Methods, systems, and apparatuses to determine voltage values of electrocardiogram signals at future scheduled times

Abstract

This application relates to the field of human bioelectrical signal measurement, specifically to a method, system, and apparatus for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time. The method involves acquiring an ECG signal over a predetermined time period and processing it in segments to enable data extraction; determining the QT interval trend slope, the proportion of low-frequency energy in the ST segment, and the standard deviation of the RR interval sequence of heart rate variability in the processed ECG signal, and assigning weighting coefficients; determining the average voltage value at each moment within the predetermined time period based on the processed ECG signal; and finally determining the voltage value of the ECG signal at the predetermined future time based on the determined trend slope, low-frequency energy proportion, sequence standard deviation, weighting coefficients, and average value. The method provided by this application allows for accurate determination of the voltage value of a user's ECG signal at a predetermined future time.

Description

Technical Field

[0001] The embodiments of this application relate to the field of human bioelectrical signal measurement, specifically to a method, system, and apparatus for determining the voltage value of an electrocardiogram signal at a predetermined future time. Background Technology

[0002] The statements herein are provided merely as background information in connection with this application and do not necessarily constitute prior art.

[0003] Measuring the bioelectrical signals of the human body can reflect the physiological state of the human body. Currently, the devices that can measure the bioelectrical signals of the human body can often only measure the bioelectrical signal data of the user at the current moment. Summary of the Invention

[0004] A brief overview of this application is provided below to offer a basic understanding of certain aspects thereof. It should be understood that this overview is not an exhaustive summary of the application. It is not intended to identify key or essential parts of the application, nor is it intended to limit its scope. Its purpose is merely to present certain concepts in a simplified form as a prelude to the more detailed description that follows.

[0005] In a first aspect, embodiments of this application provide a method for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time, comprising the following steps: S10: acquiring an ECG signal over a predetermined time period; S20: segmenting the ECG signal to enable it to be used to extract desired data; S30: determining the QT interval trend slope, the proportion of low-frequency energy in the ST segment, and the standard deviation of the RR interval sequence of heart rate variability in the processed ECG signal; S40: assigning weighting coefficients to the trend slope, low-frequency energy proportion, and sequence standard deviation determined in step S30; S50: determining the average voltage value of the ECG signal at each moment within the predetermined time period based on the processed ECG signal in step S20; S60: determining the voltage value of the ECG signal at a predetermined future time based on the trend slope, low-frequency energy proportion, and sequence standard deviation determined in step S30, the weighting coefficients determined in step S40, and the average voltage value determined in step S50.

[0006] The embodiments of this application acquire and process electrocardiogram (ECG) signals over a predetermined time period to extract necessary data. The extracted data is then weighted to ensure that the importance of trend slope, low-frequency energy proportion, and sequence standard deviation in predicting the ECG signal voltage value at a predetermined future time aligns with actual physiological conditions. The average voltage value at each moment within the predetermined ECG time period is determined as a benchmark for subsequent ECG signal prediction. Finally, based on the determined trend slope, low-frequency energy proportion, sequence standard deviation, weighting coefficients, and average value, the voltage value of the ECG signal at the predetermined future time is determined. The method provided by the embodiments of this application enables accurate prediction of the ECG signal voltage value at a predetermined future time for a user who has acquired ECG signals.

[0007] Secondly, embodiments of this application also provide a system for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time, comprising: a signal acquisition unit and a signal processing unit, wherein the signal acquisition unit is configured to acquire a user's ECG signal and perform noise filtering on the ECG signal; the signal acquisition unit is further configured to transmit the noise-filtered ECG signal to the signal processing unit; and the signal processing unit is configured to process the filtered ECG signal to determine the voltage value of the ECG signal at a predetermined future time.

[0008] The embodiments of this application acquire the required signal through a signal acquisition device, filter the noise in the acquired signal, and transmit the filtered signal to a signal processing device. The signal processing device processes the signal to determine the voltage value of the electrocardiogram (ECG) signal at a predetermined future time. This avoids the unfiltered signal from affecting the determination of the voltage value of the ECG signal at a predetermined future time. By processing the filtered ECG signal to determine the voltage value of the ECG signal at a predetermined future time, the determination of the voltage value of the ECG signal at a predetermined future time is more accurate.

[0009] Thirdly, embodiments of this application also provide an apparatus for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time, comprising: a signal acquisition unit, a preprocessing unit, and a signal processing unit; the signal acquisition unit is configured to acquire an ECG signal over a predetermined time period; the preprocessing unit is configured to process the ECG signal in segments so that the ECG signal can be used to extract required data; the signal processing unit is configured to determine the QT interval trend slope, the proportion of low-frequency energy in the ST segment, and the standard deviation of the RR interval sequence of heart rate variability of the ECG signal processed by the preprocessing unit, and assign weight coefficients to the trend slope, the proportion of low-frequency energy, and the standard deviation of the sequence; the signal processing unit is further configured to determine the average voltage value of the ECG signal at each moment within the predetermined time period based on the ECG signal processed by the preprocessing unit, and determine the voltage value of the ECG signal at a predetermined future time based on the trend slope, the proportion of low-frequency energy, the standard deviation of the sequence, the weight coefficients, and the average voltage value at each moment within the predetermined time period of the ECG signal.

