Dynamic pulse condition monitoring and analyzing system for cardiovascular diseases

Abstract

The invention relates to the technical field of medical data monitoring, in particular to a dynamic pulse condition monitoring and analyzing system for cardiovascular diseases. According to the system, the pulse condition big data analysis module is used for analyzing pulse condition information of all disease samples in the current big database, and the pathological association degree of each pulse condition to the cardiovascular disease can be determined based on statistics of the pulse condition information. The pulse condition proportion information in two time periods is independently analyzed, and the cardiovascular monitoring attention degree of each patient can be quantified in combination with the pathological association degree. The overall monitoring attention degree of each patient is more effectively reflected by combining the main artery elasticity decline degree and the small artery emergency expression degree, and medical staff can carry out key monitoring on key patients based on the overall monitoring attention degree. The pulse condition monitoring efficiency is improved, and disease delay of key patients is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of medical data monitoring, and in particular to a dynamic pulse monitoring and analysis system for cardiovascular diseases. Background Art

[0002] Cardiovascular disease is usually a chronic disease. In hospitals, long-term health monitoring can be carried out for elderly patients and other patients in need. During the long-term monitoring process, the monitoring of the patient's pulse is an important monitoring method, and targeted monitoring of different diseases can be carried out through the pulse of the patient. There are often multiple patients in the monitoring scene. In order to facilitate medical staff to understand the patient's pulse, the pulse data can be presented on the visualization panel. However, a large number of patients are concentratedly monitored and the monitoring results are displayed, which will cause medical staff to be unable to pay attention to patients who really have hidden diseases in time, affecting normal medical work. Summary of the invention

[0003] In order to solve the technical problem that the patient sample is large and the medical staff cannot pay attention to the target patient for key monitoring in time during long-term pulse monitoring, the purpose of the present invention is to provide a dynamic pulse monitoring and analysis system for cardiovascular disease, and the technical scheme adopted is as follows: The present invention proposes a dynamic pulse monitoring and analysis system for cardiovascular diseases, the system comprising: The pulse big data analysis module is used to collect statistics on the pulse information of each disease sample in the big database, and obtain the pathological correlation degree of the pulse according to the distribution of each pulse in all disease samples and the correlation of pulses between different disease samples; The pulse real-time monitoring module is used to monitor the pulse data of the target patient in real time during the day and at night and upload it to the pulse big data analysis module; obtain the daytime and nighttime proportions of each pulse of the patient based on the monitored pulse data, and obtain the characteristic pulse development degree of the target patient in the daytime and nighttime periods in combination with the pathological correlation degree of each pulse; obtain the cardiovascular monitoring attention of the target patient based on the characteristic pulse development degree in the two periods; The vascular elasticity monitoring module is used to obtain the elasticity reduction of the target patient's large arteries by monitoring PWV data; The blood pressure monitoring module is used to obtain the small artery emergency performance of the target patient by detecting AASI; The monitoring and early warning module is used to obtain the overall monitoring attention of the target patient based on the target patient's cardiovascular monitoring attention, large artery elasticity reduction and small artery emergency performance, and focus on monitoring the patient based on the overall monitoring attention.

[0004] Further, the pulse big data analysis module includes a pulse distribution statistics unit, a pulse information matching unit and a pulse pathology correlation analysis unit; The pulse condition distribution statistics unit is used to count the proportion of each pulse condition appearing in all disease samples in the large database, so as to obtain the manifestation degree of the cause characteristics of each pulse condition; and count the proportion of each pulse condition appearing in each disease sample, and screen out the characteristic pulse conditions in each disease sample. The pulse condition information matching unit is used to match the characteristic pulse condition information between different disease samples, and obtain the manifestation degree of the pulse condition linkage analysis between the disease samples based on the similarity degree of the types of characteristic pulse conditions and the similarity degree of the distribution of characteristic pulse conditions; count all the manifestation degrees of the pulse condition linkage analysis between the samples to which each characteristic pulse condition belongs, and obtain the cardiovascular disease characteristic correlation degree of each pulse condition. The pulse condition pathological correlation analysis unit is used to obtain the pathological correlation degree of the pulse condition according to the manifestation degree of the cause characteristics of each pulse condition and the cardiovascular disease characteristic correlation degree.

