the formula, pu is the total number of material types in the brain pacemaker model, ZN k is the thermal expansion coefficient of the k-th material, is the average temperature of the region occupied by the volume of the k-th material, is the standard temperature of the k-th material.

[0123] S303. Calculate the risk coefficient of each time node respectively, count the number sg of all time nodes, sort the risk coefficients of all time nodes in chronological order, and substitute them into the formula to calculate the risk index FZ:

[0124]

[0125] In the formula, FX m is the risk coefficient of the m-th time node, FX n is the risk coefficient of the n-th time node, FX n-1 is the risk coefficient of the (n - 1)-th time node.

[0126] S304. Set the risk index threshold fl. When the risk index is greater than fl, reset the sensing distance and substitute it into the COMSOL multiphysics simulation software to construct a scenario building model, simulate and analyze the three-dimensional temperature field, and calculate the risk index again to determine whether it is greater than fl. After setting the sensing distance jc times, screen and combine to obtain the sensing distance interval where the risk index is not greater than fl, and select the minimum value of the sensing distance interval as the warning distance.

[0127] S305. Set the risk coefficient threshold XS, mark the time nodes with risk coefficients greater than XS, and screen out the earliest time node JD first in chronological order, and calculate time node JD firstThe duration sc between the initial time of the time series demonstration model is used as the early warning duration; an early warning notification is generated based on the early warning distance and the early warning duration.

[0128] In S400, the early warning notification is displayed through the intelligent terminal visualization interface, and the object is prompted through the early warning notification to control the usage duration of the software application within the early warning duration and the distance from the intelligent terminal is at least more than the early warning distance.

[0129] The intelligent terminal is used to collect the stay time period of the object using the software application, and the change of the induction distance and the signal frequency within the stay time period is used to generate an operation record, which is stored in the operation log and the historical log.

[0130] Please refer to Figure 2 , the present invention provides a data analysis system for health monitoring of brain pacemaker implant recipients, including a data collection module, a data analysis module, a security management module, and a data storage module.

[0131] The data collection module collects induction data, historical logs, and device parameters through an intelligent terminal.

[0132] The data analysis module is used to analyze the historical log to establish a line chart and set sampling points, and calculate prediction parameters after screening and marking all sampling points.

[0133] A simulation scenario is constructed and a model is built, and a three-dimensional temperature field is established through the prediction parameters of the marked sampling points, and all three-dimensional temperature fields are jointly formed into a time series demonstration model.

[0134] The security management module sets time nodes in the time series demonstration model, calculates the risk coefficient of each time node according to the device parameters, and the risk index of all time nodes, so as to calculate the early warning distance and the early warning duration and generate an early warning notification.

[0135] The data storage module generates an operation record according to the induction data collected by the intelligent terminal and stores it in the historical log.

[0136] The data collection module includes an induction data collection unit, a device parameter collection unit, and a historical log collection unit.

[0137] The induction data collection unit is used to collect induction data through an intelligent terminal, specifically including the induction distance, the signal frequency, and the software application currently in use. The induction distance refers to the actual distance between the intelligent terminal and the object.

[0138] The device parameter collection unit is used to collect the parameter information of the brain pacemaker, specifically including a three-dimensional stereogram, the actual volume, the composition materials, and the thermal expansion coefficient of each material.

[0139] The historical log collection unit is used to collect the operation logs of all software applications in the intelligent terminal. The operation logs include the operation records each time when a software application is used.

[0140] Each operation record includes a stay time period, and the change conditions of the sensing distance and signal frequency within the stay time period. The stay time period refers to the time period when the object stays on the interface after clicking on the software application to enter.

[0141] The data analysis module includes a prediction analysis unit and a scenario construction unit.

[0142] The prediction analysis unit is used to calculate the predicted distance and predicted frequency.

[0143] First, obtain the current time TI now , filter out all operation records of the software applications that are being used, calculate the midpoint time according to the stay time period of each operation record, and classify all operation records with the midpoint time corresponding to the same date into the same category.

