Method for filing data of chest pain center

Through real-time monitoring and intelligent classification algorithm of the medical information management system, the data archiving of the chest pain center is automatically solved, and the problem of delay and low accuracy of data archiving in traditional methods is achieved, efficient, accurate and timely information management is achieved, and operation is improved. Efficiency and data security.

CN119028503APending Publication Date: 2024-11-26ZHONGSHAN TRADITIONAL CHINESE MEDICINE HOSPITAL
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411053411.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The traditional chest pain center data archiving method relies on manual operations, resulting in delayed data collection, entry and archiving time, human errors, low operation efficiency, and inability to meet the needs of modern medical services for efficient, accurate and timely information management.

Method used

Using the medical information management system to monitor data input in real time, automatically collect data through the data acquisition module, use intelligent classification algorithms to classify and archive data, realize automated notifications and one-click batch archiving, and combine encryption algorithms and data backup to ensure data security and integrity sex.

Benefits of technology

It significantly improves the timeliness, accuracy and operational efficiency of data archiving, simplifies operational steps, reduces human error rate, improves the scientificity and security of data management, and is suitable for rapid archiving of large amounts of data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119028503A_ABST
    Figure CN119028503A_ABST
Patent Text Reader

Abstract

The invention discloses a method for filing chest pain center data. The method comprises the following steps: S1, constructing a chest pain center data set; s2, performing format conversion and data cleaning on the acquired chest pain center data set; s3, classifying the preprocessed chest pain center data set by adopting an intelligent classification algorithm; s4, after data archiving of the chest pain center data set is completed, the system automatically generates notification information; s5, a dataman selects multiple groups of data needing to be archived in batches through a user interface; s6, the system automatically generates an archiving confirmation notice after batch archiving is completed, and a dataman confirms an archiving result through a user interface; and S7, in the archiving and transmission process, protecting the data by adopting an encryption algorithm. According to the method, the timeliness, the accuracy and the operation efficiency of data filing of the chest pain center are remarkably improved, and the requirements of modern medical services for efficient, accurate and timely information management are met.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data archiving, and in particular to a method for archiving data of a chest pain center. Background Art

[0002] The chest pain center is a specialized institution established to improve the treatment of acute chest pain diseases such as acute myocardial infarction and shorten the emergency response time. The construction and operation of the chest pain center requires comprehensive, timely and accurate archiving and management of patient medical information, diagnosis results and treatment records to ensure the quality and efficiency of medical services. However, the traditional data archiving method mainly relies on manual operation, which has many problems and needs to be improved urgently.

[0003] The existing chest pain center data archiving method usually involves manually collecting and entering patient information, diagnosis results, and treatment records. This manual operation method has the following significant defects:

[0004] Due to the limited speed of manual operation, there are often time delays in the collection, entry and filing of data. This delay will affect the timeliness of the data, and it cannot be guaranteed that the data can be filed in the first time, which in turn affects the rapid response of clinical decisions. Human errors are prone to occur during manual entry, including omission, misrecording or duplication of data. Due to the complexity and diversity of medical information, manual operation cannot completely avoid errors, which affects the accuracy and completeness of the data. Faced with a large amount of patient data, manual processing one by one is not only cumbersome and time-consuming, especially when there are a large number of patients and a large amount of information, the problem of low operation efficiency is particularly prominent. This inefficiency not only increases the workload of medical staff, but may also lead to delays and omissions of important information. Traditional data processing usually requires manual notification of relevant data clerks for processing, and this process also has time delays. The manual notification method is not only inefficient, but may also cause data processing delays due to untimely information transmission, affecting the smooth progress of the overall medical process.

[0005] Some attempts to improve existing technologies include the introduction of medical information management systems such as electronic medical record systems (EMR) and hospital information systems (HIS) to improve the efficiency of data management through partial automation. However, these systems still have shortcomings in practical applications and cannot completely solve the above problems. For example, although the electronic medical record system can achieve a certain degree of automated entry and archiving, it still requires a lot of manual intervention in real-time monitoring, intelligent classification, batch archiving, etc. of data, and fails to give full play to the advantages of automation technology. In addition, the notification mechanism in the existing system usually relies on simple message reminders, fails to achieve efficient and real-time automatic notification, and leads to a lag in information transmission.

