Personalized nursing follow-up visit method and system for coronary intervention patient

Abstract

The invention relates to the technical field of medical data mining, in particular to a personalized nursing follow-up visit method and system for coronary intervention patients. According to the method, the abnormal evaluation indexes are obtained according to the abnormal change conditions of the R-R interval and the ST section in the historical complex center dynamic period, and the abnormal period is screened; determining a psychological influence period according to the abnormal period distribution and the abnormal approximation degree; correcting the psychological influence period through the data deviation between the non-abnormal period and the psychological influence period; predicting all the periods after correction to obtain predicted electrocardiogram data, and determining a nursing follow-up review adjustment result by comparing the abnormal evaluation index during actual collection with the predicted electrocardiogram data. According to the method, abnormity preliminary screening is carried out through the R-R interval and the ST period of the historical cardiac cycle, abnormity influenced by psychological factors is further analyzed and corrected, the accuracy and reliability of follow-up and actual analysis are improved, and the effect of follow-up adjustment and nursing follow-up visit is better.

Description

Technical Field

[0001] This invention relates to the field of medical data mining technology, specifically to a personalized nursing follow-up method and system for patients undergoing coronary intervention. Background Technology

[0002] Coronary artery bypass grafting (CABG) can effectively restore blood supply to ischemic myocardium and relieve patients' symptoms. This surgery has now become one of the routine procedures in cardiac surgery. However, the impact of a surgical procedure on patients and its related perioperative and even prognostic complications cannot be ignored. Therefore, comprehensive nursing care and follow-up are necessary for CABG patients to observe the effectiveness of the surgery and the degree of improvement in patients' quality of life.

[0003] Current technology in the personalized nursing follow-up of patients undergoing coronary intervention involves notifying them to return to the hospital regularly for electrocardiogram (ECG) checkups to assess their recovery progress and detect any cardiac problems such as heart failure or arrhythmias. However, during ECG examinations, patients may experience increased heart rate due to emotional stress, anxiety, or fear. These psychological factors can cause abnormalities in the ECG waveform, affecting the accuracy of the nursing follow-up assessment and leading to errors, thus hindering the effectiveness of subsequent nursing adjustments. Summary of the Invention

[0004] To address the technical problem in existing technologies where psychological factors can cause abnormalities in electrocardiogram waveforms, thus affecting the accuracy of nursing follow-up assessments and leading to errors, the present invention aims to provide a personalized nursing follow-up method and system for patients undergoing coronary intervention. The specific technical solution adopted is as follows: This invention provides a personalized nursing follow-up method for patients undergoing coronary intervention, the method comprising: Obtain the patient's historical electrocardiogram data and cardiac cycles; For each cardiac cycle, abnormal evaluation indicators are obtained based on the degree of shortening of the RR interval and the degree of slope change of the ST segment of the local cardiac cycle; abnormal cycles are identified from the cardiac cycles based on the abnormal evaluation indicators. Based on the distribution of abnormal cycles and the approximation of corresponding abnormal evaluation indicators, the psychological impact index of each abnormal cycle is obtained; the psychological impact cycle is screened out from the abnormal cycles based on the psychological impact index; the electrocardiogram data of each psychological impact cycle is corrected by the deviation between the psychological impact cycle and the non-abnormal cycle in the electrocardiogram data, and the corrected psychological impact cycle is obtained. Based on the ECG data from the modified psychological impact period and the non-psychological impact period, predictive ECG data is obtained; based on the abnormality evaluation indicators of the current follow-up ECG data and the degree of similarity between the current follow-up ECG data and the predicted ECG data, the current follow-up nursing care adjustment results are determined.

[0005] Furthermore, the method for obtaining the anomaly evaluation index includes: For any cardiac cycle, the RR interval shortening index of the cardiac cycle is obtained based on the degree of change of the RR interval between all cardiac cycles within a preset local range, as well as the numerical distribution and deviation of the RR interval between the cardiac cycle and adjacent cardiac cycles. Obtain the slope of the ST segment in each cardiac cycle; accumulate the slope differences between every two adjacent cardiac cycles within a preset local range to obtain the ST segment variability of the cardiac cycle; combine the slope of the ST segment and the ST segment variability of the cardiac cycle to obtain the ST segment depression index of the cardiac cycle. By combining the RR interval shortening index and ST segment depression index of this cardiac cycle, abnormal evaluation indexes for this cardiac cycle are obtained.

[0006] Furthermore, the method for obtaining the RR interval shortening index includes: The maximum value of the RR intervals during all cardiac cycles within a preset local range is taken as the maximum interval value. The difference between each RR interval and the maximum interval value during cardiac cycles within the preset local range is calculated, and all differences are summed to obtain the degree of change of the cardiac cycle. Calculate the mean of the RR intervals during all cardiac cycles within a preset local range for this cardiac cycle, and use it as the local interval mean of this cardiac cycle; calculate the mean of the RR intervals between this cardiac cycle and adjacent cardiac cycles, and use it as the adjacent interval mean of this cardiac cycle; The shortening proximity of the cardiac cycle is obtained by negatively correlating the difference between the mean of adjacent intervals of the cardiac cycle and the lower limit of the preset range; the difference between the mean of adjacent intervals of the cardiac cycle and the mean of local intervals is used as the proximity deviation of the cardiac cycle. By combining the degree of change, the degree of shortening proximity, and the degree of adjacent deviation of the cardiac cycle, the RR interval shortening index of the cardiac cycle is obtained.