[0005] Further, the method for obtaining the manifestation degree of the pulse condition linkage analysis includes: For two matched disease samples, count the intersection-union ratio of the types of characteristic pulse conditions between the two disease samples as the similarity degree of the types of characteristic pulse conditions; for the characteristic pulse conditions shared between the two disease samples, take the distribution proportion of the shared characteristic pulse conditions in each disease sample as the distribution characteristic, and obtain the initial distribution similarity degree of each shared characteristic pulse condition between the two diseases according to the difference between the distribution characteristics, and take the average value of the initial distribution similarity degrees of all the shared characteristic pulse conditions as the similarity degree of the distribution of characteristic pulse conditions; take the product of the average value between the intersection-union ratio and the initial distribution similarity degree as the manifestation degree of the pulse condition linkage analysis.

[0006] Further, the method for obtaining the cardiovascular disease characteristic correlation degree includes: Match all types of disease samples in the large database with each other. If a certain pulse condition is a characteristic pulse condition in the matching process, count the manifestation degree of the pulse condition linkage analysis obtained in the matching process, and normalize the accumulated value of all the counted manifestation degrees of the pulse condition linkage analysis to obtain the cardiovascular disease characteristic correlation degree of the pulse condition.

[0007] Further, the method for obtaining the development degree of the characteristic pulse condition of the target patient in the two time periods of day and night includes: For the daytime period, multiply the pathological correlation degree of each pulse condition by the corresponding daytime proportion to obtain the development characteristic of each pulse condition in the daytime, and take the average value of the development characteristics of all the pulse conditions of the target patient as the development degree of the characteristic pulse condition in the daytime. For the night time period, obtain the development degree of the characteristic pulse condition at night based on the same method.

[0008] Further, the method for obtaining the cardiovascular monitoring attention degree includes: Taking the characteristic pulse development degree at night as the numerator and the characteristic pulse development degree during the day as the denominator, normalizing the ratio to obtain the characteristic pulse trend coefficient; Based on the characteristic pulse trend coefficient, increasing the characteristic pulse development degree during the day to obtain the cardiovascular monitoring attention level.

[0009] Further, the method for obtaining the large artery elasticity decline degree includes: Obtaining the PWV data sequence of the target patient during the monitoring period; subtracting the previous element from the next element in the PWV data sequence, and taking the ratio of the element difference to the previous element as the PWV increment ratio; taking the proportion of positive PWV increment ratios as the positive increment influence degree; taking the product of the average value of the PWV increment ratios and the positive increment influence degree as the large artery elasticity decline degree.

[0010] Further, the method for obtaining the small artery emergency performance degree includes: Obtaining the AASI value of the target patient, comparing the AASI value with a preset threshold. If it is greater than the preset threshold, normalizing the ratio of the AASI value to the preset threshold to obtain the small artery operation deviation degree of the target patient; if it is not greater than the preset threshold, setting the small artery operation deviation degree of the target patient to 0; taking the time proportion of the AASI value of the target patient being greater than the preset threshold during the preset monitoring period as the small artery function risk degree; increasing the small artery function risk degree based on the small artery operation deviation degree to obtain the small artery emergency performance degree.

[0011] Further, the method for obtaining the overall monitoring attention level includes: Taking the cardiovascular monitoring attention level of the target patient as the weight of the large artery elasticity decline degree, taking the negative correlation mapping result of the cardiovascular monitoring attention level as the weight of the small artery emergency performance degree, and performing weighted summation on the large artery elasticity decline degree and the small artery emergency performance degree to obtain the overall monitoring attention level.

[0012] Further, the key monitoring of patients according to the overall monitoring attention level includes: In the visualization panel, sorting and displaying the monitoring data of patients according to the overall monitoring attention level.

[0013] The present invention has the following beneficial effects: The present invention first uses the pulse condition big data analysis module to analyze the pulse condition information of all disease samples in the current big database. Based on the statistics of the pulse condition information, the pathological correlation degree of each pulse condition with respect to cardiovascular diseases can be determined. Through the pathological correlation degree, the importance of each pulse condition during the monitoring process can be quantified to a certain extent. The present invention further takes into account that the mental states of patients are different during the day and at night, and thus the pulse condition data needs to be analyzed separately. Therefore, by separately analyzing the pulse condition proportion information in two time periods and combining the pathological correlation degree, the cardiovascular monitoring attention of each patient can be quantified. That is, the cardiovascular monitoring attention represents the degree of attention to the pulse conditions presented by the patient. Thus, in combination with the large artery elasticity decline degree and the small artery emergency performance degree, the overall monitoring attention of each patient can be more effectively reflected. Based on the overall monitoring attention, medical staff can conduct key monitoring on key patients, improving the efficiency of pulse condition monitoring and avoiding the delay of the conditions of key patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0015] Figure 1 It is a block diagram of a dynamic pulse condition monitoring and analysis system for cardiovascular diseases provided by an embodiment of the present invention; Figure 2 It is a pulse condition curve graph provided by an embodiment of the present invention; Figure 3 It is a block diagram of a pulse condition big data analysis module structure provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of the pulse condition statistics of a disease sample provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in combination with the accompanying drawings and preferred embodiments, detail the specific implementation manners, structures, features and effects of a dynamic pulse condition monitoring and analysis system for cardiovascular diseases proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0018] The following specifically describes the specific solution of a dynamic pulse condition monitoring and analysis system for cardiovascular diseases provided by the present invention in conjunction with the accompanying drawings.