[0010] The embodiments of this application acquire electrocardiogram (ECG) signals over a predetermined time period using a signal acquisition unit. A preprocessing unit processes the ECG signals to enable data extraction. The signal processing unit extracts the data and assigns weighting coefficients to the data, ensuring that the importance of trend slope, low-frequency energy proportion, and sequence standard deviation in predicting the ECG signal voltage value at a predetermined future time aligns with actual physiological conditions. The average voltage value at each moment within the predetermined ECG time period is determined as a benchmark for subsequent ECG signal prediction. Finally, based on the determined trend slope, low-frequency energy proportion, sequence standard deviation, weighting coefficients, and average value, the voltage value of the ECG signal at the predetermined future time is determined. The apparatus provided by the embodiments of this application can accurately predict the voltage value of the ECG signal acquired by the user at a predetermined future time. Attached Figure Description

[0011] Other objects and advantages of this application will become apparent from the following description of embodiments of this application with reference to the accompanying drawings, and will help to provide a comprehensive understanding of this application.

[0012] Figure 1 This is a comparison chart of the voltage values ​​of ECG signals at a predetermined future time obtained by applying the method provided in the embodiments of this application and the voltage values ​​of ECG signals at the actual predetermined future time.

[0013] Figure 2 This is a comparison image of electrocardiogram signals before noise reduction processing using the method provided in the embodiments of this application.

[0014] Figure 3 This is a comparison image of electrocardiogram signals after noise reduction processing using the method provided in the embodiments of this application.

[0015] Figure 4 This is a schematic diagram illustrating the use of the signal acquisition component of the system provided in the embodiments of this application.

[0016] Figure 5 This is a structural cross-sectional view of the signal acquisition component of the system provided in the embodiments of this application.

[0017] It should be noted that the accompanying drawings are not necessarily drawn to scale, but are shown only in a schematic manner without affecting the reader's understanding.

[0018] Explanation of reference numerals in the attached figures: 10. Signal acquisition components; 11. Protection components; 12. Acquisition components; 13. Filtering components; 14. Transmission components; 15. Fixing components. Detailed Implementation

[0019] Exemplary embodiments of this application will be described below with reference to the accompanying drawings. For clarity and brevity, not all features of actual implementations are described in the specification. However, it should be understood that many implementation-specific decisions must be made in the development of any such actual embodiment to achieve the developer's specific goals, such as complying with constraints related to the system and business, and these constraints may vary depending on the implementation. Furthermore, it should be understood that while development work can be very complex and time-consuming, such development work is merely a routine task for those skilled in the art who benefit from the content of this application.

[0020] It should also be noted that, in order to avoid obscuring this application with unnecessary details, only the equipment structure and / or processing steps closely related to the solution according to this application are shown in the accompanying drawings, while other details that are not closely related to this application are omitted.

[0021] Currently, the ECG monitoring devices worn by users can only monitor and record the ECG signal at the current moment. They are mostly used for post-event analysis to determine the user's physical condition, but cannot predict the user's individual ECG signal condition.

[0022] To address the aforementioned problems, embodiments of this application provide a method for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time. The method includes the following steps: S10: acquiring an ECG signal over a predetermined time period; S20: segmenting the ECG signal to enable it to be used for extracting desired data; S30: determining the QT interval trend slope, the proportion of low-frequency energy in the ST segment, and the standard deviation of the RR interval sequence of heart rate variability in the processed ECG signal; S40: assigning weighting coefficients to the trend slope, low-frequency energy proportion, and sequence standard deviation determined in step S30; S50: determining the average voltage value at each moment within the predetermined time period based on the processed ECG signal in step S20; S60: determining the voltage value of the ECG signal at a predetermined future time based on the trend slope, low-frequency energy proportion, and sequence standard deviation determined in step S30, the weighting coefficients determined in step S40, and the average voltage value determined in step S50.

[0023] The embodiments of this application acquire and process electrocardiogram (ECG) signals over a predetermined time period to extract necessary data. The extracted data is then weighted to ensure that the importance of trend slope, low-frequency energy proportion, and sequence standard deviation in predicting the ECG signal voltage value at a future predetermined time aligns with actual physiological conditions. The average voltage value at each moment within the predetermined time period is determined as a benchmark for subsequent ECG signal prediction. Finally, based on the determined trend slope, low-frequency energy proportion, sequence standard deviation, weighting coefficients, and average value, the voltage value of the ECG signal at the future predetermined time is determined. The method provided by the embodiments of this application accurately determines the voltage value of the user's ECG signal at a future predetermined time, and the determined result matches the actual acquired result.

