An online management platform for nursing data of patients with cardiovascular diseases

Abstract

The present invention relates to the field of medical data processing technology, and in particular to an online management platform for nursing data of cardiovascular disease patients. The platform comprises: a heart rate data preprocessing module for acquiring normal data and abnormal data in a current sequence; an abnormal time standard acquisition module for acquiring an abnormal time standard based on a current sequence and a historical sequence; a numerical credibility calculation module for analyzing abnormal data to acquire the numerical credibility of the abnormal data; an interference coefficient acquisition module for classifying abnormal data into an electromagnetic interference class and a class to be analyzed; acquiring the interference coefficient of the abnormal data based on the interquartile range and fitting curve of the data within the abnormal period to which an abnormal data in the class to be analyzed belongs; and an abnormality score acquisition module for acquiring an abnormality score for the abnormal data based on the interference coefficient and performing an initial judgment on the patient's condition. The present invention can eliminate the situation where the heart rate abnormality is interfered with by other factors, thereby improving the accuracy of subsequent analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to an online management platform for nursing data of patients with cardiovascular diseases. Background Art

[0002] With the continuous advancement of medical technology, the treatment and management of cardiovascular disease has evolved from simple drug therapy to comprehensive, personalized integrated care. Every cardiovascular patient's situation is unique, and patients often require continuous health monitoring. Therefore, an online cardiovascular patient care data management platform has emerged. By monitoring key indicators such as heart rate and blood pressure in real time, this platform allows doctors to monitor remotely and promptly identify and address potential risks.

[0003] The online nursing data management platform monitors key indicators of cardiovascular patients and uses AI algorithms to analyze the physical condition of each cardiovascular patient, continuously optimizing nursing recommendations and improving nursing outcomes. Therefore, the accuracy of the key indicator data used to analyze the physical condition of cardiovascular patients within the platform is particularly important. The most commonly used key indicator is heart rate data. To facilitate daily monitoring, patients generally wear dedicated smart bracelets for 24-hour heart rate monitoring. Traditional methods for identifying abnormal heart rate data only use thresholds to distinguish whether the data is abnormal. They do not consider data anomalies caused by other factors, such as the patient's mood swings and exercise, as well as electromagnetic interference caused by items such as mobile phones. This can easily lead to the analysis of the patient's physical condition being inconsistent with reality, increasing the uselessness of patient examinations. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an online management platform for cardiovascular disease patient nursing data, which can identify interference anomalies in the heart rate data that is commonly used and important in the online management platform for cardiovascular disease patient nursing data, reduce the inaccuracy of the heart rate data used, and improve the reliability and accuracy of the platform's analysis results of the patient user's physical condition. The technical solutions adopted are as follows:

[0005] One embodiment of the present invention provides an online management platform for cardiovascular disease patient care data, which includes:

[0006] The heart rate data preprocessing module is used to obtain the patient's heart rate data through the monitoring device and record it as the current sequence; perform an initial judgment on the current sequence based on the patient's disease type to obtain normal data and abnormal data;

[0007] The abnormal time standard acquisition module is used to obtain historical heart rate data to form a historical sequence; record the time period in which normal data appears continuously in the current sequence and the historical sequence as a normal period; and obtain the abnormal time standard based on the normal period in the current sequence and the historical sequence;

[0008] The numerical credibility calculation module is used to segment the abnormal data in the current sequence to obtain abnormal time periods; obtain the numerical credibility of the abnormal data based on the time length of the two adjacent data and the abnormal time period to which the abnormal data belongs;

[0009] The interference coefficient acquisition module is used to classify abnormal data into electromagnetic interference category and to-be-analyzed category according to the numerical credibility; and to obtain the interference coefficient of an abnormal data in the to-be-analyzed category based on the interquartile range of the data in the abnormal period to which the abnormal data belongs and the fitting curve;

[0010] The abnormality score acquisition module is used to obtain the interference coefficient of abnormal data in the electromagnetic interference category; obtain the abnormality score of the abnormal data according to the interference coefficient of the abnormal data; and make an initial judgment on the patient's condition according to the abnormality score.

