An intelligent monitoring method based on electrocardiogram

Abstract

The present invention discloses an intelligent monitoring method based on electrocardiogram, which relates to the technical field of medical monitoring. The detection steps are as follows: S1. The patient wears a patch-type electrocardiogram monitoring module to obtain electrocardiogram data at different times and upload the data to the analysis module; S2. The analysis module analyzes the waveform morphology of the electrocardiogram data at different times, screens out the electrocardiogram waveforms in abnormal time periods, integrates the abnormal electrocardiogram waveforms to construct an electrocardiogram library, and based on the Euclidean distance calculation formula, screens out the electrocardiogram waveforms of heart disease types similar to the current patient's waveform, and preliminarily screens out heart diseases similar to the patient. The present invention screens out the electrocardiogram waveforms of heart disease types similar to the current patient's waveform based on the Euclidean distance calculation formula. This method realizes a certain degree of intelligent preliminary disease screening. Through quantitative distance calculation, the diagnosis range is objectively and efficiently narrowed, which helps to improve the diagnosis efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of medical monitoring, and specifically relates to an intelligent monitoring method based on electrocardiogram. Background Art

[0002] Electrocardiogram is a common and important means for detecting heart health, and is widely used in clinical diagnosis and daily health monitoring. By recording the electrical change curve generated by the heart in each cardiac cycle, it can reflect the depolarization and repolarization processes of the atria and ventricles, providing a key basis for the diagnosis of various heart diseases. Most of the existing intelligent electrocardiogram monitoring methods focus on the simple extraction and recognition of electrocardiogram waveform features. Through algorithms, key waveforms such as QRS complexes, P waves, and T waves are automatically detected, and basic parameters such as heart rate and intervals are calculated, and then compared with the preset normal range to determine whether there is an abnormality. However, this method often only analyzes individual waveforms or parameters in isolation. Although electrocardiograms can be recorded for a long time, subsequent interpretation of a large amount of long-term data mainly relies on professional electrocardiogram doctors for manual analysis to judge the patient's condition. This not only involves a huge workload, is time-consuming and laborious, but also due to subjective differences and visual fatigue factors in manual interpretation, the diagnostic accuracy may vary. Especially when faced with a large amount of complex electrocardiogram data, it is difficult to ensure that all subtle abnormalities can be comprehensively and timely detected, resulting in inaccurate judgments and delaying the diagnosis of patients. In response to this, we propose an intelligent monitoring method based on electrocardiogram. Summary of the Invention

[0003] To solve the above technical problems, an intelligent monitoring method based on electrocardiogram is provided, and this technical solution solves the problems of inaccurate judgment and delayed patient diagnosis mentioned above.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is: an intelligent monitoring method based on electrocardiogram, and the detection steps are as follows:

[0005] S1. The patient wears a patch-type electrocardiogram monitoring module to obtain electrocardiogram data at different times and upload the data to the analysis module;

[0006] S2. The analysis module analyzes the waveform morphologies of electrocardiogram data at different times, screens out the electrocardiogram waveforms in abnormal time periods, integrates the abnormal electrocardiogram waveforms to construct an electrocardiogram library, and based on the Euclidean distance calculation formula, screens out the electrocardiogram waveforms of heart disease types similar to the current patient's waveform, and preliminarily screens out heart diseases similar to the patient;

[0007] S3. Convert the electrocardiogram library into time series data. Based on the time series analysis vector, combine the electrocardiogram time series data into a vector form in sequence. Convert the preliminarily screened electrocardiogram data of similar heart diseases into heart disease vectors. Calculate the similarity between the disease vector and the electrocardiogram vector collected from the patient based on the cosine similarity, and specifically determine the type of heart disease from the similar heart diseases.

[0008] S4. Based on the obtained type results, give a diagnosis suggestion based on big data, a doctor's assistant diagnosis suggestion, and give a diagnosis plan.