[0006] In summary, the existing technology still has many deficiencies in the archiving of chest pain center data, and cannot meet the modern medical service's demand for efficient, accurate and timely information management. Therefore, a new method that can monitor data input in real time, automatically archive processing, intelligently classify and archive in batches with one click is urgently needed to improve the efficiency and accuracy of data management and ensure the efficient operation of the chest pain center. Summary of the invention

[0007] One object of the present invention is to propose a method for archiving chest pain center data, which significantly improves the timeliness, accuracy and operational efficiency of chest pain center data archiving, and meets the needs of modern medical services for efficient, accurate and timely information management.

[0008] A method for chest pain center data archiving according to an embodiment of the present invention includes the following steps:

[0009] S1. Use the medical information management system to monitor the data input of the chest pain center in real time, including patient information, diagnosis results, and treatment records, and automatically collect data through the data acquisition module to build a chest pain center data set;

[0010] S2. Convert the format and clean the collected chest pain center data set, remove redundant information, and standardize the data format;

[0011] S3, using an intelligent classification algorithm to classify the preprocessed chest pain center data set, assigning the data to corresponding filing categories, and automatically storing the classified data in a corresponding database or file system according to preset filing rules;

[0012] S4. After the chest pain center data set is archived, the system automatically generates notification information, including a summary of the archived content and processing requirements, and automatically sends a notification to the designated data clerk via email, SMS or system message to remind him to carry out follow-up processing;

[0013] S5. The data operator selects multiple groups of data that need to be archived in batches through the user interface. With one-click operation, the system automatically calls the batch processing algorithm to batch archive the selected data;

[0014] S6. After batch archiving is completed, the system automatically generates an archiving confirmation notification. The data clerk confirms the archiving result through the user interface. The system provides real-time status tracking function, and the data clerk can check the archiving status and processing progress of the data at any time;

[0015] S7. During the archiving and transmission process, encryption algorithms are used to protect data to prevent data leakage and unauthorized access. The system performs security checks and data backups regularly.

[0016] Optionally, S1 includes the following sub-steps:

[0017] S11. Use the medical information management system to monitor the data input of the chest pain center in real time, including patient information D p , Diagnosis result D d and treatment recordsD t ;

[0018] S12. The patient data is collected through the data collection module built into the medical information management system. p , Diagnosis result D d and treatment recordsD t Automatically collect and generate the original data set D raw :

[0019] D raw ={D p ,D d ,D t};

[0020] S13, for the original data set D raw Preprocess the original data set D raw The data in are sorted by timestamp T to construct a time series dataset D ts :

[0021] D ts ={(T1,D raw1 ),(T2,D raw2 ),…,(T n ,D rawn )};

[0022] Among them, T i is the timestamp of the ith data record, D rawi is the i-th original data;

[0023] S14. From the time series dataset D ts Extract feature data from the data set and construct chest pain center data set D c , including key patient informationI p , Diagnostic Information I d and treatment informationI t :

[0024] D c = {I p ,I d ,I t};

[0025] Among them, I p Including basic information of patient ID, name and age, I d Include the diagnosis and date of diagnosis, t Include treatment plans and treatment dates.