[0011] Preferably, an initial judgment is made on the current sequence according to the patient's disease type to obtain normal data and abnormal data, including:

[0012] The normal range of the heart rate data of the disease type of the patient corresponding to the current sequence is used to make an initial judgment on the current sequence. The heart rate data within the normal range of the heart rate data is normal data, and the heart rate data outside the normal range of the heart rate data is abnormal data.

[0013] Preferably, the normal period includes:

[0014] The amount of heart rate data in the normal period is greater than or equal to a preset amount.

[0015] Preferably, obtaining the abnormal time standard according to the normal periods in the current sequence and the historical sequence includes:

[0016] The heart rate data of each normal period in the current sequence are combined into a time period sequence, where one element in the time period sequence is the heart rate data within a normal period. Similarly, the time period sequence corresponding to each historical sequence is obtained. The intersection of the time points contained in each element in the time period sequence corresponding to the current sequence and the time points contained in each element in the time period sequence corresponding to each historical sequence are obtained to obtain different intersection time periods. The length of the shortest intersection time period is the abnormal time standard. When obtaining the intersection of the time points contained in each element, the acquisition is performed in units of elements in the sequence.

[0017] Preferably, obtaining the numerical credibility of the abnormal data based on the time length of two adjacent data of the abnormal data and the abnormal period to which the abnormal data belongs includes:

[0018] Calculate the slopes between an abnormal data and the data adjacent to the left and right respectively, and record them as the first slope and the second slope; obtain the inverse of the absolute value of the difference between the first slope and the second slope, and record it as the change characteristic value; obtain the difference between the abnormal time standard and the time length of the abnormal period where the abnormal data is located, and record it as the time difference; take the maximum value of the time difference and the first preset value; the inverse of the sum of the maximum value and the preset value is the time duration characteristic value; perform a weighted sum of the change characteristic value and the time characteristic value to obtain the numerical credibility of the abnormal data.

[0019] Preferably, the abnormal data is divided into electromagnetic interference category and to-be-analyzed category according to the numerical credibility, including:

[0020] Abnormal data with a numerical credibility less than or equal to the credibility threshold is classified as an electromagnetic interference class, and abnormal data with a numerical credibility greater than the credibility threshold is classified as a class to be analyzed.

[0021] Preferably, obtaining the interference coefficient of an abnormal data in the class to be analyzed according to the interquartile range of the data in the abnormal period and the fitting curve includes:

[0022] Arrange all data in the abnormal time period where an abnormal data in the class to be analyzed is located from small to large to obtain a sequential sequence, and the reciprocal of the interquartile range of the sequential sequence is the data change difference characteristic value; use all data in the abnormal time period where the abnormal data is located to perform curve fitting to obtain a fitting curve; obtain the number of abnormal data with derivatives greater than zero and the number of abnormal data with derivatives less than zero on the fitting curve, and record them as the first number and the second number respectively; compare the second number with the sum of the first number and the second number to obtain a ratio, and the difference between the preset value and the ratio is the derivative change characteristic value; calculate the average value of the derivative change characteristic value and the reciprocal of the time length of the abnormal time period where the abnormal data is located, and record it as the data time characteristic value; the average of the data change difference characteristic value and the data time characteristic value is the interference coefficient of the abnormal data.

[0023] Preferably, obtaining the interference coefficient of abnormal data in the electromagnetic interference category includes:

[0024] The interference coefficient of abnormal data in the electromagnetic interference category is the difference between the preset value and the numerical credibility.

[0025] Preferably, obtaining an abnormality score of abnormal data according to an interference coefficient of the abnormal data includes:

[0026] The difference between the preset value and the interference coefficient of the abnormal data and the initial abnormal value score result is obtained, and the product of the difference result and the abnormal score base value is the abnormal situation score of the abnormal data.