[0024] See Figure 1 , Figure 1 This is a comparison chart of the voltage value of the electrocardiogram (ECG) signal at a predetermined future time obtained using the method provided in the embodiments of this application, and the voltage value of the ECG signal at the actual future time. The dashed line in the chart represents the voltage value of the ECG signal at the predetermined future time obtained using the method provided in the embodiments of this application, and the solid line represents the voltage value of the ECG signal at the actual future time. As shown in the chart, the mean square error between the ECG signal voltage value determined by the method provided in the embodiments of this application and the voltage value of the ECG signal at the same moment in the subsequent actual acquisition is 0.001, and the correlation coefficient is 0.996, indicating that the two results are consistent.

[0025] In some embodiments, see Figure 2 and Figure 3 , Figure 2 This is a comparison image of electrocardiogram signals before and after noise reduction processing using the method provided in the embodiments of this application. Figure 3 This is a comparison image of electrocardiogram (ECG) signals after noise reduction processing using the method provided in the embodiments of this application. S20 may include the following steps: S21: continuously segmenting the ECG signal in time, with each adjacent two segments of the ECG signal having temporal overlap; S22: performing noise reduction processing on the continuously segmented ECG signals so that the ECG signals can be used to extract the required data.

[0026] This setup, by continuously segmenting the ECG signal in time, makes the signal easier to process. At the same time, the temporal overlap between each two adjacent ECG segments ensures the continuity of the ECG signal, and important ECG signals are not lost due to segmentation. By performing noise reduction processing on the continuously segmented ECG signal, the ECG signal can be used to extract the required data, and the subsequent determination of the ECG signal at future times is more accurate.

[0027] In such an embodiment, each segment of the continuous ECG signal can be 5 minutes long, and the temporal overlap can be 1 minute to avoid information loss.

[0028] In some embodiments, step S22, the noise reduction processing of the continuously segmented ECG signal may include the following steps: S221: obtaining the baseline drift signal amplitude of the ECG signal; S222: determining the ECG signal after removing the baseline drift based on the baseline drift signal amplitude and the amplitude of the ECG signal.

[0029] This setting allows for the removal of baseline drift signals from the electrocardiogram (ECG) signal, preventing it from affecting the measurement of ST segment amplitude and trend analysis during subsequent data extraction.

[0030] In some embodiments, step S22, the noise reduction processing of the continuously segmented ECG signal may include the following steps: S223: obtaining the power frequency angular frequency of the ECG signal; S224: determining the ECG signal with power frequency interference removed based on the power frequency angular frequency.

[0031] This setting allows for the removal of power frequency interference in the electrocardiogram (ECG) signal, preventing power frequency interference from masking subtle changes in the ECG signal and facilitating the subsequent extraction of clean and accurate data.

[0032] In some embodiments, step S30 may further include the following steps: S31: determining the voltage change of the electrocardiogram signal during the QT interval and the time interval of the QT interval; S32: determining the trend slope based on the voltage change and the time interval.

[0033] In electrocardiogram (ECG) signals, QT interval prolongation is an important early warning signal of sudden cardiac death in patients with aortic stenosis. This setting, by determining the trend slope of the QT interval, allows for the detection of abnormalities in the repolarization process through the rate of change of the QT interval over time, thus reflecting the stability of cardiac electrical activity.

[0034] In some embodiments, in step S30, the voltage change, time interval, and trend slope conform to the following relationship: .

[0035] in, The trend slope This represents the voltage change in the electrocardiogram signal during the QT interval. This is the time interval of the QT interval.

[0036] This setup allows for accurate determination of whether the QT interval in the electrocardiogram (ECG) is prolonged based on the ratio of the voltage change in the QT interval to the time interval of the QT interval. It also allows for the detection of abnormalities in the repolarization process by observing the rate of change of the QT interval over time, thereby reflecting the stability of cardiac electrical activity.

[0037] In some embodiments, step S30 may further include the following steps: S33: determining the energy of the ST segment of the ECG signal in the low-frequency band and the total energy of the ST segment of the ECG signal; S34: determining the proportion of low-frequency energy based on the energy of the ST segment in the low-frequency band and the total energy of all frequency bands of the ST segment of the ECG signal. In such embodiments, the low-frequency band may be 0.04-0.15Hz.

[0038] During myocardial ischemia, the ST segment in the electrocardiogram (ECG) signal exhibits specific low-frequency oscillations. This setting allows the degree of myocardial ischemia to be reflected based on the proportion of low-frequency energy in the ST segment.