[0009] Preferably, in step S1, the electrocardiogram acquisition period is 6 hours. After every 1 hour interval, collect the electrocardiogram of the patient once to obtain the electrocardiogram data of the patient. After uploading the data, perform preprocessing, which includes filtering and denoising, data standardization, and feature extraction. The extracted feature is the waveform feature of the electrocardiogram.

[0010] Preferably, in step S2, screen the abnormal electrocardiogram waveform by judging the overall waveform difference. Measure the overall difference degree by calculating the mean square error MSE between the actual waveform Es(t) and the normal reference waveform Ez(t) within the unit time (t1, t2). The calculation formula is:

[0011] ;

[0012] where MSE(t1, t2) is the calculated output value. By setting the normal waveform threshold, when the calculated output value is greater than the set threshold, it is judged that the electrocardiogram waveform within the time period (t1, t2) is abnormal, and the collected electrocardiogram data is screened.

[0013] Preferably, the Euclidean calculation formula in step S2 is:

[0014] ;

[0015] where D j is the Euclidean distance between the electrocardiogram waveform of the current patient and the electrocardiogram waveforms of j disease types. n is the total number of time points of the electrocardiogram waveform, that is, the length of the time series. p i is the amplitude of the electrocardiogram of the current patient at the i-th time point, and s ji is the amplitude of the electrocardiogram waveform of the j-th disease type at the i-th time point. i represents the index of the time point. The electrocardiogram waveform is a series of time series data. In the formula, calculate the square of the amplitude difference at each time point, sum the results of all time points, and finally take the square root to obtain the Euclidean distance. The obtained value D j represents the distance between the two. The smaller the distance, the more similar the waveforms are, and initially judge the diseases similar to the current electrocardiogram waveform of the patient.

[0016] Preferably, in step S3, the electrocardiogram is converted into time series data by setting the total duration of the electrocardiogram to A and the sampling frequency to b, then the total number of sampling points is: C=Ab, and E(t) represents the amplitude corresponding to the electrocardiogram signal collected at time t;

[0017] Discretize the continuous time interval (0, A) according to the sampling frequency b to obtain discrete time points t n (n=0, 1, 2, ..., n-1), where t n =n / b, corresponding to the time corresponding to each sampling point, the corresponding time series data is expressed as X=(x0, x1, x2, ... x n-1 ), where x n is a discrete time point t n The ECG amplitude collected at .

[0018] Preferably, in step S3, the time range and corresponding sampling interval of the entire ECG time series data acquired are pre-defined, and the amplitude corresponding to the first time point becomes the first element of the vector, the amplitude corresponding to the second time point becomes the second element of the vector, and so on, until all the amplitude data corresponding to all time points in the entire time range are included to form a complete vector.

[0019] Preferably, in step S3, for each known heart disease, the disease-related ECG feature information is sequentially combined into a vector form, namely a disease vector. Each disease vector carries the key features of the corresponding disease in the ECG manifestation. The cosine similarity calculation method is used to measure the cosine value of the angle between two vectors to judge their similarity. The value range is between -1 and 1. When calculating the cosine similarity between the disease vector and the ECG vector collected by the patient, it is judged to be similar to the current disease vector.

[0020] Preferably, the cosine similarity calculation formula is:

[0021] ;

[0022] Where G represents the disease vector of the heart, H represents the ECG vector currently collected by the patient, is the angle between the two vectors. A specific similarity value is obtained by calculation. When this value is closer to 1, it means that the angle between the disease vector and the patient's ECG vector in the feature space is smaller, indicating that the similarity between them is higher, indicating that the ECG characteristics of the patient are more consistent with the typical ECG characteristics of the corresponding disease; conversely, the closer the value is to -1 or 0, the lower the similarity between the two, and the less consistent the disease is with the patient's actual situation, thereby specifically determining the type of heart disease the patient is currently suffering from.

[0023] Preferably, in step S4, through big data analysis, it is learned that in the cases of diseases, for patients of different ages, genders, and basic health conditions, the development trends of the diseases, the complications, and the effects under different treatment methods. Based on the obtained network information, suggestions are given to the current patient.