[0019] Please refer to Figure 1 , which shows a block diagram of a dynamic pulse condition monitoring and analysis system for cardiovascular diseases provided by an embodiment of the present invention. The system includes a pulse condition big data analysis module 101, a pulse condition real-time monitoring module 102, a blood vessel elasticity monitoring module 103, a blood pressure monitoring module 104, and a monitoring and warning module 105.

[0020] The pulse condition big data analysis module 101 is used to statistically analyze the pulse condition information of each disease sample in the big database. The big database contains the pulse condition information of multiple diagnosed patient samples, including information such as pulse condition types and pulse condition frequencies. And through the real-time pulse condition monitoring of patients, the real-time monitored pulse condition data can be stored in the big database to update the big database. In the embodiment of the present invention, the pulse condition data of patients can be monitored based on an intelligent pulse diagnosis bracelet. The bracelet is worn on the radial artery of the patient's wrist. The internal flexible pressure sensor array and infrared positioning technology automatically calibrate the three positions of cun, guan, and chi, and can dynamically obtain the patient's pulse condition data by applying the three-stage pressures of floating, middle, and sinking through a micro stepping motor. After the data collection and upload of the bracelet, data such as pulse condition frequency data, pulse graph parameters, pulse waveform characteristics, and pulse wave propagation parameters can be obtained. Specific examples of some pulse condition information are as follows: (1) Pulse condition frequency data: such as string pulse, thin pulse, slippery pulse, sunken pulse, etc. The frequencies and proportions of these pulse conditions are often used to analyze the pulse condition characteristics of cardiovascular disease patients; (2) Pulse graph parameters: Pulse graph parameters are an important part of traditional Chinese medicine pulse diagnosis, including amplitude (such as h1, h3 / h1), time value (such as w1, t1 / t4), area (such as Ad, As), etc. These parameters can reflect the functional state of the cardiovascular system; (3) Pulse waveform characteristics: including the amplitude, speed, period, shape, etc. of the pulse wave. As Figure 2 shown, which shows a pulse graph curve provided by an embodiment of the present invention, Figure 2 the curve in corresponds to the curve of the string pulse. The string pulse has a relatively high proportion in coronary heart disease patients and usually reflects the characteristics of arteriosclerosis, increased peripheral resistance, and decreased blood vessel elasticity.

[0021] (4) Pulse wave propagation parameters: such as pulse wave velocity (PWV), arterial stiffness index (AASI), etc. These parameters can reflect blood vessel elasticity and hemodynamic changes.

[0022] It should be noted that in the embodiments of the present invention, in order to quantify the importance of patient monitoring, the pulse condition information specifically used is mainly the types of pulse conditions and the distribution information of each pulse condition in the sample.

[0023] Different pulse conditions reflect different physiological and pathological changes. Similarly, different diseases correspond to different pulse condition distributions. Therefore, in order to effectively quantify the monitoring attention of patients, it is first necessary to determine the degree of association of each pulse condition among various diseases. Common cardiovascular diseases such as coronary heart disease, myocarditis, heart failure, etc. Since the pulse condition data stored in the large database are all from patients who have been diagnosed, the pulse condition information of each disease sample in the large database can be statistically analyzed. According to the distribution of each pulse condition in all disease samples and the association of pulse conditions among different disease samples, the pathological association degree of the pulse condition can be obtained. That is, for a certain pulse condition, if it appears more frequently in all disease samples, it indicates that this pulse condition is a representative pulse condition of cardiovascular diseases and its pathological association degree is higher; and after performing association analysis among different disease samples and determining that this pulse condition appears more frequently among different diseases, it indicates that its pathological association degree is higher. Therefore, the pathological association degree of each pulse condition can be determined through the pulse condition big data analysis module 101, which is used to represent the degree of important attention of this pulse condition in the field of cardiovascular diseases.