[0027] The embodiments of the present invention have at least the following beneficial effects: the present invention performs an initial judgment on the patient's nursing data (heart rate data) obtained on the online management platform, identifies normal data and abnormal data, preliminarily judges the abnormality of the heart rate data, and improves the efficiency of subsequent calculations; further, by combining the time characteristics of normal data in a patient's historical heart rate data and normal data in the current sequence, an abnormal time standard is obtained, and the numerical credibility of the abnormal data is obtained by combining the abnormal time standard and the change of abnormal data in the current sequence, and the abnormal data is divided into an electromagnetic interference class and a class to be analyzed, and a preliminarily judgment is made as to whether the abnormal data is interfered with by factors other than pathological factors, which facilitates subsequent analysis of the interference of other factors; then, the interference coefficient of the abnormal data in the class to be analyzed and the interference coefficient of the abnormal data in the electromagnetic interference class are obtained, and the abnormality score of the abnormal data is calculated based on the interference coefficient, eliminating the interference of factors other than pathological factors on the abnormal heart rate data, improving the accuracy of the abnormal data, reducing the impact of factors other than pathological factors on the accuracy of the patient's physical condition analysis, analyzing the patient's physical condition based on more realistic heart rate data, and obtaining more accurate physical condition analysis results of cardiovascular patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 This is a platform block diagram of an online management platform for cardiovascular disease patient nursing data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] To further illustrate the technical means and effectiveness of the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of an online management platform for cardiovascular disease patient care data proposed in accordance with the present invention. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0031] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0032] The following describes in detail a specific solution of an online management platform for nursing data of cardiovascular disease patients provided by the present invention with reference to the accompanying drawings.

[0033] Example:

[0034] The main application scenario of the present invention is: This application is used to analyze patient heart rate monitoring data in an online management platform for nursing data of cardiovascular patients, and identify data anomalies caused by interference from factors other than pathological factors.

[0035] See also Figure 1 , which shows a platform block diagram of an online management platform for cardiovascular disease patient care data provided by an embodiment of the present invention. The platform includes the following modules:

[0036] The heart rate data preprocessing module is used to obtain the patient's heart rate data through the monitoring equipment and record it as the current sequence; perform an initial judgment on the current sequence according to the patient's disease type to obtain normal data and abnormal data.

[0037] The main purpose of this application is to identify interference anomalies in the heart rate data that is commonly used and important in the online management platform for cardiovascular disease patient care data.

[0038] First, it is necessary to use monitoring equipment to collect the patient's heart rate data and obtain daily heart rate monitoring data for any patient used for analysis in the management platform. The heart rate data is collected by wearing a dedicated heart rate smart bracelet (monitoring device). The bracelet has networking capabilities and can transmit data to the management platform system in real time. The heart rate smart bracelet monitoring principle is photoelectric projection measurement. That is, the LED light source (usually red or green light) inside the bracelet periodically emits light to the wrist skin. When the light penetrates the skin and encounters blood, the hemoglobin in the blood absorbs some of the light, while the unabsorbed light is reflected back. The reflected light is converted into an electrical signal. The strength of the electrical signal is related to the rhythm of the heartbeat. The signal is processed and converted into a heart rate value for display, thereby obtaining the patient's heart rate data. It should be noted that the heart rate data collection frequency in the embodiment of this application is once every minute. The implementer can adjust it according to actual conditions. Each collection cycle is one day. The heart rate data collected during the current collection cycle is organized into a sequence, recorded as the current sequence.

[0039] Furthermore, abnormal data in the current sequence is filtered out, and interference analysis is subsequently performed on the abnormal data to eliminate interference from other factors on the heart rate data. The heart rate data range of normal people is generally 60-100 beats / minute. Since this management platform is mainly aimed at cardiovascular patients, there are many different types of cardiovascular diseases. The management platform can set different normal ranges for heart rate data based on the type of cardiovascular disease to which the patient user belongs. For example, for users with hypertension, the heart rate data should be controlled at 60-80 beats / minute, for users with heart failure, the heart rate data should be controlled at 60-70 beats / minute, for users with chronic persistent atrial fibrillation, the heart rate data should be controlled at 80-100 beats / minute, and for users with stable angina, the heart rate data should be controlled at 55-60 beats / minute. Therefore, different types of diseases have different normal ranges for heart rate data. The normal range of heart rate data corresponding to the disease type of the current sequence is used to make an initial judgment on the current sequence. Heart rate data within the normal range of heart rate data is normal data, and heart rate data outside the normal range of heart rate data is abnormal data.