[0026] Optionally, S3 includes the following sub-steps:

[0027] S31. An intelligent classification algorithm based on correlation frequency analysis and dynamic priority adjustment was used to classify the preprocessed chest pain center data set D c To classify;

[0028] S32. Using data mining technology to analyze the chest pain center data set D c Perform frequency correlation analysis on various types of information in the system and calculate the correlation frequency F of each type of information. af ;

[0029] S33, based on the correlation frequency F af Construct the primary classification matrix M ic , key patient information p , Diagnostic Information I d and treatment informationI t Assign to the corresponding classification category;

[0030] S34, the primary classification matrix M ic Perform dynamic priority adjustments and adjust classification rules based on changes in real-time data flows;

[0031] S35, based on the dynamically adjusted priority, perform multi-dimensional feature mapping to generate a high-level feature vector F adv , including patient history relevance, treatment efficacy trends, and potential risk factors;

[0032] S36, comprehensive high-level feature vector F adv and dynamic priority classification results, assigning the data to the final archiving category and generating the final classification result set C final ;

[0033] S37, according to the preset archiving rules, the final classification result set C final The data in the file is automatically stored in the corresponding database or file system.

[0034] Optionally, the S32 includes the following sub-steps:

[0035] S321、Use data mining technology to analyze the chest pain center data set D c Key patient information in I p , Diagnostic Information I d and treatment informationI t Perform frequency analysis and calculate the frequency of occurrence of each category of information f i , where i represents various types of information;

[0036]

[0037] Where δ(i,k) is the indicator function. When the kth record contains category information i, δ(i,k) = 1, otherwise it is 0. N is the total number of records in the data set.

[0038] S322, according to the frequency f i Calculate the correlation frequency F between each category of information af , where the correlation frequency F af Indicates the frequency of two categories of information appearing together:

[0039]

[0040] in, is the i-th information item in the patient’s basic information, is the jth information item in the diagnostic information, δ(i, k) and δ(j, k) are indicator functions, indicating whether the kth record contains category information i and j;

[0041] S323. Treatment Information I t Perform similar frequency association analysis to calculate patient data I p and treatment informationI t The correlation frequency between af :

[0042]

[0043] in, is the kth information item in the treatment information, δ(i,m) and δ(k,m) are indicator functions, indicating whether the mth record contains category information i and k;

[0044] S324, diagnostic information I d and treatment informationI t Perform correlation frequency analysis and calculate the correlation frequency F between the two af :

[0045]

[0046] Among them, δ(j,n) and δ(k,n) are indicator functions, indicating whether the nth record contains category information j and k.

[0047] Optionally, the S33 includes the following sub-steps:

[0048] S331, based on the calculated association frequency F af , construct the primary classification matrix M ic , where the matrix element M ic (i,j) represents the degree of association between the i-th category information and the j-th category information:

[0049]

[0050] Among them, I i and I j Respectively represent each information item in the patient's basic information, diagnosis information and treatment information, and m and n are the total number of the patient's basic information and diagnosis information, respectively;

[0051] S332, the primary classification matrix M ic Each element in is standardized to obtain the standardized matrix M ic_norm ;

[0052] S333, according to the standardized primary classification matrix M ic_norm , key patient information p , Diagnostic Information I d and treatment informationI t Assign to the corresponding classification category and generate a preliminary classification result set C initial :

[0053]

[0054] Among them, Category n Indicates the nth classification category, Data m represents the mth data belonging to the category, and k represents the total number of classification categories;

[0055] S334, the preliminary classification result set C initial Perform consistency checks to ensure that data in the same category have high similarity and relevance:

[0056]

[0057] Among them, |Category n |Indicates CategoryCategory n The number of elements in , Indicates Category n The average standardized correlation frequency value of the elements in the table, the consistency test result should be within the preset threshold range.

[0058] Optionally, the S34 includes the following sub-steps:

[0059] S341, based on the primary classification matrix M ic_norm and real-time data stream, calculate the dynamic priority P of each type of information i :

[0060]

[0061] Among them, α and β are priority adjustment coefficients, fi is the occurrence frequency of the i-th type of information, is the total occurrence frequency of all categories of information, M ic_norm (i,j) is the standardized association frequency between the i-th information and the j-th information, and n is the total number of information categories;

[0062] S342, based on dynamic priority P i , for the primary classification matrix M ic_norm Adjust to form a dynamic priority classification matrix M dp :

[0063]

[0064] Among them, f i and f j is the frequency of occurrence of the corresponding category information;

