A method and system for assisting management in reducing the risk of preventable death
By performing band division and feature calculation of ECG data to determine abnormal ECG data, the problem of insensitive ECG data processing in traditional technology is solved, the detection accuracy is improved, and the risk of death caused by heart disease is reduced.
Patent Information
- Application Number
- CN202411259731.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-09-10
AI Technical Summary
Traditional electrocardiogram data processing ignores the characteristics of the correlation changes between the pre- and post-ECG laws and is insensitive to abnormal fluctuations in the electrocardiogram signal data, resulting in low accuracy of the detection results and cannot effectively reduce the risk of preventable death caused by heart disease.
By collecting the electrocardiogram signal data of the human body's preset time period, it is divided into band signals. Each band represents a complete cardiac change cycle, calculate the ECG changes characteristics and safety index, determine whether the data is abnormal, and use the band threshold and ECG changes. Indicators such as coefficient, fluctuation distance and distribution entropy improve detection accuracy.
It improves the accuracy of electrocardiogram detection, can accurately obtain the changing characteristics of the cardiac change cycle, and calculates the safety index based on the changing characteristics within different cycles, effectively reducing the risk of preventable death.
Smart Images

Figure CN118787364B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing, and in particular to an auxiliary management method and system for reducing the risk of preventable death. Background Art
[0002] In recent years, with the increase of urban life pressure, fragmented entertainment has continuously occupied life time, leading to irregular diet and work and rest, the incidence of heart disease has continued to rise, and the age characteristics of the onset population are gradually becoming younger. Accidental death caused by heart disease has become a major risk factor threatening human life and health. Therefore, it is necessary to accurately analyze the changes in electrocardiogram potential data and effectively obtain the trauma information implicit in the electrocardiogram potential change data to effectively reduce the risk of accidental death.
[0003] The traditional ECG data processing ignores the changing characteristics of the regular correlation between the ECG data before and after, and is insensitive to abnormal fluctuations in ECG signal data, resulting in low accuracy of detection results. Summary of the invention
[0004] The present invention provides an auxiliary management method and system for reducing the risk of preventable death, and the method can improve the accuracy of electrocardiogram detection.
[0005] In a first aspect, the present application provides an auxiliary management method for reducing the risk of preventable death, comprising:
[0006] Collect the ECG signal data corresponding to each moment in the preset time period of the human body;
[0007] Dividing the electrocardiogram signal data in the preset time period into at least one band signal, each band signal representing the variation characteristics of a complete cardiac variation cycle;
[0008] Calculate the ECG signal data security index at the current moment based on the ECG change characteristics of signals in different bands;
[0009] Determine whether the ECG data is abnormal based on the ECG signal data safety index at the current moment.
[0010] Optionally, dividing the electrocardiogram signal data in the preset time period into at least one band signal includes:
[0011] Divide the ECG signal data corresponding to each moment in the preset time period into data slices of length n;
[0012] Calculate the band threshold corresponding to the data slice;
[0013] The electrocardiographic signal data in the preset time period is divided into at least one band signal based on the band threshold, and the band signal includes electrocardiographic signal data corresponding to multiple moments.
[0014] Optionally, dividing the electrocardiogram signal data in the preset time period into at least one band signal based on the band threshold comprises:
[0015] The ECG signal data corresponding to the moment greater than the band threshold is used as the starting point of the band signal, and the ECG signal data corresponding to the next moment greater than the band threshold is used as the ending point of the previous band signal and the starting point of the next band signal, and then the ECG signal data in the preset time period is divided to obtain at least one band signal.
[0016] Optionally, calculating the band threshold corresponding to the data slice includes:
[0017] Calculate the ECG coefficient of the data slice at the current moment in different dimensions;
[0018] Calculate the band threshold corresponding to the data slice based on the ECG mutation coefficient;
[0019] Among them, the band threshold corresponding to the data slice is calculated using the following formula:
[0020] ;
[0021] in, Represents the threshold adjustment parameter, which is used to adjust the detail changes in the band signal division process. Indicates the current time The length obtained by dividing is The maximum value in the data slice of n Indicates the length of the data slice, Indicates the band threshold corresponding to the data slice at the current time t.
[0022] Optionally, calculating the ECG signal data safety index at the current moment based on ECG change characteristics of signals in different bands includes:
[0023] Calculate the ECG signal fluctuation distance at the current moment based on the difference between the ECG mutation coefficient corresponding to the current moment and the ECG mutation coefficient corresponding to the k moment, and the number of band signals from the current moment to the k moment; the ECG variation coefficient represents the ECG variation characteristics;
[0024] The ECG signal data safety index at the current moment is calculated based on the ECG signal fluctuation distance at the current moment.
