A cardiology postoperative nursing data monitoring method and system

Abstract

The present invention relates to the technical field of medical data processing, and in particular to a cardiology postoperative nursing data monitoring method and system, including: obtaining an electrocardiogram sequence and a suspected r wave value; obtaining a peak performance degree of the suspected r wave value according to the electrocardiogram sequence and the suspected r wave value; obtaining a suspected q wave value; obtaining a performance degree of the suspected q wave value according to the suspected r wave value and the suspected q wave value; obtaining a suspected s wave value and its performance degree; obtaining a difference degree on both sides of the suspected q wave value according to the electrocardiogram sequence and the suspected q wave value; obtaining a difference degree on both sides of the suspected s wave value; obtaining a possibility of a true r wave value according to the peak performance degree, the difference degree on both sides and the performance degree; obtaining an r wave according to the possibility of the true r wave value; and obtaining a cardiology postoperative nursing data monitoring result according to all r waves. The present invention identifies a true r wave through the possibility of an accurate and reliable true r wave value, thereby improving the accuracy of cardiology postoperative nursing data monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a cardiology postoperative nursing data monitoring method and system. Background Art

[0002] The ECG signal is an important monitoring indicator in the postoperative care process of cardiology. The ECG signal bands are mainly composed of P waves, QRS complex waves and T waves. Among them, the R wave in the QRS complex wave is the most characteristic waveform. The R wave is an important reference for determining the various bands of the ECG signal and an important reference for ECG signal analysis. Therefore, it is necessary to accurately extract the R wave in the ECG signal.

[0003] At present, the traditional R-wave extraction method is to realize the recognition of R-wave by threshold screening based on the slope information of the change of the signal value of the ECG signal. However, this recognition method is overly dependent on the slope information of the ECG signal and is more susceptible to noise interference, resulting in a reduction in the accuracy of R-wave recognition in a noise interference environment, affecting the accuracy of ECG monitoring results during postoperative care in cardiology. Summary of the invention

[0004] The present invention provides a cardiology postoperative nursing data monitoring method and system to solve the existing problems.

[0005] A cardiology postoperative nursing data monitoring method and system of the present invention adopts the following technical solutions:

[0006] The present invention proposes a cardiology postoperative nursing data monitoring method, which comprises the following steps:

[0007] Acquire an electrocardiogram sequence, wherein each element in the electrocardiogram sequence is a sampling value;

[0008] Screening a number of suspected r-wave values ​​in the electrocardiogram sequence; obtaining a stable sampling value of each suspected r-wave value according to the electrocardiogram sequence and each suspected r-wave value; obtaining a peak expression degree of each suspected r-wave value according to the electrocardiogram sequence, each suspected r-wave value and its stable sampling value;

[0009] Obtaining the suspected q wave value near each suspected r wave value; obtaining the expression degree of the suspected q wave value near each suspected r wave value according to each suspected r wave value and its stable sampling value and the suspected q wave value near each suspected r wave value; obtaining the suspected s wave value near each suspected r wave value and its expression degree;

[0010] According to the ECG sequence and the suspected q wave value near each suspected r wave value, the difference between the suspected q wave value on both sides near each suspected r wave value is obtained; the difference between the suspected s wave value on both sides near each suspected r wave value is obtained;

[0011] According to the peak expression degree of each suspected r-wave value, the expression degree of the suspected q-wave value and the suspected s-wave value near the suspected r-wave value, and the difference degree between the suspected q-wave value and the suspected s-wave value near the suspected r-wave value, the possibility of each suspected r-wave value being the true r-wave value is obtained;

[0012] According to the possibility that each suspected r-wave value is a true r-wave value, several r-waves are obtained; according to all r-waves, the monitoring results of postoperative nursing data of the cardiology department are obtained.

[0013] Furthermore, the screening of a number of suspected r-wave values ​​in the electrocardiogram sequence includes the following specific steps:

[0014] The normalized result of the absolute value of the difference between each sampling value and the next sampling value in the ECG sequence is recorded as the slope of each sampling value; according to the preset slope threshold E, the sampling value with a slope greater than E is recorded as a suspected r-wave value.