[0065] S343, dynamic priority classification matrix M dp Update, consider the impact of real-time data flow, and calculate the dynamic priority update value ΔP i :

[0066]

[0067] Among them, γ and δ are update coefficients, f j_new is the frequency of new occurrences of the i-th type of information in the real-time data stream, is the total occurrence frequency of all categories of information in the real-time data stream, M ic_norm_new (i, j) is the new normalized association frequency between the i-th information and the j-th information in the real-time data stream;

[0068] S344, update the dynamic priority value ΔP i Applied to the dynamic priority classification matrix M dp , and obtain the updated dynamic priority classification matrix M dp_updated ;

[0069] S345, according to the updated dynamic priority classification matrix M dp_updated , for the preliminary classification result set C initial Reclassify.

[0070] Optionally, the S36 includes the following sub-steps:

[0071] S361. Calculate the high-level feature vector F for each piece of data adv , including history-related R history , Treatment effect trend T effect and potential risk factors risk :

[0072] Fadv (i) = {R history (i),T effect (i),F risk (i)};

[0073] Among them, i represents the i-th data;

[0074] S362, for the advanced feature vector F adv Perform standardization to obtain the standardized high-level feature vector F adv_norm ;

[0075] S363, based on the standardized high-level feature vector F adv_norm and the dynamic priority classification matrix M dp_updated , calculate the probability P of assigning each data item to a certain category category (i,j):

[0076]

[0077] Where i represents the i-th data, j represents the j-th archive category, k represents the dimension of the high-level feature vector, m is the number of dimensions of the high-level feature vector, and f k is the frequency of the kth feature, w jk is the weight of category j for feature k;

[0078] S364, assign probability P according to filing category category (i,j), assign each piece of data to the archiving category with the highest probability max :

[0079]

[0080] Among them, Category max (i) indicates the final filing category to which the i-th data item is assigned;

[0081] S365. Generate final classification result set C final :

[0082] C final = {Category n ={Data m |Category max (m)=n},n=1,2,…,k};

[0083] Among them, Category n Indicates the nth archive category, Data m represents the mth piece of data belonging to the category, and k represents the total number of archived categories.

[0084] Optionally, S5 includes the following sub-steps:

[0085] S51. The data clerk selects multiple sets of data that need to be archived in batches through the user interface and generates the data set D to be archived. batch , where D batch Indicates all the selected data to be archived;

[0086] S52, the medical information management system is based on the data set D to be archived batch Call batch processing algorithms to preprocess and convert data formats;

[0087] S53, classifying and archiving the preprocessed batch data, and the system stores each piece of data into a corresponding database or file system according to the classification result;

[0088] S54. After completing batch archiving, the medical information management system generates an archiving confirmation notification, which includes the specific data items and archiving status of the archive:

[0089] Notify(D batch_processed )={Data i ,Status i |i∈[1,n]};

[0090] Among them, Notify is the notification function, Data i Indicates the i-th archived data, Status i Indicates the archiving status of the data, and n is the total number of batch data;

[0091] S55. The data clerk confirms the archiving results through the user interface and records and adjusts according to the archiving confirmation notification.

[0092] The beneficial effects of the present invention are:

[0093] (1) The present invention uses a medical information management system to monitor the data input of the chest pain center in real time, including patient information, diagnosis results and treatment records. The data acquisition module can automatically collect this information and construct a chest pain center data set. Based on the intelligent classification algorithm of correlation frequency analysis and dynamic priority adjustment, the frequency correlation analysis of the information in the data set is carried out through data mining technology to construct a primary classification matrix, and dynamic priority adjustment is performed on this basis to form a dynamic priority classification matrix, which can not only accurately classify the data, but also adjust the classification rules according to the changes in the real-time data flow to ensure the dynamic adaptability and accuracy of the classification results. Through multi-layer feature extraction and priority allocation, the data can be accurately assigned to the corresponding archiving category, greatly improving the accuracy and efficiency of classification.