[0144] Analyze TI now the moment TI of the corresponding date in a day sk , set the error duration ac, mark the operation records whose moment of the midpoint time corresponding date within each category has a difference less than ac from TI sk , analyze the duration of the stay time period of each marked operation record, and calculate the average value of the durations of all marked operation records as the predicted duration.

[0145] Secondly, obtain the change conditions of the sensing distance and signal frequency within the stay time period in the marked operation record MR 1 , first establish a distance line graph with time as the horizontal axis and sensing distance as the vertical axis, and then establish a frequency line graph with time as the horizontal axis and signal frequency as the vertical axis, and establish a distance line graph and a frequency line graph for each marked operation record respectively.

[0146] Set the sampling duration ct, obtain the distance line graphs and frequency line graphs of all marked operation records, and set a sampling point every duration ct in each line graph. Take the standard deviation of the sensing distance of the sampling point i in all distance line graphs as the sensing coefficient, and the standard deviation of the signal frequency in all distance line graphs as the frequency coefficient.

[0147] Finally, calculate the sensing coefficient and frequency coefficient of each sampling point respectively, set the sensing coefficient threshold x and the frequency coefficient threshold y, and mark the sampling points with the sensing coefficient less than x and the frequency coefficient less than y.

[0148] Take the average value of the sensing distance of the marked sampling points in all distance line graphs as the predicted distance, and the average value of the signal frequency in all distance line graphs as the predicted frequency.

[0149] The scenario construction unit is used to construct a time series demonstration model.

[0150] First, use the COMSOL multi-physics simulation software to construct a simulation scenario, build a human brain model and an intelligent terminal model, and build a brain pacemaker model in the human brain model according to the device parameters.

[0151] Secondly, obtain the predicted distance JL v of the marked sampling point CY v and the predicted frequency PL v , simulate and analyze the temperature distribution of the brain pacemaker model when the distance between the human brain model and the intelligent terminal model is JL v and the intelligent terminal is running at the frequency of PL v , so as to establish a three-dimensional temperature field for the marked sampling point CY v .

[0152] Finally, establish a three-dimensional temperature field for each marked sampling point, sort all the marked sampling points in chronological order, and calculate the duration between two adjacent marked sampling points as the transition duration of the corresponding two three-dimensional temperature fields. Smoothly connect all the three-dimensional temperature fields according to the transition duration, so as to construct a time series demonstration model.

[0153] The calculation process of the three-dimensional temperature field is as follows:

[0154] The temperature of the electrode part of the brain pacemaker model rises after absorbing the electromagnetic loss of the electromagnetic field of the intelligent terminal antenna. Use the solid heat transfer to calculate the electrode temperature field:

[0155]

[0156] The above formula shows that the change of the electrode temperature is determined by the electrode heat conduction ability and the external heat source. Among them, T is the transient temperature, t is the influence duration, ρ is the density of the electrode material, c is the specific heat capacity of the electrode material, and K heat is the heat transfer coefficient of the electrode. Q e is the electromagnetic energy absorbed by the electrode, and its definition is as follows:

[0157]

[0158] The above formula shows that the amount of electromagnetic energy absorbed by the electrode depends on the electrical parameters of its material. Among them, J is the current density of the electrode, σ is the conductivity of the electrode material, and E is the electric field strength.

[0159] The brain tissue part in the human brain model will also absorb electromagnetic energy, resulting in its own temperature rise. Considering the influence of metabolic heat source and blood perfusion on the brain tissue temperature, use the Penns transient bio-heat transfer equation to calculate the brain tissue temperature field:

[0160]

[0161] Based on the heat transfer in solids, the influence of blood flow and metabolic activities on the temperature field of the brain tissue is considered. Among them, ρ b is the blood density, C b is the blood heat capacity, ω b is the blood perfusion rate, T b is the blood temperature, Q met is the metabolic heat source, and Q' e is the electromagnetic energy absorbed by the brain tissue.

[0162] The safety management module includes a risk prediction unit and a warning management unit.