[0015] Furthermore, the step of obtaining a stable sampling value of each suspected r-wave value according to the electrocardiogram sequence and each suspected r-wave value includes the following specific steps:

[0016] In the ECG sequence, a window of size M1 is constructed with any suspected r-wave value as the center, which is recorded as the first window, and M1 is the preset first window size; all sampling values ​​in the first window are clustered according to the sampling value size to obtain two clusters, and the variances of the two clusters are calculated respectively; in the cluster with the smallest variance, the average value of all sampling values ​​is recorded as the stable sampling value of the suspected r-wave value.

[0017] Furthermore, the step of obtaining the peak performance degree of each suspected r wave value according to the electrocardiogram sequence, each suspected r wave value and its stable sampling value includes the following specific steps:

[0018] In the ECG sequence, a window with a length of M2 is constructed with any suspected r-wave value as the center, recorded as the second window, and M2 is the preset second window size; the maximum sampling value in the second window is obtained, recorded as the suspected r-wave peak of the suspected r-wave value; the difference between the suspected r-wave peak and the stable sampling value of the suspected r-wave value is calculated, and the normalized result of the product of the difference and the slope of the suspected r-wave peak is recorded as the peak expression degree of the suspected r-wave value.

[0019] Furthermore, the obtaining of the suspected q-wave value near each suspected r-wave value comprises the following specific steps:

[0020] In the ECG sequence, take any suspected r-wave value as the last sampling value of the window to construct a window with a length of M3, recorded as the third window, where M3 is the preset third window size; obtain the minimum sampling value in the third window, recorded as the suspected q-wave value near the suspected r-wave value.

[0021] Furthermore, the expression degree of the suspected q wave value near each suspected r wave value is obtained according to each suspected r wave value and its stable sampling value and each suspected q wave value near the suspected r wave value, including the specific calculation method as follows:

[0022]

[0023] In the formula, poQ i Aw is the performance degree of the suspected q-wave value near the i-th suspected r-wave value, i is the stable sampling value of the i-th suspected r-wave value; Q i is the suspected q-wave value near the i-th suspected r-wave value; A i is the i-th suspected r-wave value; D is the preset limit coefficient; ln( ) is a logarithmic function with a natural constant as the base.

[0024] Furthermore, the method of obtaining the difference between the two sides of the suspected q wave value near each suspected r wave value according to the electrocardiogram sequence and the suspected q wave value near each suspected r wave value includes the following specific steps:

[0025] For each suspected q wave value near the suspected r wave value, a window of length M4 is constructed on both adjacent sides of the suspected q wave value, recorded as the fourth window, where M4 is the preset fourth window size; a short-time Fourier transform is performed on the sampling values ​​in each fourth window to obtain the spectrum of each fourth window, and the frequency with the highest amplitude in the spectrum of each fourth window is obtained, which is recorded as the main frequency of each fourth window; in the ECG sequence, the degree of difference between the two sides of the suspected q wave value near the i-th suspected r wave value is calculated as follows:

[0026]

[0027] Where, DoQ i AoQ1 is the difference between the two sides of the suspected q-wave value near the i-th suspected r-wave value. i AoQ2 represents the average value of all sample values ​​in the fourth window to the left of the suspected q-wave value near the i-th suspected r-wave value, i represents the average value of all sample values ​​in the fourth window to the right of the suspected q-wave value near the i-th suspected r-wave value; σoQ1 i represents the variance of all sample values ​​in the fourth window to the left of the suspected q-wave value near the i-th suspected r-wave value, σoQ2 iHoQ1 represents the variance of all sample values ​​in the fourth window to the right of the suspected q-wave value near the i-th suspected r-wave value; i 、HoQ2 i They respectively represent the main frequencies of the fourth window on the left and right sides of the suspected q-wave value near the i-th suspected r-wave value; sigmoid() is the sigmoid function; || is the absolute value function.