[0094] (2) The present invention calculates the high-level feature vectors of each piece of data, including features such as medical history correlation, treatment effect trend and potential risk factors, to conduct in-depth analysis and standardization of the data. Combined with the dynamic priority classification matrix, the probability of archiving category assignment for each piece of data is calculated, and the data is assigned to the archiving category with the highest probability. Not only basic information is considered, but also high-level features are integrated to ensure the scientificity and accuracy of data assignment and optimize the archiving process.

[0095] (3) The present invention has designed a one-key batch archiving function. The data operator selects multiple groups of data that need to be archived in batches through the user interface, and the system automatically calls the batch processing algorithm for archiving. The data after preprocessing and format conversion is classified and archived through the batch processing algorithm. After completion, the system generates an archiving confirmation notification, which greatly simplifies the operation steps and improves the efficiency and accuracy of batch processing. It is particularly suitable for the rapid archiving of large amounts of data, greatly improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0097] Figure 1 The present invention is a flowchart of a method for archiving chest pain center data. DETAILED DESCRIPTION

[0098] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0099] refer to Figure 1 , a method for chest pain center data archiving, comprising the following steps:

[0100] S1. Use the medical information management system to monitor the data input of the chest pain center in real time, including patient information, diagnosis results, and treatment records, and automatically collect data through the data acquisition module to build a chest pain center data set;

[0101] S2. Convert the format and clean the collected chest pain center data set, remove redundant information, and standardize the data format;

[0102] S3, using an intelligent classification algorithm to classify the preprocessed chest pain center data set, assigning the data to corresponding filing categories, and automatically storing the classified data in a corresponding database or file system according to preset filing rules;

[0103] S4. After the chest pain center data set is archived, the system automatically generates notification information, including a summary of the archived content and processing requirements, and automatically sends a notification to the designated data clerk via email, SMS or system message to remind him to carry out follow-up processing;

[0104] S5. The data operator selects multiple groups of data that need to be archived in batches through the user interface. With one-click operation, the system automatically calls the batch processing algorithm to batch archive the selected data;

[0105] S6. After batch archiving is completed, the system automatically generates an archiving confirmation notification. The data clerk confirms the archiving result through the user interface. The system provides real-time status tracking function, and the data clerk can check the archiving status and processing progress of the data at any time;

[0106] S7. During the archiving and transmission process, encryption algorithms are used to protect data to prevent data leakage and unauthorized access. The system performs security checks and data backups regularly.

[0107] In this implementation, S1 includes the following sub-steps:

[0108] S11. Use the medical information management system to monitor the data input of the chest pain center in real time, including patient information D p , Diagnosis result D d and treatment recordsD t ;

[0109] S12. The patient data is collected through the data collection module built into the medical information management system. p , Diagnosis result D d and treatment recordsD t Automatically collect and generate the original data set D raw :

[0110] D raw ={D p ,D d ,D t};

[0111] S13, for the original data set D raw Preprocess the original data set D raw The data in are sorted by timestamp T to construct a time series dataset D ts :

[0112] D ts ={(T1,D raw1 ),(T2,D raw2 ),…,(T n ,D rawn )};

[0113] Among them, Ti is the timestamp of the ith data record, D rawi is the i-th original data;

[0114] S14. From the time series dataset D ts Extract feature data from the data set and construct chest pain center data set D c , including key patient informationI p , Diagnostic Information I d and treatment informationI t :

[0115] D c = {I p ,I d ,I t};

[0116] Among them, I p Including basic information of patient ID, name and age, I d Include the diagnosis and date of diagnosis, t Include treatment plans and treatment dates.