[0024] Preferably, please refer to Figure 3 , which shows a structural block diagram of a pulse condition big data analysis module provided by an embodiment of the present invention. In an embodiment of the present invention, the pulse condition big data analysis module mainly includes a pulse condition distribution statistics unit 201, a pulse condition information matching unit 202, and a pulse condition pathological association analysis unit 203.

[0025] Among them, the pulse condition distribution statistics unit 201 is used to statistically analyze the proportion of each pulse condition that appears in all disease samples in the large database, and obtain the manifestation degree of the cause characteristics of each pulse condition. That is, the ratio of the number of occurrences of each pulse condition in all samples to the total number of pulse conditions in all samples is used as the manifestation degree of the cause characteristics. The greater the manifestation degree of the cause characteristics, the more representative this pulse condition is in cardiovascular diseases. Further considering that a patient will obtain multiple pulse conditions during the pulse condition monitoring process, and the number of occurrences of some pulse conditions is small and they are not significant pulse conditions under this disease, so the occurrence proportion of each pulse condition in each disease sample is statistically analyzed, and the characteristic pulse conditions are screened out in each disease sample. That is, the characteristic pulse condition is a pulse condition with a relatively high frequency of occurrence under a certain disease. In the embodiments of the present invention, for each disease, the top four pulse conditions with the highest occurrence proportion are selected as the characteristic pulse conditions. In other embodiments, an occurrence proportion threshold can also be set, and the pulse conditions with a proportion greater than the occurrence proportion threshold are used as the characteristic pulse conditions. Please refer to Figure 4 , which shows a schematic diagram of the pulse condition statistics of a disease sample provided by an embodiment of the present invention. Figure 4It is a graph showing the pulse condition distribution results statistically obtained from a large number of samples of patients with coronary heart disease. As shown in the figure, the first four pulse conditions have significantly more distributions compared to other pulse conditions. Therefore, the first four pulse conditions can be used as the characteristic pulse conditions of the coronary heart disease sample, which is convenient for subsequent matching and correlation analysis between different diseases.

[0026] The pulse condition information matching unit 202 is used to match the characteristic pulse condition information between different disease samples. Because there are interactions and influences between different cardiovascular diseases, one disease may be a risk factor or complication of another disease. For example, hypertension is an important risk factor for coronary heart disease. Long-term hypertension will increase the burden on the heart, leading to thickening of the heart wall and arteriosclerosis, and will also increase the burden on the coronary arteries, resulting in damage to the inner wall of the blood vessels and the formation of atherosclerotic plaques, thus increasing the risk of coronary heart disease. Therefore, there will be certain similar manifestations in the pulse conditions of hypertension and coronary heart disease. Based on this characteristic, matching and correlation analysis can be carried out between different diseases in the large database, and the pulse linkage analysis performance degree between disease samples can be obtained based on the similarity degree of the types of characteristic pulse conditions and the similarity degree of the distribution of characteristic pulse conditions between the two matched diseases. That is, the more similar the types of characteristic pulse conditions between the two diseases, and the more similar the distribution ratio, it indicates that the two diseases have obvious correlation characteristics, and the greater the pulse linkage analysis performance degree.

[0027] For a certain pulse condition, if the pulse linkage analysis performance degrees obtained between the disease it belongs to and other diseases are all large, and it belongs to more diseases, it indicates that this pulse condition has a strong correlation with cardiovascular diseases. Therefore, the pulse condition information matching unit 202 further statistically calculates all the pulse linkage analysis performance degrees between the samples to which each characteristic pulse condition belongs, and obtains the cardiovascular disease characteristic correlation degree of each pulse condition.

[0028] The pulse condition pathological correlation analysis unit 203 can obtain the pathological correlation degree of the pulse condition according to the etiological characteristic performance degree and the cardiovascular disease characteristic correlation degree of each pulse condition. In the embodiment of the present invention, because the product of the quantified etiological characteristic performance degree and the cardiovascular disease characteristic correlation degree can be directly used as the pathological correlation degree of each pulse condition, that is, the two characteristics are positively correlated and combined in a multiplicative manner. The greater the etiological characteristic performance degree and the greater the cardiovascular disease characteristic correlation degree, the greater the pathological correlation degree of this pulse condition.