[0025] Optionally, the ECG signal fluctuation distance at the current moment is calculated using the following formula:
[0026] ;
[0027] in, Indicates the ECG mutation coefficient corresponding to the current time t, represents the ECG mutation coefficient corresponding to time k, Indicates the number of central electrical signal data in the band signal. Indicates the density of the band signal from the current moment to the k moment.
[0028] Optionally, calculating the ECG signal data safety index at the current moment based on the ECG signal fluctuation distance at the current moment includes:
[0029] Quantify the ECG signal fluctuation distance at the current moment into Z different intervals;
[0030] Calculate the data distribution entropy of the ECG signal corresponding to each interval, and then obtain the data distribution entropy of the ECG signal corresponding to the current moment;
[0031] The ECG signal data security index at the current moment is calculated based on the ECG signal data distribution entropy corresponding to the current moment.
[0032] Optionally, calculating the distribution entropy of the ECG signal data corresponding to each interval, and then obtaining the distribution entropy of the ECG signal data corresponding to the current moment, includes:
[0033] The following formula is used to calculate the distribution entropy of the ECG signal data corresponding to the current moment:
[0034] ;
[0035] in, Representation interval h The numerical value of the ECG signal distribution frequency is calculated as follows: ,in For interval The number of ECG signal values at different times in the ECG signal fluctuation distance interval corresponding to the quantization, represents the logarithmic function with base 2, Z represents the number of intervals, Represents the distribution entropy of the ECG signal data corresponding to the current time t.
[0036] Optionally, the ECG signal data security index at the current moment is calculated based on the ECG signal data distribution entropy corresponding to the current moment, including:
[0037] The current ECG signal data security index is calculated using the following formula:
[0038] ;
[0039] in, Indicates the total number of band signals. It indicates the The ECG signal data sequence of band signals, Indicates The ECG signal data sequence of band signals, It represents the distance between two different sequences. Indicates the length of the central electric signal data sequence of the band signal. Indicates k The distribution entropy of the data slice at time i in the band signal, Indicates k+1 The distribution entropy of the data slice at time i in the band signal.
[0040] In a second aspect, the present application provides an auxiliary management system for reducing the risk of preventable death, comprising:
[0041] The acquisition module is used to collect the ECG signal data corresponding to each moment in a preset time period of the human body;
[0042] A division module, used for dividing the electrocardiogram signal data in the preset time period into at least one band signal, each band signal representing the change characteristics of a complete cardiac change cycle;
[0043] A calculation module, used for calculating the ECG signal data safety index at the current moment based on each band signal;
[0044] The determination module is used to determine whether the ECG data is abnormal based on the ECG signal data safety index at the current moment.
[0045] The beneficial effects of the present application are different from the prior art. The auxiliary management and system for reducing the risk of preventable death of the present application include: collecting ECG signal data corresponding to each moment in a preset time period of the human body; dividing the ECG signal data in the preset time period into at least one band signal, each band signal represents the change characteristics of a complete cardiac change cycle; calculating the ECG signal data safety index at the current moment based on the ECG change characteristics corresponding to multiple moments in each band signal; determining whether the ECG data is abnormal based on the ECG signal data safety index at the current moment. This method accurately obtains the change characteristics of a complete cardiac change cycle, and calculates the safety index by combining the ECG change characteristics in different cycles, which can improve the accuracy of ECG detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 It is a flow chart of an embodiment of the auxiliary management method for reducing the risk of preventable death of the present invention;
[0047] Figure 2 for Figure 1 A schematic flow chart of an embodiment of step S12;
[0048] Figure 3 for Figure 1 A schematic flow chart of an embodiment of step S13;
[0049] Figure 4 It is a structural schematic diagram of an embodiment of the auxiliary management system for reducing the risk of preventable death of the present invention. DETAILED DESCRIPTION
[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0051] The present application is described in detail below with reference to the accompanying drawings and embodiments.
[0052] See also Figure 1 , Figure 1 This is a schematic diagram of the structure of an embodiment of an auxiliary management method for reducing the risk of preventable death according to the present invention, which specifically includes:
[0053] Step S11: Collecting ECG signal data corresponding to each moment in a preset time period of the human body.