[0024] Preferably, in step S4, the doctor refers to the given suggestions and combines the patient's clinical symptoms, considering factors such as the patient's past medical history, family medical history, and the current medications taken. Based on individualized considerations, on the basis of the big data suggestions, a diagnostic suggestion that suits the patient's own situation is customized for the patient.

[0025] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0026] The present invention screens electrocardiogram waveforms of heart disease types similar to the current patient's waveform based on the Euclidean distance calculation formula. This method realizes a certain degree of intelligent preliminary disease screening. It no longer simply relies on artificial experience to judge possible disease types, but objectively and efficiently narrows the diagnostic scope through quantitative distance calculation, provides a reasonable reference direction for more accurately determining the disease type subsequently, reduces the blindness of investigation, and helps improve the diagnostic efficiency.

[0027] The present invention calculates the similarity between the disease vector and the electrocardiac vector collected from the patient using cosine similarity, and also converts the electrocardiac data of the preliminarily screened similar heart diseases into heart disease vectors, so that the electrocardiac characteristics of different diseases can be quantitatively compared for similarity in the same vector space, making the distinction and judgment of diseases more scientific and accurate, and helping to more precisely identify the disease type that most conforms to the actual situation of the patient from similar diseases.

[0028] The present invention gives diagnostic suggestions based on big data, making full use of the valuable experience and general laws contained in the vast amount of medical data. Big data can integrate information on the disease development trends, treatment effects, and complications of many similar cases, so as to provide comprehensive and forward-looking diagnostic suggestions for the current patient. The doctor combines the patient's specific clinical symptoms, past medical history, and individual physical signs and other personalized factors, can fully consider the particularity of the patient, make the diagnostic suggestions more in line with the actual situation of the patient, avoid the omissions that may occur when mechanically applying general suggestions, and maximize the satisfaction of the individual medical needs of the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a flowchart of the detection steps of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0030] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and other obvious variations can be conceived by those skilled in the art.

[0031] Referring to Figure 1 shown, an intelligent monitoring method based on electrocardiogram, the detection steps are as follows:

[0032] S1. The patient wears a patch-type electrocardiogram monitoring module to obtain electrocardiogram data at different times and upload the data to the analysis module;

[0033] S2. The analysis module analyzes the waveform morphology of the electrocardiogram data at different times, screens out the electrocardiogram waveforms in abnormal time periods, integrates the abnormal electrocardiogram waveforms to construct an electrocardiogram library, and based on the Euclidean distance calculation formula, screens out the electrocardiogram waveforms of heart disease types similar to the current patient's waveform, and preliminarily screens out the heart diseases similar to the patient;

[0034] S3. Convert the electrocardiogram library into time series data, combine the electrocardiogram time series data into a vector form in sequence based on the time series analysis vector, convert the preliminarily screened similar heart disease electrocardiogram data into a heart disease vector, and calculate the similarity between the disease vector and the electrocardiogram vector collected from the patient based on the cosine similarity, and specifically determine the types of heart diseases from the similar heart diseases;

[0035] S4. Based on the obtained type results, give a diagnosis suggestion based on big data, and the doctor assists in the diagnosis suggestion to give a diagnosis plan.

[0036] By wearing a patch-type electrocardiogram monitoring module, the patient in this application can achieve long-term and continuous monitoring of cardiac electrical activities in the daily activity state. Different from the traditional static electrocardiogram examination that can only obtain data in a short time, this method can capture electrocardiogram data in different life scenarios and different physical states, greatly increasing the chance of discovering abnormal electrocardiogram conditions. Whether it is a transient arrhythmia or a change in cardiac electrical activity induced by specific activities, it is more likely to be recorded, providing a rich data basis for subsequent comprehensive and accurate diagnosis;

[0037] Using the Euclidean distance calculation formula to screen out the electrocardiogram waveforms of heart disease types similar to the current patient's waveform realizes preliminary intelligent disease screening. It is based on objective mathematical calculations and quickly narrows the possible disease range. Compared with the traditional method of relying on doctors to manually check various diseases one by one, it greatly improves the work efficiency in the early stage of diagnosis, enables subsequent analysis to focus more on the disease types with stronger relevance, and reduces unnecessary workload and time costs;