[0163] The risk prediction unit is used to calculate the risk coefficient and the risk index.

[0164] First, set the detection duration fe, obtain the duration time of the time series demonstration model, divide time by fe and round up to get the total number of time nodes ur.

[0165] Secondly, uniformly set ur time nodes in the time series demonstration model, and analyze to obtain the three-dimensional temperature field under each time node. Obtain the three-dimensional temperature field under the time node JD h and analyze the volume ratio of various materials in the endbrain pacemaker model under it, calculate the average temperature of the area occupied by the volume of each material, so as to calculate the risk coefficient of the time node JD h .

[0166] Finally, calculate the risk coefficients of each time node respectively, count the total number of all time nodes, sort the risk coefficients of all time nodes in chronological order, and calculate the risk index according to the risk coefficients of all time nodes.

[0167] The warning management unit is used to calculate the warning distance and the warning duration and generate a warning notice.

[0168] First, set the risk index threshold fl. When the risk index is greater than fl, reset the sensing distance and substitute it into the COMSOL multi-physics simulation software to construct a scenario building model, simulate and analyze the three-dimensional temperature field, and calculate the risk index again and judge whether it is greater than fl.

[0169] After setting the sensing distance jc times, screen and combine to obtain the sensing distance interval where the risk index is not greater than fl, and select the minimum value of the sensing distance interval as the warning distance.

[0170] Then set the risk coefficient threshold XS, mark the time nodes with a risk coefficient greater than XS, and screen out the earliest time node JD first in chronological order, and calculate the time node JD firstThe duration sc between the initial time of the time series demonstration model is used as the early warning duration. An early warning notification is generated based on the early warning distance and the early warning duration.

[0171] The data storage module displays the early warning notification through the intelligent terminal visualization interface, and prompts the object to control the software usage duration and the distance from the intelligent terminal through the early warning notification. An operation record is generated based on the sensing data collected by the intelligent terminal and stored in the operation log and the historical log.

[0172] Example 1:

[0173] Assume the time node JD 1 In the three-dimensional temperature field at the following time node JD, the brain pacemaker model is composed of two materials, A1 and A2. The average temperatures of the regions they occupy are 36.8 °C and 36.4 °C respectively, and the thermal expansion coefficients are 15×10 -6 / °C and 6×10 -6 / °C respectively. The standard temperature is 20 °C. Substitute into the formula to calculate the risk coefficient at the time node JD 1 :

[0174] (15×10 -6 ×|36.8 - 20|)+(6×10 -6 ×|36.4 - 20|) = 0.0003504

[0175] Then the risk coefficient at the time node JD 1 is 0.0003504.

[0176] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0177] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data analysis method for health monitoring of a person with a brain pacemaker implant, characterized in that: The method comprises the following steps: S100, when the subject uses the smart terminal, the sensing data, historical logs and device parameters are collected through the smart terminal; S200, analyzing historical logs to establish a line graph and set sampling points, and calculating prediction parameters after screening and marking all sampling points; constructing a simulation scene and building a model, establishing a three-dimensional temperature field by marking the prediction parameters of the sampling points, and all three-dimensional temperature fields are jointly constructed into a time series demonstration model; S300, setting time nodes in the time series demonstration model, calculating the risk coefficient of each time node and the risk index of all time nodes according to the equipment parameters, thereby calculating the warning distance and warning duration and generating a warning notification; S400: Display the warning notification through the visual interface of the smart terminal, generate an operation record based on the sensing data collected by the smart terminal, and store it in a history log.