[0028] Furthermore, the possibility of each suspected r wave value being a true r wave value is obtained according to the peak expression degree of each suspected r wave value, the expression degree of the suspected q wave value and the suspected s wave value near the suspected r wave value, and the difference degree between the suspected q wave value and the suspected s wave value near the suspected r wave value, including the specific calculation method as follows:

[0029]

[0030] Where P i is the probability that the i-th suspected r-wave value is the true r-wave value; poA i is the peak performance degree of the i-th suspected r-wave value; poQ i is the performance degree of the suspected q-wave value near the i-th suspected r-wave value; poS i is the performance degree of the suspected s-wave value near the i-th suspected r-wave value; DoQ i is the difference between the suspected q-wave values ​​on both sides near the i-th suspected r-wave value; DoS i is the difference between the suspected s-wave values ​​on both sides near the i-th suspected r-wave value; Norm( ) represents the normalization function.

[0031] Further, the method of obtaining a plurality of r waves according to the possibility that each suspected r wave value is a true r wave value and obtaining the cardiology postoperative nursing data monitoring results according to all r waves includes the following specific steps:

[0032] In the ECG sequence, all suspected r-wave values ​​whose likelihood of true r-wave values ​​is greater than a preset likelihood threshold value P are recorded as true r-wave values; a data segment consisting of continuous true r-wave values ​​is recorded as an r-wave; the maximum value in each r-wave is obtained as the peak value of each r-wave, and the time interval between every two adjacent r-wave peak values ​​is calculated. If there is a time interval less than a preset minimum time interval threshold value C or greater than a preset maximum time interval threshold value V, the ECG signal is judged to be abnormal, otherwise, the ECG signal is judged to be normal.

[0033] The present invention also proposes a cardiology postoperative care data monitoring system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the aforementioned cardiology postoperative care data monitoring method.

[0034] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the performance degree of the suspected q wave value near each suspected r wave value according to each suspected r wave value and its stable sampling value and the suspected q wave value near each suspected r wave value, preliminarily judges the possibility that the suspected r wave value is the real r wave value, and provides an initial basis for judging the real r wave value; according to the electrocardiogram sequence and the suspected q wave value near each suspected r wave value, the difference degree on both sides of the suspected q wave value near each suspected r wave value is obtained, and the possibility that the suspected r wave value is the real r wave value is further judged, and the accuracy of identifying the real r wave value is improved; according to the peak performance degree of each suspected r wave value, the performance degree of the suspected q wave value near the suspected r wave value, and the suspected s wave value, and the difference degree on both sides of the suspected q wave value and the suspected s wave value near the suspected r wave value, the possibility that each suspected r wave value is the real r wave value is obtained, and the accuracy of identifying the real r wave value is further improved. So far, the present invention accurately identifies the r wave through the possibility of accurate and reliable real r wave values, and obtains more accurate postoperative nursing data monitoring results of cardiology. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A flowchart of a method for monitoring postoperative nursing data in cardiology according to the present invention;

[0037] Figure 2 A schematic diagram of an electrocardiogram curve provided in this embodiment. DETAILED DESCRIPTION

[0038] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a cardiology postoperative nursing data monitoring method and system proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0040] The following is a detailed description of a method and system for monitoring postoperative nursing data in cardiology provided by the present invention in conjunction with the accompanying drawings.

[0041] See also Figure 1 , which shows a flowchart of a method for monitoring postoperative nursing data in a cardiology department provided by an embodiment of the present invention, the method comprising the following steps:

[0042] Step S001: Obtain an ECG sequence.

[0043] It should be noted that the purpose of this embodiment is to identify the R wave signal in the electrocardiogram signal, so it is necessary to collect the electrocardiogram signal of the patient.

[0044] Specifically, for patients who need postoperative care in the cardiology department, an ECG monitor is used to sample the patient's ECG signal at a sampling frequency of W to obtain an ECG sequence; each element in the ECG sequence is a sampling value; W is a preset acquisition frequency, W=1KHz, and this embodiment is described using this as an example.