[0039] In some embodiments, during step S30, the energy of the low-frequency band, the total energy, and the proportion of low-frequency energy conform to the following relationship: .

[0040] in, The proportion of low-frequency energy This refers to the energy of the ST segment in the low-frequency range of an electrocardiogram (ECG) signal. This represents the total energy of all frequency bands in the ST segment of the electrocardiogram signal.

[0041] This setting allows for the determination of the low-frequency energy ratio based on the ratio of the energy of the ST segment in the low-frequency band of the electrocardiogram signal to the total energy of all frequency bands of the ST segment, thus quantifying the degree of myocardial ischemia.

[0042] In some embodiments, S40 may include the following steps: S41: Acquire historical ECG signals from multiple users and process each historical ECG signal so that it can be used to extract the required data; S42: Extract feature values ​​of the QT interval trend slope, ST segment low-frequency energy proportion, and RR interval sequence standard deviation of heart rate variability from the processed historical ECG signals; S43: Determine the importance score of each feature value based on the feature values ​​extracted in step S42; S44: Determine the weighting coefficient based on the importance score; S45: Assign the weighting coefficients of the trend slope, low-frequency energy proportion, and sequence standard deviation determined in step S30.

[0043] This setup, by acquiring historical ECG signals from multiple users and extracting feature values ​​such as the QT interval trend slope, ST segment low-frequency energy proportion, and RR interval sequence standard deviation of heart rate variability from the processed historical ECG signals, avoids individual differences in single-user data and ensures the objectivity of the acquired data source. By determining weighting coefficients based on the extracted feature values, the influence of each feature value on future ECG signals can be determined based on data from multiple users. The trend slope, low-frequency energy proportion, and sequence standard deviation weighting coefficients determined in step S30 are then assigned, enabling these factors to be used to predict future ECG signals.

[0044] In some embodiments, S41 may include the following steps: S411: Segment each historical ECG signal sequentially in time, with each adjacent two segments of historical ECG signals having temporal overlap; S412: Perform noise reduction processing on the sequentially segmented historical ECG signals so that the historical ECG signals can be used to extract the required data.

[0045] This configuration, by segmenting historical ECG signals sequentially, facilitates signal processing. Furthermore, the temporal overlap between adjacent segments ensures the continuity of historical ECG signals, preventing the loss of important ECG signals due to segmentation.

[0046] In such an embodiment, each segment of the continuously segmented historical ECG signal can be 5 minutes long, and the temporal overlap can be 1 minute to avoid information loss.

[0047] In some embodiments, S43 may include the following steps: S431: Based on the feature values ​​extracted in step S42, determine the degree of influence of the ECG signal features in the next minute at the time of each feature value; S432: Assign an influence classification to the feature values ​​based on the degree of influence of the features; S433: Determine the importance score of the feature values ​​based on the influence classification.

[0048] This setup associates each feature value with the influence of the ECG signal characteristics of the next minute at its current time and determines the importance score of the feature value. The importance score is used to measure the importance of each feature value in predicting the ECG signal characteristics in the next minute, thereby making the determination of the ECG signal voltage value at a future predetermined time more accurate.

[0049] In some embodiments, S44 may include the following steps: S441: Determine the initial weight coefficient based on the importance score; S442: Obtain the user's recent electrocardiogram (ECG) signal and process the recent ECG signal so that the recent ECG signal can be used to extract the required data to adjust the initial weight coefficient; S443: Determine the weight coefficient based on the processed recent ECG signal and the initial weight coefficient.

[0050] This setup, by acquiring and processing the user's recent electrocardiogram (ECG) signals, allows the processed signals to be used to adjust the initial weighting coefficients and ultimately determine them. This enables the determination of individual differences in the user's ECG signal voltage at a predetermined future time, thereby improving the accuracy of the prediction.

[0051] In some embodiments, S60 includes the following steps: S61: determining a nonlinear scaling signal based on the trend slope determined in step S30 and the average value determined in step S50; S62: determining a low-frequency oscillation signal based on the low-frequency energy proportion determined in step S30 and the average value determined in step S50; S63: determining a physiological variation signal based on the sequence standard deviation determined in step S30 and the average value determined in step S50; S64: determining the voltage value of the electrocardiogram signal at a predetermined future time based on the nonlinear scaling signal determined in step S61, the low-frequency oscillation signal determined in step S62, the physiological variation signal determined in step S63, and the weighting coefficient determined in step S40.

[0052] This setting allows for more accurate determination of the voltage value of the ECG signal at a predetermined future time by taking into account the nonlinear scaling effect of the trend slope on the ECG signal, the effect of the low-frequency energy ratio on the low-frequency oscillation of the ECG signal, the effect of the sequence standard deviation on the physiological variation of the ECG signal, and the weight of each effect on the determination of the voltage value of the ECG signal at a predetermined future time.