[0040] For example, for patients with hypertension, the normal heart rate range is 60-80 beats / minute. For patients with hypertension, heart rate data less than 60 beats / minute and greater than 80 beats / minute are marked as abnormal data, and heart rate data between [60, 80] is normal data. Furthermore, to facilitate subsequent analysis, the initial abnormal value of abnormal data is recorded as 1, and the initial abnormal value of normal data is recorded as 0. The initial abnormal value is denoted as α.

[0041] The abnormal time standard acquisition module is used to obtain historical heart rate data to form a historical sequence; record the time period in which normal data appears continuously in the current sequence and the historical sequence as a normal period; and obtain the abnormal time standard based on the normal period in the current sequence and the historical sequence.

[0042] In the previous module, a preliminary judgment was made on the heart rate data collected in the current sequence, and the changing time and pattern of the patient's normal heart rate data were further analyzed to analyze whether the abnormal data was interfered with.

[0043] The patient user heart rate monitoring set up in the management platform is 24-hour continuous monitoring. Unless there are special circumstances, the patient user's heart rate data in adjacent days should have similar changes. Therefore, normal data can be analyzed in combination with data from multiple days.

[0044] Since the patient heart rate monitoring system within the management platform monitors patients continuously 24 hours a day, unless there are unusual circumstances, the patient's heart rate data should show similar fluctuations within consecutive days. Therefore, normal data can be analyzed by combining multiple days of historical data. First, external interference, such as electromagnetic interference and skin sweating and oil production, that can affect sensor readings is generally short-lived and reversible. Therefore, the heart rate data can be analyzed based on the duration of the period. Patients may exercise or experience emotional agitation, which can cause their heart rate data to rise rapidly and then remain elevated for a period of time before falling, depending on the duration of the exercise or the time it takes to calm down. Therefore, normal heart rates in a patient's heart rate data may appear intermittently in time periods of varying lengths. Therefore, the appropriate time period can be determined from multiple days of historical data, along with the changing characteristics of surrounding data, to determine whether abnormal data is subject to interference.

[0045] First, historical heart rate data of the same period as the current sequence is obtained from the data stored in the management platform to form a historical sequence. It should be noted that since one cycle in this application is one day, the historical sequence obtained is also composed of the patient's historical heart rate data in one day. If in a specific implementation, the collection cycle is not one day, for example, the collection cycle is from 0 o'clock to 20 o'clock, then the data in the historical sequence is also the historical heart rate data from 0 o'clock to 20 o'clock in one day. The number of historical sequences obtained needs to be determined based on the actual computing resources of the implementer.

[0046] Furthermore, the time period in which normal data appears continuously in the current sequence and the historical sequence is recorded as a normal period. It should be noted that the number of heart rate data or historical heart rate data that appears continuously in a normal period needs to be greater than or equal to a preset number. Preferably, the preset number in the present invention is 3.

[0047] For example, the sequence of heart rate data for patients with hypertension is {60, 59, 60, 61, 63, 66, 64, 67, 80, 81, 79, 78, 82}, while the data for the normal period is {60, 61, 63, 66, 64, 67, 80}.

[0048] Then, the normal time periods in the current sequence and the historical sequence are comprehensively analyzed, and the abnormal time standard is obtained based on the normal time periods in the current sequence and the historical sequence. Specifically, the heart rate data of each normal time period in the current sequence are combined into a time period sequence, and one element in the time period sequence is the heart rate data in a normal time period. Similarly, the time period sequence corresponding to each historical sequence is obtained; the intersection of the time points contained in each element in the time period sequence corresponding to the current sequence and the time points contained in each element in the time period sequence corresponding to each historical sequence are obtained respectively, and different intersection time periods are obtained; the time length of the shortest intersection time period is the abnormal time standard; when obtaining the intersection of the time points contained in each element, the acquisition is performed in units of elements in the sequence.