[0007] Furthermore, the method for obtaining the abnormal period includes: Cardiac cycles with abnormal evaluation indicators exceeding a preset abnormal threshold are defined as abnormal cycles.

[0008] Furthermore, the method for obtaining the psychological impact indicators includes: The continuously distributed abnormal period is taken as an abnormal interval, and the variance of the abnormal evaluation index in each abnormal interval is negatively correlated and mapped to obtain the abnormal approximate index of each abnormal interval. After calculating the difference in interval length between each abnormal interval and each other abnormal interval, the mean of all interval length differences is calculated to obtain the distribution difference index of each abnormal interval. For any abnormal cycle in the abnormal interval, within the abnormal interval where the abnormal cycle is located, the abnormal cycles whose difference in the abnormal evaluation index between them and the abnormal cycle is less than a preset difference threshold are taken as the distribution cycle of the abnormal cycle; the ratio of the number of distribution cycles of the abnormal cycle to the number of all abnormal cycles in the abnormal interval is taken as the distribution quantity index of the abnormal cycle. By combining the distribution quantity index of the abnormal cycle with the abnormal approximation index and distribution difference index of the abnormal interval, the psychological impact index of the abnormal cycle is obtained.

[0009] Furthermore, the method for obtaining the psychological influence cycle includes: The abnormal period in which the psychological impact index exceeds the preset psychological threshold is defined as the psychological impact period.

[0010] Furthermore, the method for obtaining the modified psychological influence cycle includes: The amplitude values ​​of the electrocardiogram data in each cardiac cycle are sorted in chronological order to obtain a data sequence; For any psychological impact cycle, the mean amplitude of the ECG data with the same sequence number in the data sequence of all non-abnormal cycles before the psychological impact cycle is taken as the normal mean for each sequence number; the mean amplitude of the ECG data with the same sequence number in the data sequence of all non-abnormal cycles before the psychological impact cycle and all psychological impact cycles is taken as the distribution mean for each sequence number. The ratio of the difference between the normal mean and the distribution mean to the mean is used as the correction weight for each index. The product of the amplitude of the electrocardiogram data corresponding to each sequence number in the psychological impact cycle and the correction weight is used as the corrected electrocardiogram data for each sequence number in the psychological impact cycle; the psychological impact cycle is updated by the corrected electrocardiogram data to obtain the corresponding corrected psychological impact cycle.

[0011] Furthermore, the method for obtaining the predicted electrocardiogram data includes: The mean amplitude of ECG data with the same sequence number in all data sequences of both the corrected psychological influence period and the non-psychological influence period is used as the predicted mean; the predicted mean is then arranged in sequence to obtain the predicted ECG data.

[0012] Furthermore, the method for obtaining the results of the follow-up nursing care adjustment includes: Calculate the DTW value between the current ECG data and the predicted ECG data and perform normalization to obtain the prediction deviation index of the current ECG. If the prediction deviation index is greater than or equal to the preset prediction threshold, obtain the abnormal evaluation index of all cardiac cycles in the current follow-up ECG data; calculate the mean of all abnormal evaluation indexes in the current follow-up ECG data as the abnormality analysis degree of the current follow-up; when the abnormality analysis degree is less than or equal to the preset analysis threshold, record the patient's current follow-up nursing care adjustment result as delayed, otherwise record the follow-up nursing care adjustment result as advanced. If the prediction deviation index is less than the preset prediction threshold, the patient's current follow-up nursing care adjustment result will be recorded as no adjustment.

[0013] The present invention also provides a personalized care follow-up system for patients undergoing coronary intervention, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0014] The present invention has the following beneficial effects: This invention uses historical electrocardiograms (ECGs) to initially screen for abnormal changes in the RR interval and ST segment. Since some abnormal cycles may be identified as abnormal due to psychological factors, further differentiation is made based on the consistency of cycle distribution and degree of abnormality between psychological and physiological abnormalities to identify cycles with psychological influence. The ECG data of these psychologically influenced cycles can then be corrected by adjusting the data in the psychologically influenced cycles based on the data deviation between non-abnormal cycles and those with psychological influence, resulting in corrected psychologically influenced cycles. Finally, all corrected cycles are used to predict the next actual cycle, yielding predicted ECG data for more reliable predictions. The predicted ECG data is then compared with the actual collected data, and abnormalities assessed during actual collection are used to comprehensively determine subsequent nursing follow-up adjustments. This invention, by screening for abnormalities in the RR interval and ST segment of historical cardiac cycles and then identifying and correcting abnormalities caused by patient psychological factors based on the degree and distribution of abnormalities, improves the accuracy and reliability of the predicted results and actual analysis, leading to better outcomes in subsequent nursing follow-up adjustments. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating a personalized nursing follow-up method for coronary intervention patients, provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of the cardiac cycle in an electrocardiogram provided in one embodiment of the present invention; Figure 3 A schematic diagram of the RR interval in an electrocardiogram is provided as an embodiment of the present invention; Figure 4 A flowchart illustrating a method for obtaining anomaly evaluation indicators according to an embodiment of the present invention; Figure 5 This is a schematic diagram of predicted electrocardiogram (ECG) data and currently reviewed ECG data provided in one embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a personalized care follow-up method and system for coronary intervention patients proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, 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 pertains.