2. The data analysis method for health monitoring of a person with a brain pacemaker implant according to claim 1, characterized in that: In S100, the object refers to a person with a brain pacemaker implant, and the smart terminal refers to a device capable of exchanging, processing and interacting with data through the Internet; the sensing data includes the sensing distance, the signal frequency and the software application currently being used; the sensing distance refers to the actual distance between the smart terminal and the object; the signal frequency refers to the radio frequency used when the smart terminal communicates with the base station; The historical log includes the operation log of all software applications in the smart terminal, and the operation log includes the operation record of each use of the software application; each operation record includes the dwell time period, and the changes in the sensing distance and signal frequency during the dwell time period; the dwell time period refers to the time period that the subject stays on the interface after clicking on the software application to enter; the device parameters refer to the parameter information of the brain pacemaker worn by the subject, including the three-dimensional stereogram, actual volume, constituent materials and the thermal expansion coefficient of each material.

3. The data analysis method for health monitoring of a person with a brain pacemaker implant according to claim 2, characterized in that: In S200, the specific steps are as follows: S201. When the object clicks to enter the software application SW, obtain the current time TI now And the operation log of the software application SW u ; Filter out operation logs OR u All operation records in the TI are analyzed, and the midpoint time is calculated according to the stay time period of each operation record. All operation records with the midpoint time corresponding to the same day are classified into the same category; now The time of day TI of the corresponding date sk , set the error duration ac, mark the time of the corresponding date of the midpoint time in each category and TI sk For operation records with a difference value less than ac, analyze the duration of each marked operation record's stay time period and calculate the average duration of all marked operation records as the predicted duration; S202, obtain the changes of the sensing distance and signal frequency in the stay time period in the marking operation record MR1, first establish a distance line graph with time as the horizontal axis and the sensing distance as the vertical axis, and then establish a frequency line graph with time as the horizontal axis and the signal frequency as the vertical axis, and respectively establish a distance line graph and a frequency line graph for each marking operation record; set the sampling time ct, obtain the distance line graph and the frequency line graph of all marking operation records, and set a sampling point in each line graph every time ct; take the standard deviation of the sensing distance of the sampling point i in all the distance line graphs as the induction coefficient, and the standard deviation of the signal frequency in all the distance line graphs as the frequency coefficient; S203, respectively calculating the inductance coefficient and frequency coefficient of each sampling point, setting the inductance coefficient threshold x and the frequency coefficient threshold y, marking the sampling points whose inductance coefficient is less than x and whose frequency coefficient is less than y; taking the average value of the induction distance of the marked sampling point in all distance line graphs as the predicted distance, and taking the average value of the signal frequency in all distance line graphs as the predicted frequency; using COMSOL multi-physics field simulation software to construct a simulation scene, and building a human brain model and an intelligent terminal model, and building a brain pacemaker model in the human brain model according to the device parameters; S204, obtain the marked sampling point CY v The predicted distance JL v and the predicted frequency PL v , the distance between the simulated human brain model and the intelligent terminal model is JL v And the intelligent terminal is at the frequency PL v Temperature distribution of the brain pacemaker model during operation, thus marking the sampling point CY v Establish three-dimensional temperature field; A three-dimensional temperature field is established for each marked sampling point respectively, all marked sampling points are sorted in chronological order, and the duration between two adjacent marked sampling points is calculated as the transition duration of the corresponding two three-dimensional temperature fields; smooth transition technology is used to connect all three-dimensional temperature fields according to the transition duration, thereby constructing a time series demonstration model.