[0045] Step S002: Filter several suspected r-wave values ​​in the ECG sequence; obtain a stable sampling value of each suspected r-wave value based on the ECG sequence and each suspected r-wave value; obtain a peak expression degree of each suspected r-wave value based on the ECG sequence, each suspected r-wave value and its stable sampling value.

[0046] It should be noted that the ECG signal is mainly composed of P wave, QRS complex wave and T wave, as shown in the following figure. Figure 2 As shown in the figure, different waves correspond to different ECG activity processes. The R wave is the most characteristic waveform in the QRS complex wave. The sampling value of its peak is larger than that of other waves, and it is an important reference for determining the various bands of the ECG signal. Under normal circumstances, the R wave in the ECG signal has the fastest amplitude change rate within the ECG signal cycle. Therefore, the slope of the data can be used to screen the suspected R wave value, and then determine the peak performance of the suspected R wave value.

[0047] Specifically, the normalized result of the absolute value of the difference between each sampling value in the ECG sequence and the next sampling value is recorded as the slope of each sampling value; it should be noted that the slope of the last sampling value in the ECG sequence is equal to the slope of the previous sampling value. In this embodiment, linear normalization is used to normalize all the obtained absolute values ​​of the difference; according to the preset slope threshold E, the sampling value with a slope greater than E is recorded as a suspected r-wave value; the preset slope threshold E=0.35, and this embodiment is described as an example; with any suspected r-wave value as the center, a window of size M1 is constructed, recorded as the first window, M1 is the preset first window size, M1=200, and this embodiment is described as an example; for all the sampling values ​​in the first window, K-Means clustering with K=2 is performed according to the size of the sampling values ​​to obtain two clusters, and the variances of the two clusters are calculated respectively; in the cluster with the smallest variance, the average value of all the sampling values ​​is recorded as the stable sampling value of the suspected r-wave value; K-Means is a well-known technology, and the specific method is not introduced here. The full name of K-Means in Chinese is k-means clustering algorithm, and the full name of K-Means in English is k-means clustering algorithm.

[0048] Furthermore, in the ECG sequence, a window with a length of M2 is constructed with any suspected r-wave value as the center, which is recorded as the second window, where M2 is the preset second window size, M2=50, and this embodiment is described as an example; the maximum sampling value in the second window is obtained, which is recorded as the suspected r-wave peak of the suspected r-wave value; the difference between the suspected r-wave peak and the stable sampling value of the suspected r-wave value is calculated, and the normalized result of the product of the difference and the slope of the suspected r-wave peak is recorded as the peak expression degree of the suspected r-wave value; wherein, this embodiment adopts a linear normalization method for normalization processing, and the normalization object is the product of each suspected r-wave value obtained according to its second window.

[0049] Step S003: Obtain the suspected q-wave value near each suspected r-wave value; obtain the expression degree of the suspected q-wave value near each suspected r-wave value according to each suspected r-wave value and its stable sampling value and the suspected q-wave value near each suspected r-wave value; obtain the suspected s-wave value near each suspected r-wave value and its expression degree.

[0050] It should be noted that when the ECG signal is disturbed or the patient's heart rate is too slow, the peak value of the R wave in the ECG signal is relatively low. At this time, it is not accurate to identify the R wave only by the slope of the ECG sequence. In addition, some myocardial ischemia or other reasons will also cause changes in the data waveform of other stages in the ECG data, which will also interfere with the identification of the R wave. Therefore, it is necessary to combine the specific characteristics of the R wave in the ECG sequence for comprehensive screening. Although the R wave is a relatively obvious wave, the R wave often does not exist alone. The R wave is part of the QRS complex wave. It can be judged by the relationship between the R wave and the adjacent Q wave and S wave in the QRS complex wave. Among them, the Q wave and the S wave appear as two small waves in the opposite direction of the R wave, and the peak of the S wave is often greater than the Q wave. The PR segment and the ST segment are adjacent to the Q wave and the S wave, respectively, and the ECG signals of the PR segment and the ST segment are relatively stable. Therefore, the PR segment and the ST segment are used as the benchmark to judge the possibility that the peak of the ECG sequence is the R wave. In addition, in combination with the peak performance of the reverse waveform with adjacent peaks, if there are two reverse peaks, and the more obvious the two reverse peaks are, the more likely the data waveform in the middle is the r wave. And the sampling value of the reverse peak of the q wave usually does not exceed a certain proportion of the peak of the r wave, so the sampling value of the reverse peak suspected of the q wave is limited.