[0054] When the human myocardium is excited and contracts, a weak current is generated and transmitted to various parts of the human body. By placing guide electrodes on the body surface, the regular current changes in the cardiac cycle can be recorded, thereby obtaining corresponding electrocardiogram potential data. In order to ensure the scientificity and effectiveness of the electrocardiogram potential data collection process, the embodiment of the present invention adopts the common standard twelve-lead system to obtain the human electrocardiogram potential data.
[0055] Assume that the current time is , the ECG signal data obtained at the current moment is , a total of 12 different dimensions of ECG signal data, corresponding to the data characteristics of different electrodes in the twelve leads.
[0056] In the original 12-lead ECG signal data obtained by acquisition, due to the weak and unstable sensor electrode current data signal, there are abnormal data such as burrs and drift in the acquired original 12-lead ECG signal data. In order to reduce or even eliminate the influence of such abnormal data signals on the subsequent further calculation process as much as possible. Slice the data of each different dimension in the original ECG signal data, and take the slice data length as , the Butterworth bandpass filter is used to optimize the ECG data of the slice, where the filter order is 3 and the cutoff frequency is the mean value of the ECG data in the slice. The original 12-lead ECG data signal is denoised by the filter to eliminate the influence of abnormal fluctuations such as burr noise.
[0057] According to the above steps, we can get Human ECG signal data at all times , Due to the setting of the electrode conductor, the ECG signal data obtained by the collection has twelve different dimensions. In order to facilitate the subsequent further calculation and analysis and reduce the cost of subsequent further calculation, it is first necessary to optimize and reduce the dimensionality of the twelve-dimensional ECG signal data.
[0058] Specifically, every moment There is a twelve-dimensional ECG signal data under each of the above conditions, and the preset time period is taken All ECG signal data at different times in the data slice are taken as data slices. Different 12-dimensional ECG signal data slices are used as input, and the principal component analysis (PCA) method is used for dimensionality reduction. PCA is a dimensionality reduction method that uses the linear correlation of high-dimensional data to transform linearly independent components to achieve the transformation of high-dimensional data into low-dimensional data and extract the main features of the data. Assume that the dimension of the ECG signal data obtained after processing is , immediately The corresponding ECG signal data is , so as to obtain the ECG signal data corresponding to all moments in the preset time period T.
[0059] Step S12: Divide the ECG signal data in the preset time period into at least one band signal, each band signal representing the variation characteristics of a complete cardiac variation cycle.
[0060] For details, please combine Figure 2 , step S12 comprises:
[0061] Step S21: Segment the ECG signal data corresponding to each moment in the preset time period into data slices of length n.
[0062] Specifically, the ECG signal data corresponding to each moment in the preset time period T is divided into data slices of length n. In one embodiment, n is taken as 16 by experience.
[0063] Step S22: Calculate the band threshold corresponding to the data slice.
[0064] Specifically, the electrocardiogram mutation coefficients of the data slice at the current moment in different dimensions are calculated.
[0065] After dimensionality reduction, there are ECG signal data of r different dimensions, and the ECG mutation coefficient corresponding to the ECG signal data of these r dimensions is calculated. Specifically, the ECG mutation coefficient is calculated using the following formula:
[0066] ;
[0067] It represents the main dimension values of the ECG data retained after PCA dimensionality reduction calculation. Respectively represent the current time , the previous moment and the next moment The The size of ECG signal data in dimensions. Indicates the time t at The ECG mutation coefficient of ECG signal data in one dimension.
[0068] The above formula can be used to calculate the time ECG mutation coefficients in different dimensions The numerical value of ECG signal data of different dimensions will have obvious potential fluctuations due to myocardial contraction discharge. If the position of the sudden increase in the ECG is Dimensional moments The difference between the potential values calculated at the two adjacent moments should be large. After further calculation of ECG signal data of different dimensions, Moment ECG coefficients in different dimensions The value will become relatively larger.
[0069] The band threshold corresponding to the data slice is calculated based on the electrocardiogram mutation coefficient. In a specific embodiment, the band threshold corresponding to the data slice is calculated using the following formula:
[0070] ;
[0071] in, Represents the threshold adjustment parameter, which is used to adjust the detail changes in the band signal division process. The empirical value is 4. Indicates the current time The length obtained by dividing is The maximum value in the data slice of n Indicates the length of the data slice, Indicates the band threshold corresponding to the data slice at the current time t.
[0072] It should be noted that when the ECG mutation coefficients of two dimensions in the data slice are both the maximum ECG mutation coefficients, it is considered that there is overlap of different bands in the current ECG signal data, and the ECG signal data is slid backward for calculation, and the sliding step length of each ECG signal data is taken as 3 as an empirical value.