[0117] In this implementation, S3 includes the following sub-steps:

[0118] S31. An intelligent classification algorithm based on correlation frequency analysis and dynamic priority adjustment was used to classify the preprocessed chest pain center data set D c To classify;

[0119] S32. Using data mining technology to analyze the chest pain center data set D c Perform frequency correlation analysis on various types of information in the system and calculate the correlation frequency F of each type of information. af ;

[0120] S33, based on the correlation frequency F af Construct the primary classification matrix M ic , key patient information p , Diagnostic Information I d and treatment informationI t Assign to the corresponding classification category;

[0121] S34, the primary classification matrix M ic Perform dynamic priority adjustments and adjust classification rules based on changes in real-time data flows;

[0122] S35, based on the dynamically adjusted priority, perform multi-dimensional feature mapping to generate a high-level feature vector F adv , including patient history relevance, treatment efficacy trends, and potential risk factors;

[0123] S36, comprehensive high-level feature vector F advand dynamic priority classification results, assigning the data to the final archiving category and generating the final classification result set C final ;

[0124] S37, according to the preset archiving rules, the final classification result set C final The data in the file is automatically stored in the corresponding database or file system.

[0125] In this implementation, S32 includes the following sub-steps:

[0126] S321、Use data mining technology to analyze the chest pain center data set D c Key patient information in I p , Diagnostic Information I d and treatment informationI t Perform frequency analysis and calculate the frequency of occurrence of each category of information f i , where i represents various types of information;

[0127]

[0128] Where δ(i,k) is the indicator function. When the kth record contains category information i, δ(i,k) = 1, otherwise it is 0. N is the total number of records in the data set.

[0129] S322, according to the frequency f i Calculate the correlation frequency F between each category of information af , where the correlation frequency F af Indicates the frequency of two categories of information appearing together:

[0130]

[0131] in, is the i-th information item in the patient’s basic information, is the jth information item in the diagnostic information, δ(i, k) and δ(j, k) are indicator functions, indicating whether the kth record contains category information i and j;

[0132] S323. Treatment Information I t Perform similar frequency association analysis to calculate patient data I p and treatment informationI t The correlation frequency between af :

[0133]

[0134] Among them, I tk is the kth information item in the treatment information, δ(i,m) and δ(k,m) are indicator functions, indicating whether the mth record contains category information i and k;

[0135] S324, diagnostic information I d and treatment informationI t Perform correlation frequency analysis and calculate the correlation frequency F between the two af :

[0136]

[0137] Among them, δ(j,n) and δ(k,n) are indicator functions, indicating whether the nth record contains category information j and k.

[0138] In this implementation, S33 includes the following sub-steps:

[0139] S331, based on the calculated association frequency F af , construct the primary classification matrix M ic , where the matrix element M ic (i,j) represents the degree of association between the i-th category information and the j-th category information:

[0140]

[0141] Among them, I i and I j Respectively represent each information item in the patient's basic information, diagnosis information and treatment information, and m and n are the total number of the patient's basic information and diagnosis information, respectively;

[0142] S332, the primary classification matrix M ic Each element in is standardized to obtain the standardized matrix M ic_norm ;

[0143] S333, according to the standardized primary classification matrix M ic_norm , key patient information p , Diagnostic Information I d and treatment informationI t Assign to the corresponding classification category and generate a preliminary classification result set C initial :

[0144]

[0145] Among them, Category n Indicates the nth classification category, Data m represents the mth data belonging to the category, and k represents the total number of classification categories;

[0146] S334, the preliminary classification result set C initial Perform consistency checks to ensure that data in the same category have high similarity and relevance:

[0147]

[0148] Among them, |Category n |Indicates CategoryCategory n The number of elements in , Indicates Category n The average standardized correlation frequency value of the elements in the , and the consistency test result should be within the preset threshold range.

[0149] In this implementation, S34 includes the following sub-steps:

[0150] S341, based on the primary classification matrix M ic_norm and real-time data stream, calculate the dynamic priority P of each type of information i :

[0151]

[0152] Among them, α and β are priority adjustment coefficients, f i is the occurrence frequency of the i-th type of information, is the total occurrence frequency of all categories of information, M ic_norm (i,j) is the standardized association frequency between the i-th information and the j-th information, and n is the total number of information categories;

[0153] S342, based on dynamic priority P i , for the primary classification matrix M ic_norm Adjust to form a dynamic priority classification matrix M dp :

[0154]

[0155] Among them, f i and f j is the frequency of occurrence of the corresponding category information;