[0049] For example, the time period sequence corresponding to the current sequence is {5,6,7,8,9; 12,13,14,15,16,17; 20,21,22,23,24,25,26,27} (5,6,7,8,9, 12,13,14,15,16,17 and 20,21,22,23,24,25,26,27 represent time points in three normal periods respectively), the time period sequence corresponding to the first historical sequence is {6,7,8,9; 12,13,14}, and the time period sequence corresponding to the second historical sequence is {6,7,8,9; 12,13,14}. The time period sequence corresponding to the sequence is {15, 16, 17; 20, 21, 22, 23, 24, 25}. The intersection time periods of the time period sequence corresponding to the current sequence and the time period sequence corresponding to the first historical sequence are 6, 7, 8, 9 and 12, 13, 14; the intersection time periods of the time period sequence corresponding to the current sequence and the time period sequence corresponding to the second historical sequence are 15, 16, 17 and 20, 21, 22, 23, 24, 25. In this example, the abnormal time standard is 3 minutes.

[0050] Due to individual and behavioral differences among patients, it is impossible to use a unified length of time as the standard length of analysis. However, for a single patient, there is a certain historical pattern in the heart rate data within adjacent time periods, that is, there is a certain repeatability in the historical data, so there will be multiple segments of repetitive time data, and these time data have certain behavioral patterns. Therefore, the data that intersects the historical heart rate data and the current heart rate data within the normal time period is representative and represents the time range in which the patient is most likely to maintain a normal heart rate. Therefore, the minimum length of the time period in all the intersection time periods is used as the abnormal time standard for subsequent analysis of abnormal data.

[0051] The numerical credibility calculation module is used to segment the abnormal data in the current sequence to obtain abnormal time periods; and obtain the numerical credibility of the abnormal data based on the time length of the two adjacent data and the abnormal time period to which the abnormal data belongs.

[0052] After obtaining the abnormal time standard, the characteristics of the abnormal data in the current sequence are combined to analyze whether the abnormal data is interfered with. Heart rate data abnormalities caused by pathology and those caused by interference have different durations. Therefore, the abnormal data in the current sequence needs to be segmented to obtain abnormal time periods. The time period when the abnormal data appears continuously is an abnormal time period, and the corresponding time period when the abnormal data appears discontinuously is also an abnormal time period.

[0053] Furthermore, the numerical credibility of the abnormal data is obtained based on the two adjacent data points and the duration of the abnormal period to which the abnormal data belongs. The slopes between the abnormal data point and the adjacent data points on the left and right are calculated, respectively, and recorded as the first slope and the second slope. The reciprocal of the absolute value of the difference between the first slope and the second slope is calculated, and recorded as the change characteristic value. The difference between the abnormal time standard and the duration of the abnormal period to which the abnormal data points belong is obtained, and recorded as the time difference. The time difference and a first preset value are maximized to obtain the maximum value. The reciprocal of the sum of the maximum value and the preset value is the time duration characteristic value. The change characteristic value and the time characteristic value are weighted summed to obtain the numerical credibility of the abnormal data.

[0054] The specific calculation formula is:

[0055] ,

[0056] Among them, β represents the numerical credibility of an abnormal data; Indicates the abnormal time standard; t indicates the length of the abnormal period where the abnormal data is located; 1 indicates the preset value, 0 indicates the first preset value; max indicates the maximum value operation; and Respectively represent the slopes between the abnormal data and the adjacent data on the left and right; and Represent the weight coefficients respectively.

[0057] The abnormal period is the time period composed of adjacent abnormal data after the normal data segment is divided (the time length corresponding to a single abnormal data without adjacent adjacent data is an abnormal period). If the abnormal period is short, it means that the abnormal data may be caused by external conditions such as electromagnetic interference, resulting in abnormal heart rate data. The numerical reliability is low and the time duration characteristic value is high. The larger it is, the more credible the abnormal data is and the lower the possibility of interference. Indicates the absolute value of the difference between the first slope and the second slope. Due to external conditions such as electromagnetic interference, abnormal data may have mutation characteristics. The mutation characteristics will cause the two slopes to be in opposite directions. Therefore, the absolute value of the difference between the slopes is large, and the change characteristic value is large. The larger the value, the more reliable the abnormal data is and the lower the possibility of interference. Since heart rate data is also affected by other factors, heart rate data may not necessarily show mutation characteristics when it is disturbed by external conditions such as electromagnetic interference. Therefore, it can be set , .