[0073] The above formula is used to calculate the corresponding band threshold for each data slice.
[0074] Step S23: dividing the electrocardiogram signal data in the preset time period into at least one band signal based on the band threshold, wherein the band signal includes electrocardiogram signal data corresponding to a plurality of moments.
[0075] Specifically, the ECG signal data corresponding to the moment greater than the band threshold is used as the starting point of the band signal, and the ECG signal data corresponding to the next moment greater than the band threshold is used as the ending point of the previous band signal and the starting point of the next band signal, and then the ECG signal data in the preset time period is divided to obtain at least one band signal. In this way, the ECG signal data in the preset time period is divided into at least one band signal.
[0076] Under normal circumstances, the human heart contracts and beats regularly, and the collected human ECG signal data will also show corresponding regular fluctuation characteristics. Therefore, the band threshold is calculated based on the ECG mutation coefficient of the acquired ECG signal data (the ECG mutation coefficient represents the fluctuation characteristics of the changes), and the band threshold is used to divide the cardiac cycle wave group to obtain the band signal. The band signal represents the ECG signal data within a complete cardiac cycle.
[0077] Step S13: Calculate the ECG signal data safety index at the current moment based on the ECG change characteristics of signals in different bands.
[0078] In one embodiment, please combine Figure 3 , step S13 comprises:
[0079] Step S31: Calculate the ECG signal fluctuation distance at the current moment based on the difference between the ECG mutation coefficient corresponding to the current moment and the ECG mutation coefficient corresponding to the k moment, and the number of band signals from the current moment to the k moment; the current moment and the k moment belong to the same band signal, and the ECG variation coefficient represents the ECG variation characteristics.
[0080] Through the above steps, the ECG signal data generated by the regular contraction and discharge of the human myocardium is divided into different band signals, each band signal represents the fluctuation characteristics of a complete cardiac cycle. Each band signal is further analyzed.
[0081] In one embodiment, the following formula is used to calculate the ECG signal fluctuation distance at the current moment:
[0082] ;
[0083] in, Indicates the ECG mutation coefficient corresponding to the current time t, represents the ECG mutation coefficient corresponding to time k, Indicates the number of central electrical signal data in the band signal. Indicates the density of the band signal from the current time t to the time k. The reciprocal of The larger the value is, the more regular the ECG changes in the band are; on the contrary, the smaller the value is, the more irregular it is. The larger it is, and the greater the difference in mutation coefficients is, the greater the fluctuation distance will be.
[0084] By time The ECG signal data at the position is centered and the length is The data slice, n The value is 16, that is There are 7 data slices at different times before the moment. There are 8 data slices at different times after the moment. Among them, 7 and 8 are empirical parameters. It should be noted that since n=16, the center position will be uncertain. In order to avoid ambiguity in the calculation description, this application defines a total of 7 data slices at different times before the moment based on experience. There are 8 data slices at different times after the moment.
[0085] The time can be calculated by the above formula ECG signal fluctuation distance The value of The greater the abnormal fluctuation of the ECG signal data at different times in the band signal centered on the center, the higher the possibility of abnormal ECG signal data at that moment, and the higher the possibility of trauma risk.
[0086] Step S32: Calculate the ECG signal data safety index at the current moment based on the ECG signal fluctuation distance at the current moment.
[0087] The ECG signal fluctuation distance at the current moment is quantified into Z different intervals; the ECG signal data distribution entropy corresponding to each interval is calculated, and then the ECG signal data distribution entropy corresponding to the current moment is obtained; the ECG signal data security index at the current moment is calculated based on the ECG signal data distribution entropy corresponding to the current moment.
[0088] In one embodiment, in order to further accurately quantify the characteristics of the fluctuation distribution of the ECG signal data, the calculated ECG signal fluctuation distance is quantified. Different intervals, The empirical value is 8, and the length of the interval is , where time In the band signal centered at , each moment has a corresponding ECG signal fluctuation distance, and the maximum ECG signal fluctuation distance is , the minimum ECG signal fluctuation distance is .
[0089] The following formula is used to calculate the distribution entropy of the ECG signal data corresponding to the current moment:
[0090] ;
[0091] in, It represents the numerical value of the distribution frequency of the ECG signal in interval h, and its calculation method is: ,in For interval The number of ECG signal values at different times in the ECG signal fluctuation distance interval corresponding to the quantization, represents the logarithmic function with base 2, Z represents the number of intervals, represents the distribution entropy of the ECG signal data corresponding to the current time t. The larger the value is, the more the local ECG signal data at that moment is fluctuating and the abnormal fluctuation is large, so the possibility of trauma risk is relatively high.