4. The data analysis method for health monitoring of a person with a brain pacemaker implant according to claim 3, characterized in that: In S300, the specific steps are as follows: S301, set the detection duration fe, obtain the duration time of the time series demonstration model, divide time by fe and round up to obtain the total number of time nodes ur; evenly set ur time nodes in the time series demonstration model, and analyze and obtain the three-dimensional temperature field at each time node; S302, obtain time node JD h The three-dimensional temperature field under the model is analyzed, and the volume proportion of various materials in the internal brain pacemaker model is analyzed. The average temperature of the area occupied by each material volume is calculated, and the time node JD is calculated by substituting it into the formula h Risk Factor FX h : Where pu is the number of all material types in the brain pacemaker model, ZN k is the thermal expansion coefficient of the kth material, is the average temperature of the volume occupied by the kth material, is the standard temperature of the kth material; S303, respectively calculate the risk coefficient of each time node, count the number of all time nodes sg, sort the risk coefficients of all time nodes in chronological order, and substitute them into the formula to calculate the risk index FZ: In the formula, FX m is the risk factor at the mth time node, FX n is the risk factor at the nth time node, FX n-1 is the risk coefficient of the n-1th time node; S304, setting a risk index threshold fl. When the risk index is greater than fl, re-setting the sensing distance and substituting it into the COMSOL multi-physics field simulation software to build a scene model, simulating and analyzing the three-dimensional temperature field, and recalculating the risk index to determine whether it is greater than fl. After setting the sensing distance jc times, screening and combining to obtain the sensing distance interval whose risk index is not greater than fl, and selecting the minimum value of the sensing distance interval as the warning distance; S305. Set a risk factor threshold XS, mark the time nodes where the risk factor is greater than XS, and select the earliest time node JD in chronological order. first , calculate the time node JD first The time length sc between the initial time of the time series demonstration model is used as the warning time length; Generate warning notifications based on warning distance and warning duration.

5. The data analysis method for health monitoring of a person with a brain pacemaker implant according to claim 4, characterized in that: In S400, a warning notification is displayed through a visual interface of the smart terminal, and the warning notification prompts the object to control the use of the software application time within the warning time, and the distance from the smart terminal exceeds the warning distance at least; The intelligent terminal collects the time period during which the object uses the software application, as well as the changes in the sensing distance and signal frequency during the time period to generate operation records, which are stored in the operation log and history log.

6. A data analysis system for health monitoring of patients with brain pacemaker implants, characterized in that: The system includes a data acquisition module, a data analysis module, a security management module and a data storage module; The data acquisition module collects sensing data, historical logs and equipment parameters through intelligent terminals; The data analysis module is used to analyze historical logs to create a line graph and set sampling points, and to calculate the prediction parameters after screening and marking all sampling points; Construct simulation scenarios and build models, establish three-dimensional temperature fields by marking the prediction parameters of sampling points, and all three-dimensional temperature fields are combined into a time series demonstration model; The safety management module sets time nodes in the time series demonstration model, calculates the risk coefficient of each time node and the risk index of all time nodes according to the equipment parameters, and thus calculates the warning distance and warning duration and generates a warning notification; The data storage module generates operation records based on the sensing data collected by the intelligent terminal and stores them in the historical log.

7. The data analysis system for health monitoring of patients with brain pacemaker implants according to claim 6, characterized in that: The data acquisition module includes a sensing data acquisition unit, a device parameter acquisition unit, and a historical log acquisition unit; The sensing data acquisition unit is used to collect sensing data through the smart terminal, including sensing distance, signal frequency and the software application currently in use. The sensing distance refers to the actual distance between the smart terminal and the object; The device parameter acquisition unit is used to acquire parameter information of the brain pacemaker, including three-dimensional stereogram, actual volume, constituent materials and thermal expansion coefficient of each material; The history log collection unit is used to collect the operation logs of all software applications in the intelligent terminal, and the operation logs include the operation records of each use of the software application; Each operation record includes the dwell time period, as well as the changes in the sensing distance and signal frequency during the dwell time period; the dwell time period refers to the time period during which the object stays on the interface after clicking on the software application to enter.