[0058] The interference coefficient acquisition module is used to classify abnormal data into electromagnetic interference category and to-be-analyzed category according to numerical credibility; and to obtain the interference coefficient of an abnormal data in the to-be-analyzed category according to the interquartile range of the data in the abnormal period to which the abnormal data belongs and the fitting curve.

[0059] When selecting some historical abnormal heart rates for analysis, since external interference has a certain degree of randomness, statistical analysis can be performed by analyzing the numerical credibility results of the abnormal heart rate data. It can be clearly seen from the histogram that there are obvious differences in some frequencies, that is, a small number of numerical credibility are between 0 and 0.4. Therefore, the credibility threshold is set to 0.4. The credibility threshold is used to divide the abnormal data into two categories based on the numerical credibility of the abnormal data. The abnormal data with numerical credibility less than or equal to the credibility threshold is divided into the electromagnetic interference category, and the abnormal data with numerical credibility greater than the credibility threshold is divided into the category to be analyzed.

[0060] Abnormal data in the class to be analyzed requires further analysis to determine whether it is affected by activities such as exercise. Arrange all data within the abnormal time period of an abnormal data in the class to be analyzed from smallest to largest to obtain a sequential sequence. The reciprocal of the interquartile range of the sequential sequence is the data change difference characteristic value. Curve fitting is performed using all data within the abnormal time period of the abnormal data to obtain a fitted curve. The number of abnormal data with derivatives greater than zero and the number of abnormal data with derivatives less than zero on the fitted curve are obtained, and recorded as the first number and the second number, respectively. The second number is compared with the sum of the first number and the second number to obtain a ratio. The difference between the preset value and the ratio is the derivative change characteristic value. The average of the derivative change characteristic value and the reciprocal of the length of the abnormal time period of the abnormal data is calculated and recorded as the data time characteristic value. The mean of the data change difference characteristic value and the data time characteristic value is the interference coefficient of the abnormal data.

[0061] The specific calculation formula is:

[0062] ,

[0063] Among them, δ represents the interference coefficient of an abnormal data in the class to be analyzed; Indicates the interquartile range of all data within the abnormal period where the abnormal data is located; Performing curve fitting on all data in the abnormal period where the abnormal data is located, and the number of abnormal data whose derivatives on the fitting curve are greater than zero is also the first number; It represents that curve fitting is performed on all data in the abnormal period where the abnormal data is located, and the number of abnormal data whose derivatives on the fitting curve are less than zero is also the second number; T represents the time length of the abnormal period where the abnormal data is located.

[0064] It represents the characteristic value of data change difference. If the interquartile range is large, it means that there is a large difference in the data change during the abnormal period of the abnormal heart rate data. There may be a relatively obvious change in the heart rate data. However, the obvious change in heart rate data may be caused by behaviors such as exercise and emotional changes, or it may be caused by its own pathological reasons.

[0065] Therefore, further analysis is needed, and the case of the derivative of abnormal data after curve fitting is introduced. A derivative greater than 0 indicates that the heart rate data at that location is on an upward trend, and a derivative less than 0 indicates that the heart rate data at that location is on a downward trend. When the heart rate data is abnormal due to exercise, emotional excitement, etc., it tends to recover to normal levels faster, while the heart rate abnormality caused by pathological reasons often takes more time to recover. Indicates the relationship and proportion of the heart rate data during the period of decline in the entire abnormal time period. If there are more heart rate data during the period of decline, it means that most of the data in the abnormal time period is in a downward trend, and the decline takes a long time. A larger value indicates that the data abnormality is more likely to be caused by pathological reasons. It represents the changing characteristic value of the inverse. The larger the value, the greater the possibility of interference.

[0066] T represents the total duration of the abnormal period in which the selected abnormal data is located. When the value of is large, it means that there are relatively more heart rate data in the falling period. However, since the total duration is short, the probability that the abnormal heart rate in the abnormal period is caused by exercise, emotional excitement, etc. is still relatively high.

[0067] Comprehensive analysis shows that if the interquartile range difference is too large, the data in this section may show a process of first rising and then falling. The heart rate data caused by exercise can return to normal in a shorter time, while the heart rate data caused by pathology requires more time to return to normal or is difficult to return to normal. At the same time, the abnormal heart rate data caused by pathology will remain for a longer time.