[0038] Based on the time series analysis vector, the electrocardiogram (ECG) time series data is combined into a vector form, and the ECG data of similar heart diseases initially screened is also converted into heart disease vectors. This process quantifies and integrates the ECG features. In the vector space, the similarity degree between different ECG data can be measured through precise mathematical calculations, more scientifically and objectively comparing the differences between the patient's ECG vector and different disease vectors, thereby improving the ability to accurately determine the specific disease type from similar heart diseases and avoiding the errors that may occur by relying solely on subjective visual judgment of waveform similarity.

[0039] In step S1, the ECG acquisition period is 6 hours. After every 1 hour, the patient's ECG is collected once to obtain the patient's ECG data. After uploading the data, preprocessing is performed, which includes filtering and denoising, data standardization, and feature extraction. The extracted features are the waveform features of the ECG.

[0040] The preprocessing step in this application is prior art and will not be elaborated here. Collecting at fixed time intervals helps discover the potential laws of cardiac electrical activity changing over time. For example, whether there are always similar subtle changes in the ECG waveform within a certain time period, or whether a certain abnormal waveform is more likely to appear after a specific time cycle. This regular data acquisition method is convenient for medical staff to analyze the rhythmic and trend characteristics of cardiac activity in a short time, which is of great significance for diagnosing some heart diseases or occult diseases related to biological clocks and daily activity rhythms, and can better understand the dynamic change pattern of cardiac function.

[0041] In step S2, abnormal ECG waveforms are screened by judging the overall waveform difference. The mean square error (MSE) between the actual waveform Es(t) and the normal reference waveform Ez(t) within the unit time (t1, t2) is calculated to measure the overall difference degree. The calculation formula is:

[0042] ;

[0043] where MSE(t1, t2) is the calculated output value. By setting a normal waveform threshold, when the calculated output value is greater than the set threshold, it is judged that the ECG waveform within the time period (t1, t2) is abnormal, and the collected ECG data is screened.

[0044] This application measures the degree of difference by calculating the mean square error (MSE) between the actual waveform Es(t) and the normal reference waveform Ez(t) per unit time, transforming the process of relying on manual subjective visual judgment of whether the electrocardiogram waveform is abnormal into a quantitative evaluation method based on mathematical formulas. This quantitative method avoids the differences caused by inconsistent personal experiences, observation angles, and subjective judgment criteria of different doctors, making the judgment of whether the electrocardiogram waveform is abnormal more objective and unified. No matter which medical staff conducts the analysis, as long as the same normal waveform threshold is set, relatively consistent judgment results can be obtained, thereby improving the scientific nature and accuracy of the diagnosis process and reducing misdiagnosis or missed diagnosis cases caused by subjective factors;

[0045] Among them, each wave form, amplitude, and duration of the normal waveform Ez(t) have standard ranges. By referring to the generally recognized electrocardiogram standards in medicine, including the guidelines of the American Heart Association (AHA) and the European Society of Cardiology (ESC), the characteristics of the normal waveform are defined; the acquisition method of the normal waveform Ez(t) is obtained through statistical analysis of electrocardiogram data of a large number of healthy people and has a tolerance range.

[0046] The Euclidean calculation formula in step S2 is:

[0047] ;

[0048] Where D j is the Euclidean distance between the electrocardiogram waveform of the current patient and the electrocardiogram waveforms of j disease types. n is the total number of time points of the electrocardiogram waveform, that is, the length of the time series. p i is the amplitude of the electrocardiogram of the current patient at the i-th time point, and s ji is the amplitude of the electrocardiogram waveform of the j-th disease type at the i-th time point. i represents the index of the time point. The electrocardiogram waveform is a series of time series data. In the formula, the square of the amplitude difference is calculated at each time point, and the results of all time points are summed, and finally the square root is taken to obtain the Euclidean distance. The obtained value D j represents the distance between the two. The smaller the distance, the more similar the waveforms are, and the diseases with which the current electrocardiogram waveform of the patient is similar can be initially judged.