[0019] The following description, in conjunction with the accompanying drawings, details a specific scheme for a personalized nursing follow-up method and system for coronary intervention patients provided by this invention.

[0020] Please see Figure 1 The diagram illustrates a flowchart of a personalized nursing follow-up method for coronary intervention patients according to an embodiment of the present invention, which includes the following steps: S1: Obtain the patient's historical electrocardiogram data and cardiac cycles.

[0021] In personalized follow-up care for patients undergoing coronary intervention, patients are instructed to return to the hospital regularly for electrocardiogram (ECG) examinations to assess their recovery progress and detect potential cardiac problems such as heart failure and arrhythmias. However, because patients may experience increased heart rate due to emotional stress, anxiety, or fear during ECG examinations, the waveform changes on the ECG may not fully reflect their true cardiac function, especially during periods of intense emotional fluctuation. This can lead to erroneous diagnostic results and affect the accuracy of the assessment.

[0022] After a patient undergoes coronary intervention surgery, the hospital first needs to follow up with the patient by phone to record the patient's condition after discharge. Then, the patient is notified to return to the hospital for a check-up every month to obtain the patient's electrocardiogram (ECG) data from the past six months. If the past six months of check-ups are less than six months, all ECG data from the check-ups are obtained, along with each cardiac cycle in the ECG.

[0023] Please see Figure 2 This illustration shows a schematic diagram of the cardiac cycle on an electrocardiogram (ECG) according to an embodiment of the present invention. An ECG uses an electrocardiograph to record the changes in electrical activity of the heart during each cardiac cycle. A cardiac cycle refers to the time required for the heart to complete one contraction and relaxation. Generally, the contraction sequence of the heart is atrial contraction followed by ventricular contraction. On an ECG, the cardiac cycle is represented by a complete cycle consisting of P waves, QRS waves, and T waves. The P wave represents atrial contraction, the QRS wave represents ventricular contraction, and the T wave represents ventricular relaxation. The length of the entire cardiac cycle determines the heart rate. An ECG typically displays multiple cardiac cycles, reflecting changes in waveforms such as the P wave, QRS wave, and T wave.

[0024] Determining the cardiac cycle is crucial for understanding heart rhythm and the condition at different time points. For example, abnormal P waves suggest atrial lesions or conduction abnormalities within the atria, while abnormal QRS complexes indicate abnormal ventricular contraction, and abnormal T waves represent ventricular depolarization, i.e., abnormal diastole. Therefore, by observing the changes between these waves, abnormalities can be preliminarily identified.

[0025] S2: For each cardiac cycle, based on the degree of shortening of the RR interval and the degree of slope change of the ST segment compared to the adjacent cardiac cycle, an abnormal evaluation index is obtained for each cardiac cycle; abnormal cycles are identified from the cardiac cycles based on the abnormal evaluation index.

[0026] In an electrocardiogram (ECG), the RR interval is the time interval between the peak values ​​of the R waves in two consecutive heartbeats. It is used to assess the stability and normal function of the heart rhythm. Under normal circumstances, the resting heart rate of an adult is usually 60-100 beats per minute. During periods of emotional stress, the heart rate may exceed 100 beats per minute, manifesting as sinus tachycardia, which shortens the RR interval. During the recovery period after coronary intervention, patients may experience changes in the electrical activity of the atria and atrioventricular nodes. Some patients may experience shortened atrioventricular conduction time due to hemodynamic or electrophysiological changes, resulting in a localized shortening of the RR interval. Sinus tachycardia or atrial fibrillation in the early postoperative period after coronary intervention can also lead to a shortened RR interval. Please refer to [link to relevant documentation]. Figure 3 This illustrates a schematic diagram of the RR interval in an electrocardiogram provided by an embodiment of the present invention.

[0027] In an electrocardiogram (ECG), the ST segment reflects the changes in the ventricular myocardium from the end of depolarization to the beginning of repolarization. A normal ST segment should be on an isoelectric line or with a slight vertical offset. When the heart rate is too high, sympathetic nerve excitation may cause ST segment depression, usually an upsloping ST segment depression, where the ST segment slope is affected. Some patients may experience myocardial inflammation after coronary intervention, and this inflammation may affect the ECG presentation, resulting in mild ST segment depression. Please refer to [link to ECG]. Figure 3 The diagram illustrates a schematic representation of ST segment depression according to an embodiment of the present invention.

[0028] Therefore, a preliminary assessment of cardiac cycle abnormalities is performed based on changes in the shortening of the RR interval and the decrease in the slope of the ST segment. In this embodiment of the invention, the method for obtaining the abnormality evaluation indicators of the cardiac cycle is described in [reference needed]. Figure 4 The diagram illustrates a flowchart of a method for obtaining anomaly evaluation indicators according to an embodiment of the present invention. The method includes the following steps: S201: For any cardiac cycle, based on the consistency of the RR interval between the cardiac cycle and all cardiac cycles within a preset local range, as well as the numerical distribution and deviation of the RR interval between the cardiac cycle and adjacent cardiac cycles, the RR interval shortening index of the cardiac cycle is obtained.