[0068] In this way, the interference coefficient of each abnormal data in the class to be analyzed is obtained, and the analysis of each data is stored in the data storage module of the management platform. Every time the heart rate data of the patient user is collected, the above process is recalculated based on the new data, and the analysis of the heart rate data in the data storage module is updated at the same time. Subsequent scoring is based on the data at the time of analysis.

[0069] The abnormality score acquisition module is used to obtain the interference coefficient of abnormal data in the electromagnetic interference category; obtain the abnormality score of the abnormal data according to the interference coefficient of the abnormal data; and make an initial judgment on the patient's condition according to the abnormality score.

[0070] For abnormal data in the electromagnetic interference category, its interference coefficient is obtained using its numerical credibility. The interference coefficient of the abnormal data in the electromagnetic interference category is the difference between the preset value and the numerical credibility.

[0071] After obtaining the initial abnormal value of each heart rate data and the interference coefficient of the abnormal data, the abnormality score of the heart rate data obtained by the management platform can be calculated. Doctors can view the heart rate data score of each patient user and obtain the physical condition of the patient user through the management platform at any time. They can also understand the effectiveness of the nursing plan based on the changes in the patient's physical data in the management platform, and can adjust the patient's nursing plan in a targeted manner to improve the nursing effect.

[0072] For normal data, that is, heart rate data with an initial abnormal value of 0, no score calculation is required. The abnormality score is set to 0, and only the abnormal data needs to be scored.

[0073] For abnormal data, set an abnormality score base value. Preferably, in the embodiment of the present invention, the abnormality score base value is set to 10. The implementer can set it according to the actual situation. Subtract the preset value from the interference coefficient of the abnormal data and the initial abnormal value score result to obtain the difference result. The product of the difference result and the abnormality score base value is the abnormality score of the abnormal data. The specific calculation formula is:

[0074] ,

[0075] Here, ε represents the abnormality score of an abnormal data item; 10 represents the baseline abnormality score; δ and α represent the interference coefficient and initial abnormality value of the abnormal data, respectively. A higher normality score indicates a more abnormal heart rate data for the patient. The management platform should focus on the user's physical data and issue a timely heart rate warning to the patient and the doctor.

[0076] After obtaining the abnormality score of each abnormal data, a detailed physical examination was conducted on several patients with different scores. Based on the statistical analysis of the examination results, the distribution of patients' different health status in each score was obtained, and the score classification intervals were obtained, which were 0, (0,7] and (7,10). For normal data, that is, when the abnormality score is 0, it means that the current heart rate data is normal and does not require too much attention; when the abnormality score of the abnormal data is within (0,7], it means that the abnormal heart rate data may be interfered with and requires continuous attention from medical staff. Whether to issue a heart rate warning will be decided based on the subsequent physical condition of the patient. If the subsequent heart rate data continues to be abnormal, a heart rate warning will be issued to remind the patient to undergo further examination; when the abnormality score of the abnormal data is within (7,10], it means that the heart rate data is abnormal and requires special attention, and a heart rate warning will be issued to remind the patient to undergo further examination.

[0077] In addition, when using the built-in AI algorithm in the platform to analyze the patient's physical condition based on heart rate data, if the abnormality score of the abnormal data is within (0,7], and the patient is subsequently observed and no abnormal physical condition is found, then the abnormal data with an abnormality score within (0,7] needs to be processed. The mean replacement method can be used, such as selecting the heart rate data with adjacent scores not in (0,7] and calculating the mean for replacement, so as to improve the accuracy of the data and thus improve the accuracy of subsequent analysis.

[0078] Patients can seek medical treatment on time and adjust their daily behavior habits in a timely manner based on information such as heart rate warnings on the platform. Doctors and other caregivers can modify care plans based on the physical data of each patient on the platform, improve treatment and care measures in a timely manner, and enhance care outcomes.

[0079] In summary, the technical solution provided by the present invention takes into account the situation where heart rate data is interfered with by factors other than pathology during heart rate monitoring, analyzes the data during the monitoring process, eliminates these interferences, and further improves the accuracy of monitoring.