[0049] The Euclidean distance calculation formula of the present application provides a clear and precise quantitative means for measuring the similarity between the current patient's ECG waveform and the ECG waveforms of different disease types. By converting the difference in waveform amplitude at each time point into a specific numerical value, the traditional fuzzy judgment method based on experience and subjective visual comparison is abandoned, making the similarity assessment objective and measurable. Medical personnel can intuitively judge which type of disease has an ECG waveform closer to the patient based on the specific distance value, providing accurate and convincing data support for subsequent diagnostic analysis, helping to reduce the risk of misdiagnosis due to subjective judgment differences and improve the scientificity and accuracy of diagnosis.

[0050] In step S3, the electrocardiogram is converted into time series data by setting the total duration of the electrocardiogram to A and the sampling frequency to b. Then the total number of sampling points is: C=Ab, and E(t) is used to represent the amplitude corresponding to the electrocardiogram signal collected at time t;

[0051] Discretize the continuous time interval (0, A) according to the sampling frequency b to obtain discrete time points t n (n=0, 1, 2, ..., n-1), where t n =n / b, corresponding to the time corresponding to each sampling point, the corresponding time series data is expressed as X=(x0, x1, x2, ... x n-1 ), where x n is a discrete time point t n The ECG amplitude collected at .

[0052] The present application organizes electrocardiogram data in the form of a time series, which helps to improve the efficiency and accuracy of subsequent calculations and processing. When a computer processes such structured data, it can operate on the data at each time point in sequence, thus avoiding the analysis difficulties and errors that may occur when processing complex waveforms.

[0053] In step S3, the time range and corresponding sampling interval of the entire ECG time series data are pre-defined for the acquired ECG time series data. In order, the amplitude corresponding to the first time point becomes the first element of the vector, and the amplitude corresponding to the second time point becomes the second element of the vector, and so on, until all the amplitude data corresponding to all time points in the entire time range are included to form a complete vector.

[0054] This application integrates the electrocardiogram amplitude data scattered at different time points into a vector, achieving a high degree of data integration. It simplifies the originally complex and chronologically arranged large amount of discrete data into an ordered overall structure, enabling a clear view of the similarities and differences in electrocardiogram amplitudes at different time points, and then judging the similarity of the overall waveform. Moreover, when performing similarity measurement and disease type judgment based on the cosine similarity method subsequently, the vector-form data can seamlessly connect to the corresponding calculation logic, more accurately determining the proximity between the patient's electrocardiogram vector and various disease vectors, and improving the accuracy and efficiency of disease diagnosis.

[0055] In step S3, for various known heart diseases, the electrocardiogram feature information related to the diseases is combined into a vector form in sequence, which is the disease vector. Each disease vector carries the key features of the corresponding disease in the electrocardiogram manifestation. The cosine similarity calculation method is used to measure the cosine value of the angle between two vectors to judge their similarity degree. Its value range is between -1 and 1. When calculating the cosine similarity between the disease vector and the electrocardiogram vector collected from the patient, it is judged to be similar to the current disease vector.

[0056] The numerical range obtained by this application through cosine similarity calculation is between -1 and 1, which can quantitatively measure the similarity degree between the disease vector and the patient's electrocardiogram vector. Compared with the traditional method of relying on doctors' visual observation and experience to judge the similarity of electrocardiogram features, this quantitative result is more objective and accurate, greatly reducing the diagnostic deviation caused by subjective factors, enabling medical staff to measure the degree of fit between the patient's electrocardiogram performance and various known heart diseases based on exact numerical values, and providing a reliable basis for subsequent accurate diagnosis.