[0029] When there is an abnormal heart rhythm, it usually manifests as a series of abnormal heartbeats. Therefore, when the heartbeat is analyzed locally, if there is a high degree of shortening in all local heartbeats, and the shortening is more severe in adjacent cases, it indicates that the heartbeat cycle is more likely to reflect an abnormality. Furthermore, the closer the heartbeat frequency is to the lowest limit of the normal range, the more severe the shortening of the RR interval is. Comprehensive analysis yields the RR interval shortening index.

[0030] In this embodiment of the invention, the method for obtaining the RR interval shortening index includes: First, the maximum value of the RR intervals during all cardiac cycles within a preset local range is taken as the maximum interval value, reflecting the slowest interval within the local heartbeat range. Then, the difference between each RR interval during the cardiac cycle within the preset local range and the maximum interval value is calculated. All differences are then summed to obtain the degree of variability of the cardiac cycle. The degree of shortening of each RR interval within the local range reflects the degree of change in the local heart rhythm; a greater degree of variability indicates a higher degree of local shortening. In this embodiment of the invention, the preset local range is set as the range of the 10 cardiac cycles closest to the cardiac cycle; the specific size of the range can be adjusted by the implementer.

[0031] Then, the mean value of the RR intervals during all cardiac cycles within a preset local range is calculated as the local interval mean value of the cardiac cycle. The mean value of the RR intervals between the cardiac cycle and adjacent cardiac cycles is calculated as the adjacent interval mean value of the cardiac cycle. The mean values ​​of the RR intervals are obtained from the local and adjacent ranges respectively so as to further quantify the adjacent variation amplitude of the cardiac cycle.

[0032] Further, a negative correlation mapping is performed on the difference between the mean of adjacent intervals in the cardiac cycle and the lower limit of a preset range to obtain the shortening proximity of the cardiac cycle. The lower limit of the preset range is the normal minimum value of the RR interval during normal beating. The closer the mean of adjacent intervals is to the lower limit of the range, the more obvious the shortening trend of the heartbeat and the more severe the shortening. The difference between the mean of adjacent intervals and the mean of local intervals in the cardiac cycle is used as the adjacent deviation degree of the cardiac cycle. The degree of deviation reflects the relative degree of shortening of the cardiac cycle within a local range. The larger the adjacent deviation, the more severe the shortening of this cycle. It should be noted that the negative correlation mapping is a technique well known to those skilled in the art and can be in the form of an inverse proportional value or a negative exponential power, which will not be elaborated here.

[0033] Finally, by combining the variability, proximity of shortening, and adjacent deviation of the cardiac cycle, the RR interval shortening index of the cardiac cycle is obtained. In this embodiment of the invention, the product of the variability, proximity of shortening, and adjacent deviation of the cardiac cycle is used as the RR interval shortening index of the cardiac cycle. The larger the RR interval shortening index, the more abnormal the cardiac rhythm. As an example, the expression for the RR interval shortening index is: In the formula, Represented as the first The RR interval shortening index per cardiac cycle Represented as the first The degree of change in a cardiac cycle Represented as the first Mean of adjacent intervals in a cardiac cycle Represented as the first Mean of local intervals in a cardiac cycle This is represented as the lower limit of the preset range. Represented as an absolute value extraction function, It is represented as an exponential function with the natural constant as the base. Represented as the first Adjacent deviation of one cardiac cycle, Represented as the first The proximity of shortened cardiac cycles.

[0034] S202: Obtain the slope of the ST segment in each cardiac cycle; accumulate the slope difference between every two adjacent cardiac cycles within a preset local range of the cardiac cycle to obtain the ST segment variability of the cardiac cycle; combine the slope of the ST segment and the ST segment variability of the cardiac cycle to obtain the ST segment depression index of the cardiac cycle.

[0035] Further analysis of ST segment changes reveals that the higher the cumulative slope change in a localized cardiac cycle, the more likely the cardiac cycle is in a period of high abnormality, and the higher the probability of cardiac cycle abnormality. Furthermore, when the cardiac cycle itself has a slope, it is also reflected in the ST segment deviating from the normal level, corresponding to a higher probability of cardiac cycle abnormality.

[0036] By combining the slope of the ST segment and the sum of the slope differences of the ST segment during the cardiac cycle, the ST segment depression index is obtained. In this embodiment of the invention, the sum of the slope of the ST segment and the ST segment variability during the cardiac cycle is used as the ST segment depression index. For example, the expression for the ST segment depression index is: In the formula, Represented as the first ST segment depression index per cardiac cycle Represented as the first The slope of the ST segment in one cardiac cycle, Represented as the first ST segment variability over one cardiac cycle.

[0037] S203: Combining the RR interval shortening index and ST segment depression index of this cardiac cycle, obtain the abnormal evaluation index of this cardiac cycle.

[0038] Finally, by combining the shortening of the RR interval and the ST segment depression, the abnormality of each cardiac cycle is evaluated. In this embodiment of the invention, the product of the RR interval shortening index and the ST segment depression index of the cardiac cycle is used as the abnormality evaluation index of the cardiac cycle. The larger the RR interval shortening index and the ST segment depression index, the more severe the RR interval shortening and ST segment depression of the cardiac cycle are, and therefore the higher the abnormality evaluation of the cardiac cycle is.