[0051] Specifically, in the ECG sequence, any suspected r wave value is taken as the last sampling value of the window to construct a window with a length of M3, which is recorded as the third window. M3 is the preset third window size, M3=100, and this embodiment is described as an example; the minimum sampling value in the third window is obtained, which is recorded as the suspected q wave value near the suspected r wave value;

[0052] In the ECG sequence, the degree of expression of the suspected q wave value near the i-th suspected r wave value is calculated as follows:

[0053]

[0054] Where poQ i Aw is the performance degree of the suspected q-wave value near the i-th suspected r-wave value, i is the stable sampling value of the i-th suspected r-wave value; Q i is the suspected q-wave value near the i-th suspected r-wave value; A i is the i-th suspected r-wave value; D is a preset limit coefficient, D=0.25, and this embodiment is described by taking this as an example; ln() is a logarithmic function with a natural constant as the base.

[0055] It should be noted that AW i -Q i It indicates the amplitude of the suspected q-wave value near the i-th suspected r-wave value. The larger its value is, the more prominent the suspected q-wave value is. It indicates the relative amplitude of the i-th suspected r-wave value and its nearby suspected q-wave value. The smaller its value is, the smaller the suspected q-wave value is than the suspected r-wave value, and the i-th suspected r-wave value may also be the real r-wave value. It represents the relationship between the relative amplitude of the i-th suspected r-wave value and its nearby suspected q-wave values ​​and the preset limit coefficient. The larger the value is, the more likely the i-th suspected r-wave value is to be the real r-wave value.

[0056] Furthermore, in the ECG sequence, a window with a length of M3 is constructed with any suspected r-wave value as the first sampling value of the window, and the minimum sampling value in the window is used as the suspected s-wave value near the suspected r-wave value. Similarly, the expression degree of the suspected s-wave value near the i-th suspected r-wave value is obtained according to the method of obtaining the expression degree of the suspected q-wave value near the i-th suspected r-wave value.

[0057] Step S004: according to the ECG sequence and the suspected q wave value near each suspected r wave value, obtain the difference between the suspected q wave value on both sides near each suspected r wave value; obtain the difference between the suspected s wave value on both sides near each suspected r wave value.

[0058] It should be noted that in the QRS complex wave, the sampling values ​​and slopes on both sides of the reverse peak of the Q wave and the reverse peak of the S wave are different. The greater the difference in the sampling values ​​and slopes on both sides of the suspected Q wave value and the suspected S wave value near the suspected R wave value, the more likely the suspected R wave value is to be the peak of the R wave.

[0059] Specifically, for each suspected q wave value near the suspected r wave value, a window of length M4 is constructed on both adjacent sides of the suspected q wave value, which is recorded as the fourth window, M4 is the preset fourth window size, M4=25, and this embodiment is described as an example; a short-time Fourier transform is performed on the sampling values ​​in each fourth window to obtain a spectrum diagram of each fourth window, and the frequency with the highest amplitude in the spectrum diagram of each fourth window is obtained, which is recorded as the main frequency of each fourth window; short-time Fourier transform is a well-known technology, and the specific method is not introduced here; in the electrocardiogram sequence, the degree of difference between the two sides of the suspected q wave value near the i-th suspected r wave value is calculated as follows:

[0060]