[0057] The cosine similarity calculation formula is:

[0058] ;

[0059] where G represents the disease vector of the heart, and H represents the electrocardiogram vector currently collected from the patient. is the angle between the two vectors. By calculating, a specific similarity value is obtained. When this value is closer to 1, it indicates that the angle between the disease vector and the patient's electrocardiogram vector in the feature space is smaller, indicating a higher similarity between them, and indicating that the electrocardiogram features of the patient are more consistent with the typical electrocardiogram features of the corresponding disease; on the contrary, the closer the value is to -1 or 0, the lower the similarity between the two, and the smaller the degree of fit between the disease and the actual situation of the patient, thus specifically determining the type of heart disease currently suffered by the patient.

[0060] In this application, the cosine similarity calculation formula is based on rigorous mathematical principles. It represents the similarity between the disease vector and the patient's electrocardiogram vector with a specific numerical value, and its value range is clearly limited between -1 and 1. This quantitative method completely abandons the ambiguity of relying on subjective visual observation and empirical judgment. No matter which medical staff conducts the analysis, as long as they rely on the same data and this calculation formula, they can obtain the same similarity value, providing an objective and unified measurement standard for judging the fit between the patient's electrocardiogram and electrocardiograms of various diseases, greatly improving the scientific nature and accuracy of the diagnosis process, and effectively avoiding misdiagnosis caused by differences in human judgment.

[0061] In step S4, through big data analysis, it is learned that in the cases of diseases, for patients of different ages, genders, and basic health conditions, the development trends, complication situations, and effects under different treatment methods of the diseases. Based on the obtained network information, suggestions are given for the current patient. In step S4, the doctor refers to the suggestions and combines the patient's clinical symptoms, considering factors such as the patient's past medical history, family medical history, and current medications. Based on individualized considerations, on the basis of the big data suggestions, a diagnosis suggestion tailored to the patient's own situation is customized for the patient.

[0062] Through big data analysis, this application can comprehensively consider the impacts of multiple dimensional factors such as different ages, genders, and basic health conditions on diseases. Due to differences in physical functions and physiological characteristics among different groups of patients, the development trajectories of diseases in them are often different. Some heart diseases may progress relatively slowly but have more complications in the elderly, while in the young, they may progress rapidly but respond more positively to treatment. Big data covers a large amount of case information of different types of patients, can comprehensively present these diverse manifestations, enabling medical staff to clearly grasp the general development laws of diseases in different populations from a macroscopic perspective, and providing a comprehensive reference basis for the prognosis of the current patient's condition.

[0063] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. An intelligent monitoring method based on electrocardiogram, characterized in that: The detection steps are: S1. The patient wears a patch-type ECG monitoring module to obtain ECG data at different times and upload the data to the analysis module; S2, the analysis module analyzes the waveform morphology of the ECG data of different periods, screens out the ECG waveforms of abnormal time periods, integrates the abnormal ECG waveforms to build an ECG library, and screens out the ECG waveforms of heart disease types similar to the current patient's waveform based on the Euclidean distance calculation formula, and preliminarily screens out heart diseases similar to the patient; S3, converting the ECG library into time series data, combining the ECG time series data into amplitude vectors in order; converting the preliminarily screened similar heart disease ECG data into heart disease vectors, calculating the similarity between the disease vector and the ECG vector collected by the patient based on cosine similarity, and specifically determining the type of heart disease from the similar heart diseases; S4. Based on the obtained type results, diagnosis suggestions are given based on big data, doctors provide auxiliary diagnosis suggestions, and give diagnosis plans.

2. The electrocardiogram-based intelligent monitoring method according to claim 1, characterized in that: The ECG collection period in step S1 is 6 hours. After every 1 hour, the patient's ECG is collected once to obtain the patient's ECG data. After uploading the data, preprocessing is performed. The preprocessing includes filtering and denoising, data standardization and feature extraction. The extracted features are the waveform characteristics of the ECG.

3. The electrocardiogram-based intelligent monitoring method according to claim 1, characterized in that: In step S2, the abnormal ECG waveform is screened by judging the overall waveform difference, and the overall difference is measured by calculating the mean error MSE between the actual waveform Es(t) and the normal reference waveform Ez(t) within the unit time (t1, t2). The calculation formula is: Among them, MES (t1, t2) is the calculated output value. By setting the normal waveform threshold, when the calculated output value is greater than the set threshold, it is judged that the ECG waveform in the time period (t1, t2) is abnormal, and the collected ECG data is screened.