[0039] Furthermore, abnormal cycles can be determined from cardiac cycles based on abnormal evaluation indicators. In this embodiment of the invention, cardiac cycles with abnormal evaluation indicators greater than a preset abnormal threshold are considered abnormal cycles. The abnormal evaluation indicators are normalized, and the preset abnormal threshold is set to 0.5. When the normalized abnormal evaluation indicator is greater than 0.5, it indicates that the quantitative abnormal assessment result is serious, and the corresponding cardiac cycle has an abnormal rhythm. The cardiac cycle is then considered an abnormal cycle. The specific numerical setting can be adjusted by the implementer according to the specific implementation situation and is not limited here. It should be noted that normalization is a well-known technique in the art. The choice of normalization can be linear normalization, maximum-minimum normalization, or standard normalization, etc. The specific normalization method is not limited here.

[0040] S3: Based on the distribution of abnormal cycles and the approximation of corresponding abnormal evaluation indicators, obtain the psychological impact index for each abnormal cycle; based on the psychological impact index, filter out the psychological impact cycles from the abnormal cycles; through the deviation of the psychological impact cycles and non-abnormal cycles in the electrocardiogram data, correct the electrocardiogram data in each psychological impact cycle to obtain the corrected psychological impact cycle.

[0041] After coronary artery surgery, the shortened RR interval and ST segment depression on the electrocardiogram (ECG) are usually caused by the impact of the surgical procedure itself on the heart. These changes are often related to physiological responses during or early after surgery, and the shortened RR interval and ST segment depression are usually continuous and may persist for a period of time. In contrast, increased heart rate caused by psychological factors is usually closely related to emotional fluctuations. When patients experience psychological stress or emotional fluctuations, sympathetic nerve activity increases, which may lead to an increased heart rate, manifesting as transient ECG changes such as increased heart rate and shortened RR interval. Unlike the physiological changes caused by surgery, heart rate abnormalities caused by psychological state are usually temporary, and their manifestations often return to normal as the patient's emotions calm down.

[0042] Heart rate abnormalities influenced by psychological factors are typically intermittent and short-lived. While the timing of these changes is uncertain and the frequency is low, heart rate and electrocardiogram (ECG) findings usually return to normal quickly after the patient's emotions stabilize. Furthermore, the degree of heart rate abnormality in cycles caused by psychological factors is generally consistent between cycles. In contrast, heart rate abnormalities caused by physiological changes resulting from surgery manifest as heart murmurs, and the abnormalities are more complex, with varying degrees of abnormality between cycles.

[0043] Therefore, based on the distribution and the similarity of abnormal evaluation indicators, the abnormal cycle is likely influenced by psychological factors. In this embodiment of the invention, the method for obtaining the psychological influence indicators includes: First, the continuously distributed abnormal cycles are taken as an abnormal interval. The variance of the abnormal evaluation index in each abnormal interval is negatively correlated and mapped to obtain the abnormal approximate index for each abnormal interval. Since abnormal heart rhythms are usually continuous, the overall analysis is carried out through continuous abnormal cycles. When the abnormal evaluation indexes in continuous abnormal cycles are closer, that is, the smaller the variance and the larger the abnormal approximate index, it indicates that the continuous abnormality is closer to being caused by psychological factors. Conversely, abnormalities caused by physiological factors are irregular.

[0044] Furthermore, after calculating the difference in interval length between each abnormal interval and each other abnormal interval, the mean of all interval length differences is calculated to obtain the distribution difference index for each abnormal interval. Since the abnormal manifestations caused by psychological factors are relatively short-lived and the abnormal period is short, there will be a large difference in length between them and other intervals. The distribution difference of intervals is used for quantification. When the distribution difference index is larger, it indicates that the overall difference between the abnormal interval and other intervals is higher, and the possibility that it is caused by psychological factors is higher.

[0045] Further considering the local analysis of the impact of each abnormal cycle in the abnormal interval, for any abnormal cycle in the abnormal interval, the abnormal cycle in the abnormal interval where the abnormal evaluation index difference with the abnormal cycle is less than the preset difference threshold is taken as the distribution cycle of the abnormal cycle. The cycle with similar abnormal evaluation index is selected in the abnormal interval. In the embodiment of the present invention, the preset difference threshold is set to 0.1.

[0046] For abnormal cycles, the more distribution cycles selected, the higher the probability that the interval is caused by a single psychological factor. The situation where psychological and physiological factors have a mixed influence in the abnormal interval is relatively small, and the corresponding abnormal cycle is more likely to be a cycle affected by psychological factors. Therefore, the ratio of the number of distribution cycles of the abnormal cycle to the number of all abnormal cycles in the abnormal interval is used as the distribution quantity index of the abnormal cycle. The larger the ratio, that is, the larger the distribution quantity index, the higher the probability that the abnormal cycle is affected by psychological factors.