[0092] In the ECG signal data of a healthy person without heart disease, each different band signal should have similar fluctuation characteristics, which is caused by the regular contraction and discharge of the myocardium. Therefore, further calculation and analysis are performed based on the ECG signal distribution entropy combined with the ECG change characteristics of different band signals, such as fluctuation characteristics.
[0093] The ECG signal data security index at the current moment is calculated based on the ECG signal data distribution entropy corresponding to the current moment, including: calculating the ECG signal data security index at the current moment using the following formula:
[0094] ;
[0095] in, Indicates the total number of band signals. It indicates the The ECG signal data sequence of band signals, Indicates The ECG signal data sequence of band signals, It represents the distance between two different sequences. Indicates the length of the central electric signal data sequence of the band signal. Indicates k The distribution entropy of the data slice at time i in the band signal, Indicates k+1 The distribution entropy of the data slice at time i in the band signal.
[0096] The ECG signal data security index can be calculated by the above formula The value of is, because the ECG signal of the human body in a healthy state shows regular contraction and change characteristics, so the data fluctuation and change characteristics between the different wave groups obtained after division are highly similar. The calculated DTW distance is relatively small, and the difference in the ECG signal data distribution entropy value is also relatively small. At this time, the calculated ECG signal data security index The value will be larger; on the contrary, when the ECG signal data fluctuates abnormally, the characteristics of the wave groups of different ECG signal data will be relatively large, and the ECG safety index calculated at this time The value will be relatively small.
[0097] Step S14: determining whether the ECG data is abnormal based on the ECG signal data safety index at the current moment.
[0098] Through the above steps, the ECG signal data safety index can be obtained. This value represents the risk of ECG signal data fluctuation at the current moment. If this value is less than the empirical threshold of 0.9, it is considered that the myocardium has irregular contraction and discharge, resulting in abnormal ECG signal data fluctuations. Timely warning of abnormal trauma is given, and emergency medical measures are taken to reduce the risk of casualties.
[0099] The embodiment of the present invention uses a standard twelve-lead system to obtain human ECG signal data, and calculates the ECG mutation coefficient in combination with the fluctuation characteristics of the ECG data, highlighting the abnormal fluctuation values in the ECG signal data. At the same time, the ECG signal data collected and pre-processed is effectively divided according to the ECG mutation coefficient to obtain different ECG wave groups, ensuring the scientific nature of the subsequent analysis process. Furthermore, the embodiment of the present invention calculates the distribution characteristics of the ECG signal data, characterizes the abnormal fluctuation characteristics of the ECG signal data through the ECG signal data distribution entropy, and calculates the similar change characteristics of the ECG signal wave groups at different times in combination with the characteristics, thereby completing the judgment and early warning of abnormal ECG fluctuations. It avoids the shortcomings of the traditional calculation process that only shallow data features are calculated and cannot sensitively respond to abnormal fluctuations in the ECG signal data, and improves the accuracy and real-time effect of early warning of casualties and trauma.
[0100] See also Figure 4 , Figure 4It is a structural diagram of an embodiment of the auxiliary management system for reducing the risk of preventable death of the present invention, which specifically includes: a collection module 41, a division module 42, a calculation module 43 and a determination module 44.
[0101] Among them, the acquisition module 41 is used to collect the ECG signal data corresponding to each moment in the preset time period of the human body. The division module 42 is used to divide the ECG signal data in the preset time period into at least one band signal, and each band signal represents the change characteristics of a complete cardiac change cycle. The calculation module 43 is used to calculate the ECG signal data safety index at the current moment based on each band signal. The determination module 44 is used to determine whether the ECG data is abnormal based on the ECG signal data safety index at the current moment.