4. The electrocardiogram-based intelligent monitoring method according to claim 1, characterized in that: The Euclidean calculation formula in step S2 is: Where Dj is the Euclidean distance between the current patient's ECG waveform and the ECG waveform of the jth disease type, n is the total number of time points of the ECG waveform, that is, the length of the time series, pi is the amplitude of the current patient's ECG at the i-th time point, sji is the amplitude of the ECG waveform of the j-th disease type at the i-th time point, i represents the index of the time point, and the ECG waveform is a series of time series data. The formula calculates the square of the amplitude difference at each time point, sums the results of all time points, and finally takes the square root to get the Euclidean distance. The obtained value Dj represents the distance between the two. The smaller the distance, the more similar the waveforms are, and the disease similar to the patient's current ECG waveform can be preliminarily determined.

5. The electrocardiogram-based intelligent monitoring method according to claim 1, characterized in that: In step S3, the electrocardiogram is converted into time series data by setting the total duration of the electrocardiogram to A and the sampling frequency to b, then the total number of sampling points is: C = Ab, and E(t) is used to represent the amplitude corresponding to the electrocardiogram signal collected at time t; Discretize the continuous time interval (0, A) according to the sampling frequency b to obtain discrete time points t n (n=0, 1, 2, ..., n-1), where t n =n / b, corresponding to the time corresponding to each sampling point, the corresponding time series data is expressed as X=(x0, x1, x2, ... x n-1 ), where x n is a discrete time point t n The ECG amplitude collected at .

6. The electrocardiogram-based intelligent monitoring method according to claim 1, characterized in that: In step S3, the time range and corresponding sampling interval of the entire ECG time series data are pre-defined for the acquired ECG time series data. In order, the amplitude corresponding to the first time point becomes the first element of the vector, and the amplitude corresponding to the second time point becomes the second element of the vector, and so on, until all the amplitude data corresponding to all time points in the entire time range are included to form a complete vector.

7. The electrocardiogram-based intelligent monitoring method according to claim 1, characterized in that: In step S3, for various known heart diseases, the disease-related ECG feature information is combined in sequence into a vector form, namely the disease vector. Each disease vector carries the key features of the corresponding disease in the ECG manifestation. The cosine similarity calculation method is used to measure the cosine value of the angle between two vectors to judge their similarity. The value range is between -1 and 1. When calculating the cosine similarity between the disease vector and the ECG vector collected from the patient, it is judged to be similar to the current disease vector.

8. The electrocardiogram-based intelligent monitoring method according to claim 7, characterized in that: The formula for calculating cosine similarity is: Where G represents the disease vector of the heart, H represents the ECG vector currently collected by the patient, and θ is the angle between the two vectors. A specific similarity value is obtained by calculation. When this value is closer to 1, it means that the angle between the disease vector and the patient's ECG vector in the feature space is smaller, indicating that the similarity between them is higher, indicating that the ECG characteristics of the patient are more consistent with the typical ECG characteristics of the corresponding disease; conversely, the closer the value is to -1 or 0, the lower the similarity between the two, and the less consistent the disease is with the patient's actual situation, thereby specifically determining the type of heart disease the patient is currently suffering from.

9. The electrocardiogram-based intelligent monitoring method according to claim 1, characterized in that: In step S4, through big data analysis, we can understand the development trends of the disease, complications and effects of different treatments for patients of different ages, genders and basic health conditions in the disease cases, and give suggestions for the current patients based on the obtained online information.

10. The electrocardiogram-based intelligent monitoring method according to claim 1, characterized in that: In step S4, the doctor gives advice based on the patient's clinical symptoms, taking into account the patient's medical history, family history, and current medications. Based on individual considerations and big data recommendations, the doctor provides the patient with customized diagnostic advice that suits their situation.

Images