[0047] Finally, by combining the distribution quantity index of the abnormal cycle, as well as the abnormal approximation index and distribution difference index of the abnormal interval, the psychological impact index of the abnormal cycle is obtained. In this embodiment of the invention, the distribution quantity index of the abnormal cycle, the abnormal approximation index of the abnormal interval, and the distribution difference index of the abnormal cycle are multiplied to obtain the psychological impact index of the abnormal cycle. The larger the distribution quantity index, the abnormal approximation index, and the distribution difference index, the more similar cycles there are in the interval, the closer the overall abnormal evaluation distribution is, the shorter the duration of the distribution, and the fewer the continuous similar situations. In this case, the higher the probability that the abnormal cycle is caused by psychological factors, and the larger the psychological impact index is.

[0048] Therefore, psychological impact cycles can be further screened from abnormal cycles based on psychological impact indicators. In this embodiment of the invention, abnormal cycles with psychological impact indicators greater than a preset psychological threshold are taken as psychological impact cycles. The psychological impact indicators are normalized, and the preset psychological threshold is set to 0.6. That is, when the normalized psychological impact indicator is greater than 0.6, it indicates that the abnormal cycle is more likely to be caused by psychological factors, and the abnormal cycle is taken as the psychological impact cycle. The specific value setting can be adjusted by the implementer according to the specific implementation situation, and is not limited here.

[0049] After identifying abnormal cycles caused by psychological influences, and considering that these cycles might also mask other abnormalities, normal cycles are not directly used for replacement. Instead, the ECG data for each psychologically influenced cycle is corrected based on the overall deviation between the ECG data from the normal cycle and the ECG data from the cycle with psychological influences. This reduces the interference of psychological factors and improves the accuracy of the data.

[0050] In this embodiment of the invention, the method for obtaining the modified psychological influence cycle includes: First, the amplitude values ​​of the electrocardiogram data in each cardiac cycle are sorted in chronological order to obtain a data sequence. Subsequently, each amplitude value is analyzed and corrected separately.

[0051] Furthermore, for any given psychological impact period, the mean amplitude of ECG data with the same sequence number from all non-abnormal periods preceding that psychological impact period is used as the normal mean for each sequence number. The mean of each amplitude position within the normal period reflects the distribution of normal amplitude at each sequence number. The mean amplitude of ECG data with the same sequence number from both the data sequences of all non-abnormal periods preceding the psychological impact period and the psychological impact period is used as the distribution mean for each sequence number. Combining the normal period and the psychological impact period, the distribution of amplitude at each sequence number is obtained.

[0052] Then, the ratio of the difference between the normal mean and the distribution mean to the mean is used as the correction weight for each index. By analyzing the relative deviation, the correction weight is analyzed for the different degrees of amplitude change caused by psychology under each index, thereby improving the reliability of the correction.

[0053] Furthermore, the product of the amplitude of the electrocardiogram data corresponding to each sequence number in this psychological influence cycle and the correction weight is used as the corrected electrocardiogram data for each sequence number in this psychological influence cycle. As an example, the expression for the corrected electrocardiogram data is: In the formula, Represented as the first The data sequence in the psychological influence cycle Corrected electrocardiogram data for each serial number, Represented as the first The data sequence in the psychological influence cycle The amplitude of the electrocardiogram data for each serial number Represented as the first The data sequence in the psychological influence cycle The normal mean of each serial number. Represented as the first The data sequence in the psychological influence cycle The distribution mean of each sequence number Represented as the first The data sequence in the psychological influence cycle Corrected weights for each sequence number.

[0054] Finally, the psychological impact cycle is updated by correcting the electrocardiogram data. The cardiac cycle is reconstructed from the corrected electrocardiogram data to obtain the corresponding corrected psychological impact cycle.

[0055] S4: Obtain predicted electrocardiogram (ECG) data based on ECG data from the corrected psychological impact period and the non-psychological impact period; determine the current follow-up nursing care adjustment results based on the abnormality evaluation indicators of the current ECG data and the degree of similarity between the current ECG data and the predicted ECG data.

[0056] By analyzing all corrected follow-up ECG results, predictions can be made about the current follow-up ECG data, reflecting the predicted current cardiac electrical activity under historical follow-up conditions. Furthermore, by comparing the predicted ECG data with the actual ECG data, if a significant error is found between the predicted and actual ECGs, and the actual ECG shows fewer abnormalities, it indicates that the patient's postoperative recovery is good and there are no significant abnormal changes. In this case, the subsequent nursing follow-up plan can be adjusted.

[0057] In this embodiment of the invention, the method for obtaining predicted electrocardiogram data includes: The mean amplitude of ECG data with the same sequence number in all data sequences of the corrected psychological influence cycle and the non-psychological influence cycle is used as the predicted mean. The current re-examination situation is predicted by combining the corrected cardiac cycle with all other cardiac cycles. The predicted mean is arranged in order of sequence number to obtain the predicted ECG data, which is the mean of ECG data of all corrected cardiac cycles, and is used as the predicted ECG data for the current re-examination.