[0053] In some embodiments, in step S61, the trend slope, average value, and nonlinear scaling signal conform to the following relationship: .

[0054] in, It is a nonlinear scaling signal. This is the average value. The trend slope The region is the area of ​​influence corresponding to the QT interval trend. The predetermined continuous interval, where t is time. The coefficient represents the influence of the QT trend on the time scaling of the ECG waveform.

[0055] This setup, which determines the nonlinear scaling signal based on the trend slope and average value, takes into account the nonlinear scaling effect of the trend slope on the ECG signal when determining the voltage value of the ECG signal at a predetermined future time, thus making the determination of the voltage value of the ECG signal at a predetermined future time more accurate.

[0056] In some embodiments, in step S62, the low-frequency energy percentage, average value, and low-frequency oscillation signal conform to the following relationship: .

[0057] in, It is a low-frequency oscillation signal. This is the average value. The proportion of low-frequency energy The region corresponding to ST energy is [region name]. The predetermined continuous interval, where t is time. The ST influence coefficient indicates the impact of ST energy on the amplitude of low-frequency oscillations in the ST segment.

[0058] This setting determines the low-frequency oscillation signal based on the proportion and average value of low-frequency energy, so that the influence of the proportion of low-frequency energy on the low-frequency oscillation of the ECG signal is taken into account when determining the voltage value of the ECG signal at a future predetermined time, thereby making the determination of the voltage value of the ECG signal at a future predetermined time more accurate.

[0059] In some embodiments, in step S63, the sequence standard deviation, mean, and physiological variation signal conform to the following relationship: .

[0060] in, This is a physiological variation signal. This is the average value. for A low-frequency random process within a predetermined continuous interval, where t is time. The influence coefficient of the standard deviation of the RR interval sequence for heart rate variability. The standard deviation of the RR interval sequence for heart rate variability. This is a reference value for the standard deviation of the RR interval sequence for heart rate variability.

[0061] This setup determines physiological variation signals based on the sequence standard deviation and mean, making the determination of the voltage value of the ECG signal at a future predetermined time more accurate by taking into account the influence of the sequence standard deviation on the physiological variation of the ECG signal.

[0062] In some embodiments, in step S60, the trend slope, the proportion of low-frequency energy, the sequence standard deviation, the weighting coefficient, the average value, and the voltage value of the electrocardiogram signal at a predetermined future time conform to the following relationship: .

[0063] Where t is time, The voltage value of the electrocardiogram signal at a predetermined future time. It is a nonlinear scaling signal. It is a low-frequency oscillation signal. This is a physiological variation signal. This is a weighting coefficient for the proportion of low-frequency energy. The weighting coefficients are the standard deviations of the series. The weighting coefficients for the trend slope are: > > .

[0064] This setting allows for the determination of the voltage value of the ECG signal at a predetermined future time to take into account nonlinear stretching signals, low-frequency oscillation signals, physiological variation signals, and the weight of different signals in determining the voltage value of the ECG signal at a predetermined future time, thereby enabling a more accurate determination of the voltage value of the ECG signal at a predetermined future time.

[0065] Embodiments of this application also provide a system for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time. The system may include a signal acquisition unit and a signal processing unit. The signal acquisition unit is configured to acquire the user's ECG signal and perform noise filtering on the ECG signal. The signal acquisition unit is also configured to transmit the noise-filtered ECG signal to the signal processing unit. The signal processing unit is configured to process the filtered ECG signal to determine the voltage value of the ECG signal at a predetermined future time.

[0066] The embodiments of this application acquire the required signal through a signal acquisition device, filter the noise in the acquired signal, and transmit the filtered signal to a signal processing device. The signal processing device processes the signal to determine the voltage value of the electrocardiogram (ECG) signal at a predetermined future time. This avoids the unfiltered signal from affecting the determination of the voltage value of the ECG signal at a predetermined future time. By processing the filtered ECG signal to determine the voltage value of the ECG signal at a predetermined future time, the determination of the voltage value of the ECG signal at a predetermined future time is more accurate.

[0067] The system provided in the embodiments of this application can use the method provided in the first aspect of the embodiments of this application to determine the voltage value of the electrocardiogram signal at a predetermined future time.

[0068] In some embodiments, the signal processing unit may be configured to determine the QT interval trend slope, the proportion of low-frequency energy in the ST segment, and the standard deviation of the RR interval sequence of heart rate variability of the processed electrocardiogram (ECG) signal; assign weighting coefficients to the trend slope, the proportion of low-frequency energy, and the standard deviation of the sequence; determine the average voltage of the ECG signal at each moment within a predetermined time period; and determine the voltage value of the ECG signal at a future predetermined time based on the determined trend slope, the proportion of low-frequency energy, the standard deviation of the sequence, the weighting coefficients, and the average value.