[0029] Furthermore, in an embodiment of the present invention, the method for obtaining the pulse linkage analysis performance degree includes: For the two matched disease samples, the intersection-union ratio of the types of characteristic pulse conditions between the two disease samples is statistically calculated as the similarity degree of the types of characteristic pulse conditions. The larger the intersection-union ratio, the more the same the types of characteristic pulse conditions between the two disease samples, that is, the greater the similarity degree of the types.

[0030] For the characteristic pulse conditions shared between two disease samples, the distribution proportion of the shared characteristic pulse condition in each disease sample is used as the distribution feature, and the initial distribution similarity degree of each shared characteristic pulse condition between the two diseases is obtained based on the differences between the distribution features. Since there is an initial distribution similarity degree for each shared characteristic pulse condition and there are multiple shared characteristic pulse conditions between the two diseases, the average value of the initial distribution similarity degrees of all the shared characteristic pulse conditions is used as the similarity degree of the characteristic pulse condition distribution. In the embodiments of the present invention, the initial distribution similarity degree is the ratio between two distribution features, where the denominator is the larger value, that is, the closer the ratio is to 1, the closer the distribution features of the shared characteristic pulse condition are, and the greater the initial distribution similarity degree is.

[0031] The product of the intersection-over-union ratio and the average value of the initial distribution similarity degree is used as the performance of the pulse condition linkage analysis.

[0032] Furthermore, in the embodiments of the present invention, the method for obtaining the correlation degree of cardiovascular disease characteristics includes: All types of disease samples in the large database are matched with each other. If a certain pulse condition is a characteristic pulse condition in the matching process, the performance of the pulse condition linkage analysis obtained in the matching process is statistically analyzed, and the accumulated value of all the statistically analyzed performances of the pulse condition linkage analysis is normalized to obtain the correlation degree of the cardiovascular disease characteristics of the pulse condition.

[0033] It should be noted that the normalization methods in the embodiments of the present invention all adopt the range normalization method, that is, the maximum value and the minimum value are statistically analyzed in their respective dimensions, and each data is normalized using the maximum and minimum values. The specific method is a technical means well-known to those skilled in the art and will not be elaborated here.

[0034] The pulse condition real-time monitoring module 102 is used to monitor the pulse condition of the target patient in real time. In the embodiments of the present invention, considering the dynamic monitoring process, the monitoring during the day is easily affected by various activities such as exercise, stress, and diet, and these effects will change the pulse condition information, thereby masking the early signals of cardiovascular health. While during the night monitoring, the patient is usually in a resting state and other influencing factors are relatively small, so it helps to reflect the true state of the patient's cardiovascular function. Therefore, the pulse condition real-time monitoring module divides the real-time monitoring period into day and night. It should be noted that when the information collected during the day and night is jointly analyzed in the embodiments of the present invention, the data between the current day during the day and the previous night is selected.

[0035] The real-time pulse condition monitoring module 102 can obtain the daytime and nighttime ratios of each pulse condition of the patient based on the monitored pulse condition data. For a patient, the higher the ratio of a certain pulse condition monitored in a period and the greater the degree of pathological correlation of this pulse condition, it indicates that the development of the pulse condition of the target patient in the current period has more obvious disease characteristics. Therefore, the characteristic pulse condition development degrees of the target patient in the daytime and nighttime periods can be obtained by combining the degree of pathological correlation of each pulse condition. Furthermore, the characteristic pulse condition development degrees of the two periods are jointly analyzed to determine the cardiovascular monitoring attention degree of the target patient on the same day.

[0036] Preferably, in the embodiment of the present invention, obtaining the characteristic pulse condition development degrees of the target patient in the daytime and nighttime periods includes: For the daytime period, multiply the degree of pathological correlation of each pulse condition by the corresponding daytime ratio to obtain the development characteristic of each pulse condition in the daytime, and take the average value of the development characteristics of all pulse conditions of the target patient as the characteristic pulse condition development degree in the daytime.

[0037] For the nighttime period, the characteristic pulse condition development degree in the nighttime is obtained based on the same method.

[0038] Preferably, in the embodiment of the present invention, the method for obtaining the cardiovascular monitoring attention degree includes: Since the night can reflect the relevant manifestations of the patient's cardiovascular disease more than the day, when the patient's pulse condition is in a more obvious abnormal state at night, it indicates that there may be instantaneous pulse condition characteristics corresponding to more accurate, real and undisturbed accidental cardiovascular events (such as atrial fibrillation, myocardial ischemia, etc.).