[0156] S343, dynamic priority classification matrix M dp Update, consider the impact of real-time data flow, and calculate the dynamic priority update value ΔP i :

[0157]

[0158] Among them, γ and δ are update coefficients, f j_new is the frequency of new occurrences of the i-th type of information in the real-time data stream, is the total occurrence frequency of all categories of information in the real-time data stream, M ic_norm_new (i, j) is the new normalized association frequency between the i-th information and the j-th information in the real-time data stream;

[0159] S344, update the dynamic priority value ΔP i Applied to the dynamic priority classification matrix M dp , and obtain the updated dynamic priority classification matrix M dp_updated ;

[0160] S345, according to the updated dynamic priority classification matrix M dp_updated , for the preliminary classification result set C initial Reclassify.

[0161] In this implementation, S36 includes the following sub-steps:

[0162] S361. Calculate the high-level feature vector F for each piece of data adv , including history-related R history , Treatment effect trend T effect and potential risk factors risk :

[0163] F adv (i) = {R history (i),T effect (i),F risk (i)};

[0164] Among them, i represents the i-th data;

[0165] S362, for the advanced feature vector F adv Perform standardization to obtain the standardized high-level feature vector F adv_norm ;

[0166] S363, based on the standardized high-level feature vector F adv_norm and the dynamic priority classification matrix M dp_updated , calculate the probability P of assigning each data item to a certain category category (i,j):

[0167]

[0168] Where i represents the i-th data, j represents the j-th archive category, k represents the dimension of the high-level feature vector, m is the number of dimensions of the high-level feature vector, and f k is the frequency of the kth feature, w jk is the weight of category j for feature k;

[0169] S364, assign probability P according to filing category category (i,j), assign each piece of data to the archiving category with the highest probability max :

[0170]

[0171] Among them, Category max (i) indicates the final filing category to which the i-th data item is assigned;

[0172] S365. Generate final classification result set C final :

[0173] C final = {Category n ={Data m |Category max (m)=n},n=1,2,…,k};

[0174] Among them, Category n Indicates the nth archive category, Data m represents the mth piece of data belonging to the category, and k represents the total number of archived categories.

[0175] In this implementation, S5 includes the following sub-steps:

[0176] S51. The data clerk selects multiple sets of data that need to be archived in batches through the user interface and generates the data set D to be archived. batch , where D batch Indicates all the selected data to be archived;

[0177] S52, the medical information management system is based on the data set D to be archived batch Call batch processing algorithms to preprocess and convert data formats;

[0178] S53, classifying and archiving the preprocessed batch data, and the system stores each piece of data into a corresponding database or file system according to the classification result;

[0179] S54. After completing batch archiving, the medical information management system generates an archiving confirmation notification, which includes the specific data items and archiving status of the archive:

[0180] Notify(D batch_processed )={Data i ,Status i |i∈[1,n]};

[0181] Among them, Notify is the notification function, Data i Indicates the i-th archived data, Status i Indicates the archiving status of the data, and n is the total number of batch data;

[0182] S55. The data clerk confirms the archiving results through the user interface and records and adjusts according to the archiving confirmation notification.

[0183] Embodiment 1:

[0184] Example 1 The feasibility of the present invention is verified in the chest pain center of a general hospital in a certain city. The chest pain center of a general hospital in a certain city receives a large number of acute chest pain patients every day, involving the diagnosis and treatment of acute chest pain diseases such as acute myocardial infarction. The center not only needs to respond to emergency cases quickly, but also needs to efficiently manage and archive patients' medical information, diagnosis results and treatment records. The traditional manual archiving method has problems such as delay, low accuracy, cumbersome operation and insufficient safety, and cannot meet the needs of efficient management.