[0069] This configuration allows the signal processing unit to determine the QT interval trend slope, ST segment low-frequency energy proportion, and RR interval sequence standard deviation of the processed ECG signal and assign weighting coefficients. This ensures that the importance of the trend slope, low-frequency energy proportion, and sequence standard deviation in predicting the ECG signal voltage value at a predetermined time in the future aligns with actual physiological conditions. The average voltage value at each moment within the predetermined time period of the ECG signal is determined as the benchmark for subsequent ECG signal prediction. Finally, based on the determined trend slope, low-frequency energy proportion, sequence standard deviation, weighting coefficients, and average value, the voltage value of the ECG signal at the predetermined time in the future is determined.

[0070] In some embodiments, see Figure 4 , Figure 4 This is a schematic diagram illustrating the use of the signal acquisition component of the system provided in an embodiment of this application. The signal acquisition component 10 can be fixed at the projection position of the user's aortic valve on the body surface for acquiring the user's electrocardiogram (ECG) signal. This configuration allows for convenient acquisition of the user's ECG signal.

[0071] In some embodiments, see Figure 5 , Figure 5 This is a structural cross-sectional view of the signal acquisition component of the system provided in an embodiment of this application. The signal acquisition component 10 includes: a protective component 11, an acquisition component 12, a filter component 13, a transmission component 14, and a fixing component 15; the protective component 11 is configured to protect the acquisition component 12; the acquisition component 12 is configured to acquire electrocardiogram (ECG) signals; the filter component 13 is configured to filter noise from the ECG signals; the transmission component 14 is configured to transmit the noise-filtered ECG signals to a signal processing component; the fixing component 15 is configured to be fixed to the user's skin so that the acquisition component 12 can acquire the user's ECG signals.

[0072] This configuration allows the signal acquisition unit 10 to be placed on the user's skin to acquire electrocardiogram (ECG) signals and to filter the ECG signals for noise, so that the filtered ECG signals can be transmitted to the signal processing unit to determine the voltage value of the ECG signals at a predetermined future time.

[0073] In some embodiments, the transmission element 14, the filter element 13, the acquisition element 12, and the protective element 11 are stacked sequentially on the side of the fixing element 15 away from the user's skin, and the protective element 11 is disposed on the side of the acquisition element 12, the filter element 13, and the transmission element 14 away from the user's skin to protect the acquisition element 12, the filter element 13, the transmission element 14, and the fixing element 15.

[0074] This configuration helps the protective component 11 protect the acquisition component 12, the filter component 13, the transmission component 14, and the fixing component 15, preventing damage to the acquisition component 12, the filter component 13, and the transmission component 14, which would render the acquired signal unusable.

[0075] Embodiments of this application also provide an apparatus for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time, comprising: a signal acquisition unit, a preprocessing unit, and a signal processing unit; the signal acquisition unit is configured to acquire an ECG signal over a predetermined time period; the preprocessing unit is configured to process the ECG signal in segments so that the ECG signal can be used to extract required data; the signal processing unit is configured to determine the QT interval trend slope, the proportion of low-frequency energy in the ST segment, and the standard deviation of the RR interval sequence of heart rate variability of the ECG signal processed by the preprocessing unit, and assign weight coefficients to the trend slope, the proportion of low-frequency energy, and the standard deviation of the sequence; the signal processing unit is further configured to determine the average voltage value of the ECG signal at each moment within the predetermined time period based on the ECG signal processed by the preprocessing unit, and determine the voltage value of the ECG signal at a predetermined future time based on the trend slope, the proportion of low-frequency energy, the standard deviation of the sequence, the weight coefficients, and the average value.

[0076] The embodiments of this application acquire electrocardiogram (ECG) signals over a predetermined time period using a signal acquisition unit. A preprocessing unit processes the ECG signals to enable data extraction. The signal processing unit extracts the data and assigns weighting coefficients to the data, ensuring that the importance of trend slope, low-frequency energy proportion, and sequence standard deviation in predicting the ECG signal voltage value at a predetermined future time aligns with actual physiological conditions. The average voltage value at each moment within the predetermined ECG time period is determined as a benchmark for subsequent ECG signal prediction. Finally, based on the determined trend slope, low-frequency energy proportion, sequence standard deviation, weighting coefficients, and average value, the voltage value of the ECG signal at the predetermined future time is determined. The apparatus provided by the embodiments of this application can accurately predict the voltage value of the ECG signal acquired by the user at a predetermined future time.

[0077] Regarding the embodiments of this application, it should also be noted that, without conflict, the embodiments of this application and the features in the embodiments can be combined with each other to obtain new embodiments.

[0078] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. The scope of protection of this application shall be determined by the scope of the claims.