[0039] Therefore, take the characteristic pulse condition development degree in the nighttime as the numerator and the characteristic pulse condition development degree in the daytime as the denominator, and normalize the ratio to obtain the characteristic pulse condition trend coefficient. That is, the larger the characteristic pulse condition trend coefficient, the more urgent the pulse condition information of the patient in the nighttime, and the more attention is needed for key monitoring. Therefore, the characteristic pulse condition trend coefficient can be used as a weight to adjust the characteristic pulse condition development degree in the daytime, so as to obtain the cardiovascular monitoring attention degree during the day and effectively remind medical staff to pay key attention. Based on the characteristic pulse condition trend coefficient, increase the characteristic pulse condition development degree in the daytime to obtain the cardiovascular monitoring attention degree. It should be noted that because the characteristic pulse condition trend coefficient has been normalized, the characteristic pulse condition trend coefficient can be added to the positive integer 1 as the adjustment coefficient, and the adjustment process can be directly achieved by multiplying the adjustment coefficient by the characteristic pulse condition development degree in the daytime.

[0040] Pulse wave velocity (PWV) can quantify vascular stiffness from the perspective of large artery elastic function and is applicable to the assessment of systemic arteriosclerosis; arterial stiffness index (AASI) can quantify vascular stiffness from the perspective of small artery function, which reflects the function of small arteries and microcirculation and is more sensitive to early vascular regulatory abnormalities. Therefore, based on the data of the two, the hemodynamic state of the patient's vascular system can be evaluated, and then a more accurate overall monitoring attention can be obtained. Therefore, the vascular elasticity monitoring module 103 obtains the degree of large artery elastic decline of the target patient by monitoring PWV data; the blood pressure monitoring module 104 obtains the emergency performance degree of the small arteries of the target patient by detecting AASI; the monitoring and warning module 105 obtains the overall monitoring attention of the target patient according to the cardiovascular monitoring attention, the degree of large artery elastic decline and the emergency performance degree of the small arteries of the target patient, and focuses on monitoring the patient according to the overall monitoring attention.

[0041] Preferably, in the embodiment of the present invention, it is considered that WV is negatively correlated with the elasticity of the arterial wall. The worse the elasticity, the higher the vascular stiffness and the faster the PWV. And the acceleration of PWV continuously increases the afterload of the left ventricle, which can lead to left ventricular hypertrophy in the long term and increase the risk of heart failure. Therefore, in the embodiment of the present invention, a relatively long monitoring time period is set to obtain the PWV data sequence of the target patient during the monitoring time period. In the embodiment of the present invention, the monitoring time period is set to one week, and each element in the PWV data sequence represents one day. That is, for the real-time monitoring process of a patient, the data of the previous week of the patient on the current day are selected to form the PWV data sequence.

[0042] Subtract the previous element from the next element in the PWV data sequence, and use the ratio of the element difference to the previous element as the PWV increment ratio. It should be noted that because it is an element difference, the PWV increment ratio has positive and negative situations. A negative value represents a negative increment, and a positive value represents a positive increment. If there are more positive increments in the PWV increment ratio and the value is larger, it means that the patient has a higher risk of getting sick and the degree of large artery elastic decline is greater. Key monitoring is required. Therefore, the proportion of positive PWV increment ratios is used as the positive increment influence degree, and the product of the average value of the PWV increment ratio and the positive increment influence degree is used as the degree of large artery elastic decline.

[0043] Preferably, in the embodiment of the present invention, the method for obtaining the emergency performance degree of small arteries includes: Similar to the above PWV data, a preset monitoring period is also set to obtain the AASI value of the target patient every day during the monitoring period, and the AASI value is compared with a preset threshold. The larger the AASI value, the more serious the emergency situation of the corresponding cardiovascular event. In the embodiment of the present invention, the threshold is set to 0.7.

[0044] If it is greater than the preset threshold, then normalize the ratio of the AASI value to the preset threshold to obtain the degree of small artery operation deviation of the target patient.

[0045] If it is not greater than the preset threshold, then set the degree of small artery operation deviation of the target patient to 0.

[0046] Take the proportion of the time when the AASI value of the target patient is greater than the preset threshold in the preset monitoring period as the small artery function risk degree. The greater the small artery function risk degree and the degree of small artery operation deviation, it indicates that the small artery condition of the patient is more urgent under the current monitoring period. Increase the small artery function risk degree based on the degree of small artery operation deviation to obtain the small artery emergency performance degree. In the embodiments of the present invention, the method for increasing the small artery function risk degree is the same as the method for increasing the characteristic pulse condition development degree. Since the degree of small artery operation deviation is normalized data, it is multiplied by the small artery function risk degree after adding it to the positive integer 1 to obtain the small artery emergency performance degree.