[0058] By comparing the current follow-up results with the predicted results, if the difference is small, it indicates that the predicted results are close to the actual results, and subsequent nursing follow-up can be carried out normally. Conversely, if the difference between the predicted results and the actual results is large, the condition may have improved or worsened, requiring adjustment of the nursing follow-up examination schedule. Please refer to [link / reference needed]. Figure 5 This illustration shows a schematic diagram of predicted electrocardiogram (ECG) data and current follow-up ECG data according to an embodiment of the present invention. The predicted data deviates significantly from the actual data. Therefore, in this embodiment, based on the abnormality evaluation indicators of the current follow-up ECG data and the degree of similarity between the current follow-up ECG data and the predicted ECG data, the current follow-up nursing care adjustment result is determined, including: First, the DTW value between the current ECG data and the predicted ECG data is calculated and normalized to obtain the prediction deviation index of the current review. The DTW algorithm can be used to obtain the DTW distance between the ECG data of the predicted ECG and the actual ECG as the DTW value. The larger the DTW value, the higher the dissimilarity between the prediction result and the actual result.

[0059] If the prediction deviation index is greater than or equal to the preset prediction DTW value threshold, it indicates a significant deviation between the prediction result and the actual result, requiring further analysis. The abnormal evaluation index for all cardiac cycles in the currently reviewed electrocardiogram data is obtained; the method for obtaining this index has been described in step S2 and will not be repeated here. In this embodiment of the invention, the preset prediction DTW value threshold is set to 0.5, which can be adjusted by the implementer.

[0060] The mean of all abnormal evaluation indicators in the current follow-up electrocardiogram data is calculated as the abnormality analysis degree of the current follow-up, reflecting the overall probability of abnormality. When the abnormality analysis degree is less than or equal to the preset analysis threshold, it indicates that there are no obvious abnormalities in the patient's actual electrocardiogram data, the required nursing care is not high, and the next nursing follow-up time can be extended. The patient's current follow-up nursing care adjustment result is recorded as delayed. Otherwise, it indicates that there are obvious abnormalities, the postoperative condition may be serious, and the frequency of follow-up nursing care needs to be increased and observation strengthened. Therefore, the follow-up nursing care adjustment result is recorded as advanced.

[0061] If the prediction deviation index is less than the preset prediction threshold, it indicates that there is no significant deviation between the predicted and actual results, and the current follow-up nursing frequency is appropriate. Therefore, the patient's current follow-up nursing adjustment result is recorded as "no adjustment". Personalized follow-up nursing adjustments for coronary intervention patients aim to reduce the burden of medical visits, optimize resource utilization, and improve the quality of life and follow-up outcomes after coronary intervention.

[0062] In summary, this invention initially screens out abnormal cycles by analyzing abnormal changes in the RR interval and ST segment within historical electrocardiograms. Since some abnormal cycles may be identified as abnormal due to psychological factors, further differentiation is made based on the consistency of cycle distribution and degree of abnormality between psychological and physiological abnormalities to identify cycles with psychological influence. The electrocardiogram data of these psychologically influenced cycles can then be corrected by adjusting the data within the psychologically influenced cycles based on the data deviation between non-abnormal cycles and those affected by psychological influence. Finally, the next actual cycle is predicted using all corrected cycles to obtain predicted electrocardiogram data, leading to more reliable prediction results. The predicted electrocardiogram data is then compared with the actual collected data, and abnormality assessments during actual collection are used to comprehensively determine subsequent nursing follow-up adjustments. This invention, by screening for abnormalities in the RR interval and ST segment of historical cardiac cycles and then identifying and correcting abnormalities caused by patient psychological factors based on the degree and distribution of abnormalities, improves the accuracy and reliability of the prediction results and actual analysis, resulting in better outcomes for subsequent nursing follow-up adjustments.

[0063] The present invention also provides a personalized care follow-up system for patients undergoing coronary intervention, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0064] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A personalized nursing follow-up method for patients undergoing coronary intervention, characterized in that, The method includes: Obtain the patient's historical electrocardiogram data and cardiac cycles; For each cardiac cycle, abnormal evaluation indicators are obtained based on the degree of shortening of the RR interval and the degree of slope change of the ST segment of the local cardiac cycle; abnormal cycles are identified from the cardiac cycles based on the abnormal evaluation indicators. Based on the distribution of abnormal cycles and the approximation of corresponding abnormal evaluation indicators, the psychological impact index of each abnormal cycle is obtained; the psychological impact cycle is screened out from the abnormal cycles based on the psychological impact index; the electrocardiogram data of each psychological impact cycle is corrected by the deviation between the psychological impact cycle and the non-abnormal cycle in the electrocardiogram data, and the corrected psychological impact cycle is obtained. Based on the ECG data from the modified psychological impact period and the non-psychological impact period, predictive ECG data is obtained; based on the abnormality evaluation indicators of the current follow-up ECG data and the degree of similarity between the current follow-up ECG data and the predicted ECG data, the current follow-up nursing care adjustment results are determined.

2. The personalized nursing follow-up method for coronary intervention patients according to claim 1, characterized in that, The methods for obtaining the anomaly evaluation indicators include: For any cardiac cycle, the RR interval shortening index of the cardiac cycle is obtained based on the degree of change of the RR interval between all cardiac cycles within a preset local range, as well as the numerical distribution and deviation of the RR interval between the cardiac cycle and adjacent cardiac cycles. Obtain the slope of the ST segment in each cardiac cycle; accumulate the slope differences between every two adjacent cardiac cycles within a preset local range to obtain the ST segment variability of the cardiac cycle; combine the slope of the ST segment and the ST segment variability of the cardiac cycle to obtain the ST segment depression index of the cardiac cycle. By combining the RR interval shortening index and ST segment depression index of this cardiac cycle, abnormal evaluation indexes for this cardiac cycle are obtained.