[0061] Where, DoQ i AoQ1 is the difference between the two sides of the suspected q-wave value near the i-th suspected r-wave value. i AoQ2 represents the average value of all sample values ​​in the fourth window to the left of the suspected q-wave value near the i-th suspected r-wave value, irepresents the average value of all sample values ​​in the fourth window to the right of the suspected q-wave value near the i-th suspected r-wave value; σoQ1 i represents the variance of all sample values ​​in the fourth window to the left of the suspected q-wave value near the i-th suspected r-wave value, σoQ2 i HoQ1 represents the variance of all sample values ​​in the fourth window to the right of the suspected q-wave value near the i-th suspected r-wave value; i 、HoQ2 i They respectively represent the main frequencies of the fourth window on the left and right sides of the suspected q-wave value near the i-th suspected r-wave value; sigmid() is the sigmoid function; || is the absolute value function.

[0062] It should be noted that Represents the amplitude difference of the sampling values ​​in the fourth window on the left and right sides of the suspected q wave value near the i-th suspected r wave value. The larger the value, the more likely the i-th suspected r wave value is to be the true r wave value; ||HoQ1 i -HoQ2 i | represents the degree of difference in the main frequencies of the fourth window on the left and right sides of the suspected q-wave value near the i-th suspected r-wave value. The larger its value is, the more likely the i-th suspected r-wave value is to be the true r-wave value.

[0063] Similarly, in the ECG sequence, the difference between the suspected s wave values ​​near the ith suspected r wave value is obtained according to the method for obtaining the difference between the suspected q wave values ​​near the ith suspected r wave value.

[0064] Step S005: According to the peak expression degree of each suspected r-wave value, the expression degree of the suspected q-wave value and the suspected s-wave value near the suspected r-wave value, and the difference degree between the suspected q-wave value and the suspected s-wave value near the suspected r-wave value, the possibility of each suspected r-wave value being the true r-wave value is obtained.

[0065] It should be noted that in the QRS complex wave, the Q wave is a negative wave generated by the incomplete consistency between the excitation conduction direction of the atrioventricular bundle and the electrocardiographic vector, so the true value of the Q wave is uncertain. In the process of R wave identification, the closer the performance of the suspected Q wave value is to the performance of the suspected S wave value, the greater the weight of the Q wave in the identification.

[0066] Specifically, the probability that the i-th suspected r-wave value is the true r-wave value is calculated as follows:

[0067]

[0068] Where P i is the probability that the i-th suspected r-wave value is the true r-wave value; poA iis the peak performance degree of the i-th suspected r-wave value; poQ i is the performance degree of the suspected q-wave value near the i-th suspected r-wave value; poS i is the performance degree of the suspected s-wave value near the i-th suspected r-wave value; DoQ i is the difference between the suspected q-wave values ​​on both sides near the i-th suspected r-wave value; DoS i is the difference between the two sides of the suspected s-wave value near the i-th suspected r-wave value; Norm () represents a linear normalization function, and the normalization object is the peak performance degree of each suspected r-wave value, or the peak performance degree of each suspected r-wave value.

[0069] It should be noted that Indicates the similarity between the performance of suspected Q-wave values ​​and suspected S-wave values. The larger the value, the greater the weight of Q-wave in R-wave identification. i ×DoQ i and PoS i ×DoS i They respectively represent the characteristic expression degrees of the suspected q-wave value and the suspected s-wave value near the i-th suspected r-wave value. The larger the value, the more likely the i-th suspected r-wave value is to be the true r-wave value.

[0070] Step S006: According to the possibility that each suspected r-wave value is a true r-wave value, several r-waves are obtained; according to all r-waves, the postoperative nursing data monitoring results of the cardiology department are obtained.