[0047] Preferably, in the embodiments of the present invention, considering that the pulse wave velocity (PWV) and the arterial stiffness index (AASI) reflect the hemodynamic performance of the patient from the perspectives of the systemic arteries and the small artery microcirculation respectively, and the two are analyzed from the perspectives of the recent continuous performance and the current emergency situation respectively. The two should be analyzed specifically. Therefore, the method for obtaining the overall monitoring attention degree includes: Based on the cardiovascular monitoring attention degree of the target patient, the higher the cardiovascular monitoring attention degree, it indicates that more attention should be paid to the function of the large arteries of the patient, so as to reflect the overall and the recent continuous hemodynamic performance of the patient; on the contrary, it indicates that more attention should be paid to the function of the small arteries, so as to reflect the early vascular abnormality performance presented from the perspective of the small artery microcirculation. Therefore, take the cardiovascular monitoring attention degree of the target patient as the weight of the large artery elasticity decline degree, take the negative correlation mapping result of the cardiovascular monitoring attention degree as the weight of the small artery emergency performance degree, and perform weighted summation on the large artery elasticity decline degree and the small artery emergency performance degree to obtain the overall monitoring attention degree.

[0048] Preferably, in the embodiments of the present invention, in the visualization panel, sort and display the monitoring data of the patient according to the overall monitoring attention degree. Through the sorted display, the monitoring center can pay more attention to the patients with greater cardiovascular disease risks, improving the monitoring efficiency.

[0049] In summary, in the embodiments of the present invention, first, the pulse condition big data analysis module analyzes the pulse condition information of all disease samples in the current big database. Based on the statistics of the pulse condition information, the pathological correlation degree of each pulse condition with respect to cardiovascular diseases can be determined. By separately analyzing the pulse condition proportion information in two time periods and combining the pathological correlation degree, the cardiovascular monitoring attention of each patient can be quantified. Combining the degree of large artery elasticity decline and the degree of small artery emergency manifestation can more effectively reflect the overall monitoring attention of each patient. Based on the overall monitoring attention, medical staff can conduct key monitoring on key patients. The present invention improves the efficiency of pulse condition monitoring and avoids the delay of the conditions of key patients.

[0050] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A dynamic pulse condition monitoring and analysis system for cardiovascular diseases, characterized in that, The system includes: A pulse condition big data analysis module, which is used to count the pulse condition information of each disease sample in the big database, and obtain the pathological correlation degree of the pulse condition according to the distribution of each pulse condition in all disease samples and the correlation of pulse conditions between different disease samples; A pulse condition real-time monitoring module, which is used to monitor the pulse condition data of the target patient during the day and night in real time and upload it to the pulse condition big data analysis module; obtain the day-time proportion and night-time proportion of each pulse condition of the patient according to the monitored pulse condition data, and combine the pathological correlation degree of each pulse condition to obtain the characteristic pulse condition development degree of the target patient in the two time periods of day and night; obtain the cardiovascular monitoring attention degree of the target patient according to the characteristic pulse condition development degree in the two time periods; An arterial elasticity monitoring module, which is used to obtain the degree of decline in the elasticity of the large arteries of the target patient by monitoring the PWV data; The blood pressure monitoring module is used to obtain the emergency performance degree of the small arteries of the target patient by detecting the AASI; A monitoring and warning module, which is used to obtain the overall monitoring attention degree of the target patient according to the cardiovascular monitoring attention degree, the degree of decline in the elasticity of the large arteries and the emergency performance degree of the small arteries of the target patient, and conduct key monitoring on the patient according to the overall monitoring attention degree.