[0102] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A method for assisting management in reducing the risk of preventable death, characterized in that: include: Collect the ECG signal data corresponding to each moment in the preset time period of the human body; Dividing the electrocardiogram signal data in the preset time period into at least one band signal, each band signal representing the variation characteristics of a complete cardiac variation cycle; Calculate the ECG signal data security index at the current moment based on the ECG change characteristics of signals in different bands; Determine whether the ECG data is abnormal based on the ECG signal data safety index at the current moment; The ECG signal data security index at the current moment is calculated based on the ECG change characteristics of signals in different bands, including: Calculate the ECG signal fluctuation distance at the current moment based on the difference between the ECG mutation coefficient corresponding to the current moment and the ECG mutation coefficient corresponding to the k moment, and the number of band signals from the current moment to the k moment; the ECG mutation coefficient represents the ECG change characteristics; Calculate the ECG signal data security index at the current moment based on the ECG signal fluctuation distance at the current moment; Use the following formula to calculate the ECG signal fluctuation distance at the current moment: ; in, Indicates the ECG mutation coefficient corresponding to the current time t, represents the ECG mutation coefficient corresponding to time k, Indicates the number of central electrical signal data in the band signal. Indicates the density of the band signal from the current moment to the k moment; The ECG signal data security index at the current moment is calculated based on the ECG signal fluctuation distance at the current moment, including: Quantify the ECG signal fluctuation distance at the current moment into Z different intervals; Calculate the data distribution entropy of the ECG signal corresponding to each interval, and then obtain the data distribution entropy of the ECG signal corresponding to the current moment; The ECG signal data security index at the current moment is calculated based on the ECG signal data distribution entropy corresponding to the current moment; Calculating the distribution entropy of the ECG signal data corresponding to each interval, and then obtaining the distribution entropy of the ECG signal data corresponding to the current moment, including: The following formula is used to calculate the distribution entropy of the ECG signal data corresponding to the current moment: ; in, Representation interval h The numerical value of the ECG signal distribution frequency is calculated as follows: ,in For interval The number of ECG signal values at different times in the ECG signal fluctuation distance interval corresponding to the quantization, represents the logarithmic function with base 2, Z represents the number of intervals, Represents the distribution entropy of the ECG signal data corresponding to the current time t; The ECG signal data security index at the current moment is calculated based on the ECG signal data distribution entropy corresponding to the current moment, including: The current ECG signal data security index is calculated using the following formula: ; in, Indicates the total number of band signals. It indicates the The ECG signal data sequence of band signals, Indicates The ECG signal data sequence of band signals, It represents the distance between two different sequences. Indicates the length of the central electric signal data sequence of the band signal. Indicates k The distribution entropy of the data slice at time i in the band signal, Indicates k+1 The distribution entropy of the data slice at time i in the band signal.
2. The auxiliary management method for reducing the risk of preventable death according to claim 1, characterized in that: Dividing the electrocardiogram signal data in the preset time period into at least one band signal comprises: Divide the ECG signal data corresponding to each moment in the preset time period into data slices of length n; Calculate the band threshold corresponding to the data slice; The electrocardiographic signal data in the preset time period is divided into at least one band signal based on the band threshold, and the band signal includes electrocardiographic signal data corresponding to multiple moments.
3. The auxiliary management method for reducing the risk of preventable death according to claim 2, characterized in that: Dividing the electrocardiogram signal data in the preset time period into at least one band signal based on the band threshold comprises: The ECG signal data corresponding to the moment greater than the band threshold is used as the starting point of the band signal, and the ECG signal data corresponding to the next moment greater than the band threshold is used as the ending point of the previous band signal and the starting point of the next band signal, and then the ECG signal data in the preset time period is divided to obtain at least one band signal.
4. The auxiliary management method for reducing the risk of preventable death according to claim 2, characterized in that: Calculate the band threshold corresponding to the data slice, including: Calculate the ECG coefficient of the data slice at the current moment in different dimensions; Calculate the band threshold corresponding to the data slice based on the ECG mutation coefficient; Among them, the band threshold corresponding to the data slice is calculated using the following formula: ; in, Represents the threshold adjustment parameter, which is used to adjust the detail changes in the band signal division process. Indicates the current time The length obtained by dividing is The maximum value in the data slice of n Indicates the length of the data slice, Indicates the band threshold corresponding to the data slice at the current time t.
5. An auxiliary management system for reducing the risk of preventable death, characterized in that: The auxiliary management method for reducing the risk of preventable death according to claim 1 comprises: The acquisition module is used to collect the ECG signal data corresponding to each moment in a preset time period of the human body; A division module, used for dividing the electrocardiogram signal data in the preset time period into at least one band signal, each band signal representing the change characteristics of a complete cardiac change cycle; A calculation module, used for calculating the ECG signal data safety index at the current moment based on each band signal; The determination module is used to determine whether the ECG data is abnormal based on the ECG signal data safety index at the current moment.
Citation Information
Patent Citations
Electrocardiosignal quality detection method and device, computer equipment and storage medium
CN110179451A
Method for detecting atrial fibrillation in electrocardiogram
CN113499079A