[0071] Specifically, in the ECG sequence, all suspected r-wave values ​​whose likelihood of true r-wave values ​​is greater than a preset likelihood threshold value P are recorded as true r-wave values; a data segment consisting of continuous true r-wave values ​​is recorded as an r-wave; the likelihood threshold value P = 0.9, and this embodiment is described using this as an example; the maximum value in each r-wave is obtained as the peak value of each r-wave, and the time interval between every two adjacent r-wave peak values ​​is calculated. If there is a time interval less than a preset minimum time interval threshold value C or greater than a preset maximum time interval threshold value V, it is judged that the ECG signal is abnormal, otherwise, it is judged that the ECG signal is normal; the preset minimum time interval threshold value C = 0.6 seconds, and the preset maximum time interval threshold value V = 1 second, and this embodiment is described using this as an example.

[0072] At this point, this embodiment is completed.

[0073] The present invention also provides a cardiology postoperative care data monitoring system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the aforementioned cardiology postoperative care data monitoring method.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cardiology postoperative nursing data monitoring method, characterized in that: The method comprises the following steps: Acquire an electrocardiogram sequence, wherein each element in the electrocardiogram sequence is a sampling value; Screening a number of suspected r-wave values ​​in the electrocardiogram sequence; obtaining a stable sampling value of each suspected r-wave value according to the electrocardiogram sequence and each suspected r-wave value; obtaining a peak expression degree of each suspected r-wave value according to the electrocardiogram sequence, each suspected r-wave value and its stable sampling value; Obtaining the suspected q wave value near each suspected r wave value; obtaining the expression degree of the suspected q wave value near each suspected r wave value according to each suspected r wave value and its stable sampling value and the suspected q wave value near each suspected r wave value; obtaining the suspected s wave value near each suspected r wave value and its expression degree; According to the ECG sequence and the suspected q wave value near each suspected r wave value, the difference between the suspected q wave value on both sides near each suspected r wave value is obtained; the difference between the suspected s wave value on both sides near each suspected r wave value is obtained; According to the peak expression degree of each suspected r-wave value, the expression degree of the suspected q-wave value and the suspected s-wave value near the suspected r-wave value, and the difference degree between the suspected q-wave value and the suspected s-wave value near the suspected r-wave value, the possibility of each suspected r-wave value being the true r-wave value is obtained; According to the possibility that each suspected r-wave value is a true r-wave value, several r-waves are obtained; according to all r-waves, the postoperative nursing data monitoring results of the cardiology department are obtained; The step of obtaining a stable sampling value of each suspected r-wave value according to the electrocardiogram sequence and each suspected r-wave value includes the following specific steps: In the ECG sequence, a window of size M1 is constructed with any suspected r-wave value as the center, which is recorded as the first window, and M1 is the preset first window size; all sampling values ​​in the first window are clustered according to the sampling value size to obtain two clusters, and the variances of the two clusters are calculated respectively; in the cluster with the smallest variance, the average value of all sampling values ​​is recorded as the stable sampling value of the suspected r-wave value; The step of obtaining the peak performance degree of each suspected r wave value according to the electrocardiogram sequence, each suspected r wave value and its stable sampling value includes the following specific steps: In the ECG sequence, taking any suspected r-wave value as the center, construct a window with a length of M2, recorded as the second window, where M2 is the preset second window size; obtain the maximum sampling value in the second window, recorded as the suspected r-wave peak of the suspected r-wave value; calculate the difference between the suspected r-wave peak and the stable sampling value of the suspected r-wave value, and normalize the product of the difference and the slope of the suspected r-wave peak, recorded as the peak expression degree of the suspected r-wave value; The specific steps of obtaining the suspected q-wave value near each suspected r-wave value are as follows: In the ECG sequence, any suspected r-wave value is taken as the last sampling value of the window to construct a window with a length of M3, which is recorded as the third window, and M3 is the preset third window size; the minimum sampling value in the third window is obtained, which is recorded as the suspected q-wave value near the suspected r-wave value; The specific calculation method of obtaining the performance degree of the suspected q wave value near each suspected r wave value according to each suspected r wave value and its stable sampling value and each suspected q wave value near each suspected r wave value is as follows: Where poQ i Aw is the performance degree of the suspected q-wave value near the i-th suspected r-wave value, i is the stable sampling value of the i-th suspected r-wave value; Q i is the suspected q-wave value near the i-th suspected r-wave value; A i is the i-th suspected r-wave value; D is the preset limit coefficient; ln() is a logarithmic function with a natural constant as the base; The step of obtaining the difference between the two sides of the suspected q wave value near each suspected r wave value according to the electrocardiogram sequence and the suspected q wave value near each suspected r wave value includes the following specific steps: For each suspected q wave value near the suspected r wave value, a window of length M4 is constructed on both adjacent sides of the suspected q wave value, recorded as the fourth window, where M4 is the preset fourth window size; a short-time Fourier transform is performed on the sampling values ​​in each fourth window to obtain the spectrum of each fourth window, and the frequency with the highest amplitude in the spectrum of each fourth window is obtained, which is recorded as the main frequency of each fourth window; in the ECG sequence, the degree of difference between the two sides of the suspected q wave value near the i-th suspected r wave value is calculated as follows: Where, DoQ i AoQ1 is the difference between the two sides of the suspected q-wave value near the i-th suspected r-wave value. i AoQ2 represents the average value of all sample values ​​in the fourth window to the left of the suspected q-wave value near the i-th suspected r-wave value, i represents the average value of all sample values ​​in the fourth window to the right of the suspected q-wave value near the i-th suspected r-wave value; σoQ1 i represents the variance of all sample values ​​in the fourth window to the left of the suspected q-wave value near the i-th suspected r-wave value, σoQ2 i HoQ1 represents the variance of all sample values ​​in the fourth window to the right of the suspected q-wave value near the i-th suspected r-wave value; i 、HoQ2 i Respectively represent the main frequencies of the fourth window on the left and right sides of the suspected q-wave value near the i-th suspected r-wave value; sigmoid() is the sigmoid function; || is the absolute value function; The possibility of each suspected r wave value being a true r wave value is obtained according to the peak expression degree of each suspected r wave value, the expression degree of the suspected q wave value and the suspected s wave value near the suspected r wave value, and the difference degree between the suspected q wave value and the suspected s wave value near the suspected r wave value, including the specific calculation method as follows: Where P i is the probability that the i-th suspected r-wave value is the true r-wave value; poA i is the peak performance degree of the i-th suspected r-wave value; poQ i is the performance degree of the suspected q-wave value near the i-th suspected r-wave value; poS i is the performance degree of the suspected s-wave value near the i-th suspected r-wave value; DoQ i is the difference between the suspected q-wave values ​​on both sides near the i-th suspected r-wave value; DoS i is the degree of difference between the suspected s-wave values ​​on both sides near the i-th suspected r-wave value; Norm() represents the normalization function.