2. The dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 1, wherein The pulse condition big data analysis module includes a pulse condition distribution statistics unit, a pulse condition information matching unit and a pulse condition pathological correlation analysis unit; The pulse condition distribution statistics unit is used to count the proportion of each pulse condition appearing in all disease samples in the big database, and obtain the etiological characteristic manifestation degree of each pulse condition; And count the proportion of each pulse condition appearing in each disease sample, and screen out the characteristic pulse conditions in each disease sample; The pulse condition information matching unit is used to match the characteristic pulse condition information between different disease samples, and obtain the pulse condition linkage analysis manifestation degree between disease samples based on the similarity of the types of characteristic pulse conditions and the similarity of the distribution of characteristic pulse conditions; count all the pulse condition linkage analysis manifestation degrees between the samples to which each characteristic pulse condition belongs, and obtain the cardiovascular disease characteristic correlation degree of each pulse condition; The pulse condition pathological correlation analysis unit is used to obtain the pathological correlation degree of the pulse condition according to the etiological characteristic manifestation degree and the cardiovascular disease characteristic correlation degree of each pulse condition.

3. The dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 2, wherein The method for obtaining the pulse condition linkage analysis manifestation degree includes: For two matched disease samples, count the intersection ratio of the types of characteristic pulse conditions between the two disease samples as the similarity of the types of characteristic pulse conditions; for the characteristic pulse conditions shared between the two disease samples, take the distribution proportion of the shared characteristic pulse conditions in each disease sample as the distribution characteristic, and obtain the initial distribution similarity of each shared characteristic pulse condition between the two diseases according to the difference between the distribution characteristics, and take the average value of the initial distribution similarities of all shared characteristic pulse conditions as the similarity of the distribution of characteristic pulse conditions; take the product of the average value between the intersection ratio and the initial distribution similarity as the pulse condition linkage analysis manifestation degree.

4. A dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 2, characterized in that, The method for obtaining the cardiovascular disease characteristic correlation degree includes: All types of disease samples in the large database are matched with each other. If a certain pulse condition is a characteristic pulse condition during the matching process, the performance degree of the pulse condition linkage analysis obtained during the matching process is statistically analyzed, and the accumulated value of all the performance degrees of the pulse condition linkage analysis is normalized to obtain the cardiovascular disease characteristic correlation degree of the pulse condition.

5. A dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 1, characterized in that The obtaining of the characteristic pulse condition development degrees of the target patient in two time periods, daytime and night, includes: For the daytime period, multiply the pathological correlation degree of each pulse condition by the corresponding daytime proportion to obtain the development characteristic of each pulse condition during the day, and take the average value of the development characteristics of all the pulse conditions of the target patient as the characteristic pulse condition development degree during the day; For the night period, obtain the characteristic pulse condition development degree at night based on the same method.

6. The dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 1, characterized in that, The method for obtaining the cardiovascular monitoring attention degree includes: Take the characteristic pulse condition development degree at night as the numerator and the characteristic pulse condition development degree during the day as the denominator, and normalize the ratio to obtain the characteristic pulse condition trend coefficient; Based on the characteristic pulse condition trend coefficient, increase the characteristic pulse condition development degree during the day to obtain the cardiovascular monitoring attention degree.

7. A dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 1, characterized in that, The method for obtaining the large artery elasticity decrease degree includes: Obtain the PWV data sequence of the target patient during the monitoring period; subtract the previous element from the next element in the PWV data sequence, and take the ratio of the element difference to the previous element as the PWV increment ratio; take the proportion of the positive PWV increment ratio as the positive increment influence degree; take the product of the average value of the PWV increment ratio and the positive increment influence degree as the large artery elasticity decrease degree.

8. The dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 1, characterized in that The method for obtaining the small artery emergency performance degree includes: Obtain the AASI value of the target patient, compare the AASI value with a preset threshold. If it is greater than the preset threshold, normalize the ratio of the AASI value to the preset threshold to obtain the small artery operation detachment degree of the target patient; if it is not greater than the preset threshold, set the small artery operation detachment degree of the target patient to 0; take the time proportion of the AASI value of the target patient being greater than the preset threshold during the preset monitoring period as the small artery function risk degree; based on the small artery operation detachment degree, increase the small artery function risk degree to obtain the small artery emergency performance degree.

9. The dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 1, characterized in that The method for obtaining the overall monitoring attention degree includes: Take the cardiovascular monitoring attention degree of the target patient as the weight of the large artery elasticity decrease degree, take the negative correlation mapping result of the cardiovascular monitoring attention degree as the weight of the small artery emergency performance degree, and perform weighted summation on the large artery elasticity decrease degree and the small artery emergency performance degree to obtain the overall monitoring attention degree.

10. The dynamic pulse condition monitoring and analysis system for cardiovascular diseases according to claim 1, characterized in that, The key monitoring of the patient according to the overall monitoring attention degree includes: In the visualization panel, sort and display the monitoring data of the patient according to the overall monitoring attention degree.

Images