[0080] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0081] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0082] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An online management platform for nursing data of cardiovascular disease patients, characterized by: The platform includes: The heart rate data preprocessing module is used to obtain the patient's heart rate data through the monitoring device and record it as the current sequence; perform an initial judgment on the current sequence based on the patient's disease type to obtain normal data and abnormal data; The abnormal time standard acquisition module is used to obtain historical heart rate data to form a historical sequence; record the time period in which normal data appears continuously in the current sequence and the historical sequence as a normal period; form the heart rate data of each normal period in the current sequence into a time period sequence, where an element in the time period sequence is the heart rate data within a normal period, and similarly obtain the time period sequence corresponding to each historical sequence; obtain the intersection of the time points contained in each element in the time period sequence corresponding to the current sequence and the time points contained in each element in the time period sequence corresponding to each historical sequence, respectively, to obtain different intersection time periods; the time length of the shortest intersection time period is the abnormal time standard; when obtaining the intersection of the time points contained in each element, the acquisition is performed in units of elements in the sequence; The numerical credibility calculation module is used to segment the abnormal data in the current sequence to obtain abnormal time periods; calculate the slope between an abnormal data and the data adjacent to the left and right, respectively, and record it as a first slope and a second slope; obtain the reciprocal of the absolute value of the difference between the first slope and the second slope, and record it as a change characteristic value; obtain the difference between the abnormal time standard and the time length of the abnormal time period in which the abnormal data is located, and record it as a time difference; perform a maximum operation on the time difference and a first preset value to obtain a maximum value; the reciprocal of the sum of the maximum value and the preset value is the time duration characteristic value; perform a weighted sum of the change characteristic value and the time characteristic value to obtain the numerical credibility of the abnormal data; An interference coefficient acquisition module is used to classify abnormal data into electromagnetic interference categories and to-be-analyzed categories based on numerical credibility; arrange all data within an abnormal period where an abnormal data in the to-be-analyzed category is located in ascending order to obtain a sequential sequence, and the reciprocal of the interquartile range of the sequential sequence is the data change difference characteristic value; perform curve fitting using all data within the abnormal period where the abnormal data is located to obtain a fitting curve; obtain the number of abnormal data with derivatives greater than zero and the number of abnormal data with derivatives less than zero on the fitting curve, and record them as a first number and a second number, respectively; compare the second number with the sum of the first number and the second number to obtain a ratio, and the difference between the preset value and the ratio is the derivative change characteristic value; calculate the average value of the derivative change characteristic value and the reciprocal of the time length of the abnormal period where the abnormal data is located, and record it as the data time characteristic value; the average value of the data change difference characteristic value and the data time characteristic value is the interference coefficient of the abnormal data; The abnormality score acquisition module is used to obtain the interference coefficient of abnormal data in the electromagnetic interference category. The interference coefficient of abnormal data in the electromagnetic interference category is the difference between the preset value and the numerical credibility; the abnormality score of the abnormal data is obtained according to the interference coefficient of the abnormal data: , where ε represents the abnormality score of an abnormal data; 10 represents the basic value of the abnormality score; δ and α represent the interference coefficient and initial abnormality value of the abnormal data respectively; the patient's condition is initially judged based on the abnormality score.

2. The online management platform for cardiovascular disease patient care data according to claim 1, characterized in that: The initial judgment of the current sequence based on the patient's disease type to obtain normal data and abnormal data includes: The normal range of the heart rate data of the disease type of the patient corresponding to the current sequence is used to make an initial judgment on the current sequence. The heart rate data within the normal range of the heart rate data is normal data, and the heart rate data outside the normal range of the heart rate data is abnormal data.

3. The online management platform for cardiovascular disease patient care data according to claim 1, characterized in that: The normal period includes: The amount of heart rate data in the normal period is greater than or equal to a preset amount.

4. The online management platform for cardiovascular disease patient care data according to claim 1, characterized in that: The abnormal data is divided into electromagnetic interference type and to-be-analyzed type according to the numerical credibility, including: Abnormal data with a numerical credibility less than or equal to the credibility threshold is classified as an electromagnetic interference class, and abnormal data with a numerical credibility greater than the credibility threshold is classified as a class to be analyzed.

Images