Claims

1. A method for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time, characterized in that, It includes the following steps: S10: Acquire electrocardiogram signals for a predetermined time period; S20: Process the electrocardiogram (ECG) signal in segments so that the ECG signal can be used to extract the required data; S30: Determine the QT interval trend slope, ST segment low-frequency energy proportion, and RR interval sequence standard deviation of the processed ECG signal; S40: Assign the trend slope, the proportion of low-frequency energy, and the weighting coefficient of the sequence standard deviation determined in step S30; S50: Based on the electrocardiogram signal processed in step S20, determine the average voltage of the electrocardiogram signal at each moment within a predetermined time period; S60: Based on the trend slope, the proportion of low-frequency energy, and the standard deviation of the sequence determined in step S30, the weighting coefficient determined in step S40, and the average value determined in step S50, determine the voltage value of the electrocardiogram signal at a predetermined future time.

2. The method according to claim 1, characterized in that, S20 includes the following steps: S21: The electrocardiogram signal is segmented continuously in time, and each two adjacent segments of the electrocardiogram signal have temporal overlap; S22: Perform noise reduction processing on the continuously segmented electrocardiogram (ECG) signal so that the ECG signal can be used to extract the required data.

3. The method according to claim 2, characterized in that, In step S22, the noise reduction processing of the continuously segmented electrocardiogram signal includes the following steps: S221: Obtain the baseline drift signal amplitude of the electrocardiogram signal; S222: Determine the ECG signal after removing the baseline drift based on the amplitude of the baseline drift signal and the amplitude of the ECG signal.

4. The method according to claim 2, characterized in that, In step S22, the noise reduction processing of the continuously segmented electrocardiogram signal includes the following steps: S223: Obtain the power frequency angular frequency of the electrocardiogram signal; S224: Determine the ECG signal after removing power frequency interference based on the power frequency angular frequency.

5. The method according to claim 1, characterized in that, Step S30 also includes the following steps: S31: Determine the voltage change of the electrocardiogram signal during the QT interval and the time interval of the QT interval; S32: Determine the trend slope based on the voltage change and the time interval.

6. The method according to claim 5, characterized in that, In step S30, The voltage change, the time interval, and the trend slope conform to the following relationship: ， in, The slope of the trend. The voltage change of the electrocardiogram signal during the QT interval. The time interval is the QT interval.

7. The method according to claim 1, characterized in that, Step S30 also includes the following steps: S33: Determine the energy of the ST segment of the electrocardiogram signal in the low-frequency band and the total energy of the ST segment of the electrocardiogram signal; S34: Determine the proportion of low-frequency energy based on the energy of the ST segment in the low-frequency band and the total energy of all frequency bands of the ST segment of the electrocardiogram signal.

8. The method according to claim 7, characterized in that, In step S30, The energy of the low-frequency band, the total energy, and the proportion of low-frequency energy conform to the following relationship: ， in, The low-frequency energy percentage is mentioned above. The energy of the ST segment of the electrocardiogram signal in the low-frequency band. This represents the total energy of all frequency bands in the ST segment of the electrocardiogram signal.

9. The method according to claim 1, characterized in that, S40 includes the following steps: S41: Acquire historical ECG signals from multiple users and process each historical ECG signal so that the historical ECG signal can be used to extract the required data; S42: Extract the characteristic values ​​of the QT interval trend slope, ST segment low-frequency energy proportion, and RR interval sequence standard deviation of the processed historical ECG signal; S43: Determine the importance score of each feature value based on the feature values ​​extracted in step S42; S44: Determine the weighting coefficients based on the importance scores; S45: Assign the weighting coefficients to the trend slope, the proportion of low-frequency energy, and the standard deviation of the sequence determined in step S30.

10. The method according to claim 9, characterized in that, S44 includes the following steps: S441: Determine the initial weighting coefficients based on the importance scores; S442: Acquire the user's recent electrocardiogram (ECG) signal and process the recent ECG signal so that the recent ECG signal can be used to extract the required data to adjust the initial weight coefficient; S443: Determine the weighting coefficients based on the processed recent electrocardiogram signal and the initial weighting coefficients.

11. The method according to claim 1, characterized in that, S60 includes the following steps: S61: Determine the nonlinear scaling signal based on the trend slope determined in step S30 and the average value determined in step S50; S62: Determine the low-frequency oscillation signal based on the low-frequency energy ratio determined in step S30 and the average value determined in step S50; S63: Determine the physiological variation signal based on the sequence standard deviation determined in step S30 and the average value determined in step S50; S64: Determine the voltage value of the electrocardiogram signal at a predetermined future time based on the nonlinear stretching signal determined in step S61, the low-frequency oscillation signal determined in step S62, the physiological variation signal determined in step S63, and the weighting coefficient determined in step S40.