3. The personalized nursing follow-up method for coronary intervention patients according to claim 2, characterized in that, The method for obtaining the RR interval shortening index includes: The maximum value of the RR intervals during all cardiac cycles within a preset local range is taken as the maximum interval value. The difference between each RR interval and the maximum interval value during cardiac cycles within the preset local range is calculated, and all differences are summed to obtain the degree of change of the cardiac cycle. Calculate the mean of the RR intervals during all cardiac cycles within a preset local range for this cardiac cycle, and use it as the local interval mean of this cardiac cycle; calculate the mean of the RR intervals between this cardiac cycle and adjacent cardiac cycles, and use it as the adjacent interval mean of this cardiac cycle; The shortening proximity of the cardiac cycle is obtained by negatively correlating the difference between the mean of adjacent intervals of the cardiac cycle and the lower limit of the preset range; the difference between the mean of adjacent intervals of the cardiac cycle and the mean of local intervals is used as the proximity deviation of the cardiac cycle. By combining the degree of change, the degree of shortening proximity, and the degree of adjacent deviation of the cardiac cycle, the RR interval shortening index of the cardiac cycle is obtained.

4. The personalized nursing follow-up method for coronary intervention patients according to claim 1, characterized in that, The method for obtaining the abnormal period includes: Cardiac cycles with abnormal evaluation indicators exceeding a preset abnormal threshold are defined as abnormal cycles.

5. The personalized nursing follow-up method for coronary intervention patients according to claim 1, characterized in that, The methods for obtaining the psychological impact indicators include: The continuously distributed abnormal period is taken as an abnormal interval, and the variance of the abnormal evaluation index in each abnormal interval is negatively correlated and mapped to obtain the abnormal approximate index of each abnormal interval. After calculating the difference in interval length between each abnormal interval and each other abnormal interval, the mean of all interval length differences is calculated to obtain the distribution difference index of each abnormal interval. For any abnormal cycle in the abnormal interval, within the abnormal interval where the abnormal cycle is located, the abnormal cycles whose difference in the abnormal evaluation index between them and the abnormal cycle is less than a preset difference threshold are taken as the distribution cycle of the abnormal cycle; the ratio of the number of distribution cycles of the abnormal cycle to the number of all abnormal cycles in the abnormal interval is taken as the distribution quantity index of the abnormal cycle. By combining the distribution quantity index of the abnormal cycle with the abnormal approximation index and distribution difference index of the abnormal interval, the psychological impact index of the abnormal cycle is obtained.

6. The personalized nursing follow-up method for coronary intervention patients according to claim 1, characterized in that, The methods for obtaining the psychological influence cycle include: The abnormal period in which the psychological impact index exceeds the preset psychological threshold is defined as the psychological impact period.

7. The personalized nursing follow-up method for coronary intervention patients according to claim 1, characterized in that, The method for obtaining the modified psychological influence cycle includes: The amplitude values ​​of the electrocardiogram data in each cardiac cycle are sorted in chronological order to obtain a data sequence; For any psychological impact cycle, the mean amplitude of the ECG data with the same sequence number in the data sequence of all non-abnormal cycles before the psychological impact cycle is taken as the normal mean for each sequence number; the mean amplitude of the ECG data with the same sequence number in the data sequence of all non-abnormal cycles before the psychological impact cycle and all psychological impact cycles is taken as the distribution mean for each sequence number. The ratio of the difference between the normal mean and the distribution mean to the mean is used as the correction weight for each index. The product of the amplitude of the electrocardiogram data corresponding to each sequence number in the psychological impact cycle and the correction weight is used as the corrected electrocardiogram data for each sequence number in the psychological impact cycle; the psychological impact cycle is updated by the corrected electrocardiogram data to obtain the corresponding corrected psychological impact cycle.

8. The personalized nursing follow-up method for coronary intervention patients according to claim 7, characterized in that, The method for obtaining the predicted electrocardiogram data includes: The mean amplitude of ECG data with the same sequence number in all data sequences of both the corrected psychological influence period and the non-psychological influence period is used as the predicted mean; the predicted mean is then arranged in sequence to obtain the predicted ECG data.

9. The personalized nursing follow-up method for coronary intervention patients according to claim 1, characterized in that, The methods for obtaining the results of the follow-up nursing care adjustments include: Calculate the DTW value between the current ECG data and the predicted ECG data and perform normalization to obtain the prediction deviation index of the current ECG. If the prediction deviation index is greater than or equal to the preset prediction threshold, obtain the abnormal evaluation index of all cardiac cycles in the current follow-up ECG data; calculate the mean of all abnormal evaluation indexes in the current follow-up ECG data as the abnormality analysis degree of the current follow-up; when the abnormality analysis degree is less than or equal to the preset analysis threshold, record the patient's current follow-up nursing care adjustment result as delayed, otherwise record the follow-up nursing care adjustment result as advanced. If the prediction deviation index is less than the preset prediction threshold, the patient's current follow-up nursing care adjustment result will be recorded as no adjustment.

10. A personalized care follow-up system for coronary intervention patients, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the personalized nursing follow-up method for coronary intervention patients as described in any one of claims 1 to 9.

Images