8. The data analysis system for health monitoring of patients with brain pacemaker implants according to claim 7, characterized in that: The data analysis module includes a prediction analysis unit and a scenario construction unit; The prediction analysis unit is used to calculate the prediction distance and prediction frequency; First, get the current time TI now , filter out all operation records of the software application in use, calculate the midpoint time according to the stay time period of each operation record, and classify all operation records whose midpoint time corresponds to the same day into the same category; Analyze TI now The time of day TI of the corresponding date sk , set the error duration ac, mark the time of the corresponding date of the midpoint time in each category and TI sk For operation records with a difference value less than ac, analyze the duration of each marked operation record's stay time period and calculate the average duration of all marked operation records as the predicted duration; Secondly, obtain the changes of the sensing distance and signal frequency in the stay time period in the marking operation record MR1, first establish a distance line graph with time as the horizontal axis and the sensing distance as the vertical axis, and then establish a frequency line graph with time as the horizontal axis and the signal frequency as the vertical axis, and respectively establish a distance line graph and a frequency line graph for each marking operation record; Set the sampling time ct, obtain the distance line graph and frequency line graph of all marking operation records, set a sampling point in each line graph every time ct; take the standard deviation of the sensing distance of sampling point i in all distance line graphs as the sensing coefficient, and the standard deviation of the signal frequency in all distance line graphs as the frequency coefficient; Finally, the inductance coefficient and frequency coefficient of each sampling point are calculated respectively, the inductance coefficient threshold x and the frequency coefficient threshold y are set, and the sampling points whose inductance coefficient is less than x and whose frequency coefficient is less than y are marked; The average of the sensing distances of the marked sampling points in all distance line graphs is taken as the predicted distance, and the average of the signal frequencies in all distance line graphs is taken as the predicted frequency; The scenario construction unit is used to construct a time series demonstration model; First, the COMSOL multi-physics simulation software was used to build a simulation scenario, and a human brain model and an intelligent terminal model were built. A brain pacemaker model was built in the human brain model according to the device parameters. Secondly, obtain the marked sampling point CY v The predicted distance JL v and the predicted frequency PL v , the distance between the simulated human brain model and the intelligent terminal model is JL v And the intelligent terminal is at the frequency PL v Temperature distribution of the brain pacemaker model during operation, thus marking the sampling point CY v Establish three-dimensional temperature field; Finally, a three-dimensional temperature field is established for each marked sampling point, all marked sampling points are sorted in chronological order, and the duration between two adjacent marked sampling points is calculated as the transition duration of the corresponding two three-dimensional temperature fields; all three-dimensional temperature fields are smoothly connected according to the transition duration to construct a time series demonstration model.

9. The data analysis system for health monitoring of patients with brain pacemaker implants according to claim 8, characterized in that: The safety management module includes a risk prediction unit and an early warning management unit; The risk prediction unit is used to calculate the risk coefficient and risk index; First, set the detection duration fe, obtain the duration time of the time series demonstration model, divide time by fe and round up to get the total number of time nodes ur; Secondly, ur time nodes are evenly set in the time series demonstration model, and the three-dimensional temperature field at each time node is analyzed; the JD of the time node is obtained. h The three-dimensional temperature field under the circumference of the brain pacemaker model is analyzed, and the volume proportion of various materials in the model is analyzed to calculate the average temperature of the area occupied by each material volume, so as to calculate the JD at the time node h The risk factor of Finally, the risk coefficient of each time node is calculated respectively, the number of all time nodes is counted, the risk coefficients of all time nodes are sorted in chronological order, and the risk index is calculated based on the risk coefficients of all time nodes; The warning management unit is used to calculate the warning distance and warning duration and generate a warning notification; First, set the risk index threshold fl. When the risk index is greater than fl, reset the sensing distance and substitute it into the COMSOL multi-physics field simulation software to build a scene model, simulate and analyze the three-dimensional temperature field, and calculate the risk index again to determine whether it is greater than fl. After setting the sensing distance jc times, the sensing distance interval with a risk index not greater than fl is screened and combined, and the minimum value of the sensing distance interval is selected as the warning distance; Then set the risk factor threshold XS, mark the time nodes where the risk factor is greater than XS, and select the earliest time node JD in chronological order first , calculate the time node JD first The time length sc between the initial time of the time series demonstration model is used as the warning time length; Generate warning notifications based on warning distance and warning duration.

10. The data analysis system for health monitoring of patients with brain pacemaker implants according to claim 9, characterized in that: The data storage module displays the warning notification through the smart terminal visual interface, and prompts the object to control the software usage time and the distance from the smart terminal through the warning notification; generates operation records based on the sensing data collected by the smart terminal and stores them in the operation log and history log.

Images