12. The method according to claim 11, characterized in that, In step S61, The trend slope, the average value, and the nonlinear scaling signal conform to the following relationship: ， in, For the nonlinear scaling signal, The average value is... The slope of the trend. The region is the area of ​​influence corresponding to the QT interval trend. The predetermined continuous interval, where t is time. The coefficient represents the influence of the QT trend on the time scaling of the ECG waveform.

13. The method according to claim 11, characterized in that, In step S62, The low-frequency energy percentage, the average value, and the low-frequency oscillation signal conform to the following relationship: ， in, The low-frequency oscillation signal, The average value is... The low-frequency energy percentage is mentioned above. The region corresponding to ST energy is the area of ​​influence. The predetermined continuous interval, where t is time. The ST influence coefficient indicates the impact of ST energy on the amplitude of low-frequency oscillations in the ST segment.

14. The method according to claim 11, characterized in that, In step S63, The sequence standard deviation, the mean, and the physiological variation signal conform to the following relationship: ， in, This refers to the physiological variation signal. The average value is... for A low-frequency random process within a predetermined continuous interval, where t is time. The influence coefficient of the standard deviation of the RR interval sequence for heart rate variability. The standard deviation of the RR interval sequence for heart rate variability. This is a reference value for the standard deviation of the RR interval sequence for heart rate variability.

15. The method according to claim 11, characterized in that, In step S60, The trend slope, the proportion of low-frequency energy, the sequence standard deviation, the weighting coefficient, the average value, and the voltage value of the ECG signal at the predetermined future time conform to the following relationship: ， Where t is time, The voltage value of the electrocardiogram signal at the predetermined future time. For the nonlinear scaling signal, The low-frequency oscillation signal, This refers to the physiological variation signal. This is the weighting coefficient for the proportion of low-frequency energy. The weighting coefficients are the standard deviations of the series. The weighting coefficient for the slope of the trend is denoted as , and > > .

16. A system for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time, comprising determining the voltage value of the ECG signal at any one of claims 1-15, characterized in that, It includes: Signal acquisition components and signal processing components, The signal acquisition device is configured to acquire the user's electrocardiogram (ECG) signal and filter the ECG signal for noise. The signal acquisition device is also configured to transmit the noise-filtered electrocardiogram signal to the signal processing device; The signal processing unit is configured to process the filtered electrocardiogram (ECG) signal to determine the voltage value of the ECG signal at a predetermined future time.

17. The system according to claim 16, characterized in that, The signal processing unit is configured to determine the QT interval trend slope, the proportion of low-frequency energy in the ST segment, and the standard deviation of the RR interval sequence of heart rate variability of the processed electrocardiogram signal. Assign the trend slope, the proportion of low-frequency energy, and the weighting coefficient of the sequence standard deviation; Determine the average voltage of the electrocardiogram signal at each moment within a predetermined time period; The voltage value of the electrocardiogram signal at a predetermined future time is determined based on the determined trend slope, the proportion of low-frequency energy, the sequence standard deviation, the weighting coefficient, and the average value.

18. The system according to claim 16, characterized in that, The signal acquisition component includes: a protective component, an acquisition component, a filtering component, a transmission component, and a fixing component; The protective component is configured to protect the collecting component, the filtering component, the transmitting component, and the fixing component; The acquisition device is configured to acquire the electrocardiogram signal; The filter is configured to filter noise from the electrocardiogram signal. The transmission device is configured to transmit the noise-filtered electrocardiogram signal to the signal processing device; The fastener is configured to be fixed to the user's skin so that the acquisition device can acquire the user's electrocardiogram signal.

19. The system according to claim 18, characterized in that, The transmission component, the filtering component, the acquisition component, and the protective component are sequentially stacked on the side of the fixing component away from the user's skin. The protective element is disposed on the side of the acquisition element, the filter element, and the transmission element away from the user's skin to protect the acquisition element, the filter element, the transmission element, and the fixing element.

20. A device for determining the voltage value of an electrocardiogram (ECG) signal at a predetermined future time, characterized in that, It includes: Signal acquisition components, preprocessing components, and signal processing components; The signal acquisition device is configured to acquire electrocardiogram signals over a predetermined time period; The preprocessor is configured to process the electrocardiogram (ECG) signal in segments so that the ECG signal can be used to extract the required data. The signal processing unit is configured to determine the QT interval trend slope, ST segment low-frequency energy proportion, and RR interval sequence standard deviation of the ECG signal after processing by the preprocessing unit, and assign weight coefficients to the trend slope, the low-frequency energy proportion, and the sequence standard deviation. The signal processing unit is further configured to determine the average voltage of the electrocardiogram signal at each moment within a predetermined time period based on the electrocardiogram signal processed by the preprocessing unit, and to determine the voltage value of the electrocardiogram signal at a future predetermined moment based on the trend slope, the proportion of low-frequency energy, the sequence standard deviation, the weighting coefficient, and the average value.

Images