2. According to claim 1, a cardiology postoperative nursing data monitoring method is characterized in that: The specific steps of screening a number of suspected r-wave values ​​in the electrocardiogram sequence are as follows: The normalized result of the absolute value of the difference between each sampling value and the next sampling value in the ECG sequence is recorded as the slope of each sampling value; according to the preset slope threshold E, the sampling value with a slope greater than E is recorded as a suspected r-wave value.

3. According to claim 1, a cardiology postoperative nursing data monitoring method is characterized in that: The method of obtaining a plurality of r waves according to the possibility that each suspected r wave value is a true r wave value and obtaining the cardiology postoperative nursing data monitoring results according to all r waves includes the following specific steps: In the ECG sequence, all suspected r-wave values ​​whose likelihood of true r-wave values ​​is greater than a preset likelihood threshold value P are recorded as true r-wave values; a data segment consisting of continuous true r-wave values ​​is recorded as an r-wave; the maximum value in each r-wave is obtained as the peak value of each r-wave, and the time interval between every two adjacent r-wave peak values ​​is calculated. If there is a time interval less than a preset minimum time interval threshold value C or greater than a preset maximum time interval threshold value V, the ECG signal is judged to be abnormal, otherwise, the ECG signal is judged to be normal.

4. A cardiology postoperative care data monitoring system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of a cardiology postoperative care data monitoring method as described in any one of claims 1 to 3 are implemented.

Images