[0185] On a weekday with a high incidence of acute chest pain, the chest pain center received 50 patients with acute chest pain. During the consultation process, the patient's medical information, diagnosis results and treatment records were quickly input into the medical information management system. The method of the present invention is applied to the entire data archiving process, and the specific steps are as follows:

[0186] First, the medical information management system monitors the data input of all patients in real time, including patient information (name, age, medical history), diagnosis results (such as electrocardiogram, blood test results) and treatment records (medication, surgical records). The system's built-in data acquisition module automatically collects this information and constructs a chest pain center data set, as shown in Table 1 below:

[0187] Table 1 Chest pain center data set

[0188] Data Types content Time Basic Information Name: Zhang San, Age: 56, Medical History: Hypertension 08:00 Diagnosis ECG showed ST segment elevation, blood test: elevated troponin 08:10 Treatment Records Oxygen inhalation, nitroglycerin, emergency PCI surgery 08:20-09:00

[0189] After data collection is completed, the system converts the format of the collected data and cleans the data, removes redundant information, standardizes the data format, and ensures the accuracy and consistency of the data.

[0190] Next, the system uses an intelligent classification algorithm based on correlation frequency analysis and dynamic priority adjustment to classify the preprocessed chest pain center data set. Through frequency correlation analysis, the system calculates the correlation frequency of each type of information and constructs a primary classification matrix. On this basis, the classification rules are dynamically adjusted to form a dynamic priority classification matrix to ensure the dynamic adaptability and accuracy of the classification results.

[0191] Then, the system calculates the high-level feature vectors for each piece of data, including features such as medical history relevance, treatment effect trends, and potential risk factors. After the high-level feature vectors are standardized, they are combined with the dynamic priority classification matrix to calculate the probability of assigning each piece of data to the archiving category. Based on the assignment probability, the system assigns each piece of data to the archiving category with the highest probability, and generates the final classification result set as shown in Table 2 below:

[0192] Table 2 Final classification result set

[0193] Patient ID Basic information status Diagnosis result status Treatment record status Final Archive Category Zhang San Archived Archived Archived Category A

[0194] After the classification is completed, the data clerk selects multiple groups of data that need to be archived in batches through the user interface. The system automatically calls the batch processing algorithm to classify and archive the data after preprocessing and format conversion. After the batch archiving is completed, the system generates an archiving confirmation notification to inform the data clerk of the specific data items and archiving status of the archive.

[0195] Finally, the data clerk confirms the archiving results through the user interface and makes necessary records and adjustments based on the archiving confirmation notification to ensure that all data is archived correctly.

[0196] To verify the effectiveness of the method of the present invention, we conducted a comparative experiment. The experimental location was the chest pain center of a general hospital in a certain city, and the experimental time was a peak working day in a certain month, and 50 patients with acute chest pain were admitted. The experiment compared the performance of the method of the present invention and the traditional manual filing method in the data filing process. The comparative data is shown in Table 3 below:

[0197] Table 3 Comparison items between the present invention and the traditional method

[0198] Compare Projects Traditional methods Method of the present invention Data collection time 3 hours 1 hour Data cleaning accuracy 85% 99% Archive category time 2 hours 30 minutes Classification Accuracy 80% 98% Batch archiving time 2 hours 15 minutes Total processing time 7 hours 1 hour 45 minutes Delayed information transmission 30 minutes 5 minutes Data security generally high

[0199] As can be seen from Table 3, the method of the present invention is significantly superior to the traditional method in terms of data collection time, data cleaning accuracy, filing classification time, classification accuracy, batch filing time and total processing time. In addition, the method of the present invention also shows obvious advantages in information transmission delay and data security.

[0200] In summary, the method of the present invention shows significant superiority in archiving chest pain center data. Through technical means such as real-time monitoring, intelligent classification, advanced feature vector analysis and one-click batch archiving, it solves the problems of delay, low accuracy, cumbersome operation and insufficient security existing in traditional methods, greatly improves the efficiency and accuracy of data management, and has important practical application value.

[0201] The present invention uses a medical information management system to monitor the data input of the chest pain center in real time, including patient information, diagnosis results and treatment records. The data acquisition module can automatically collect this information and construct a chest pain center data set. Based on the intelligent classification algorithm of correlation frequency analysis and dynamic priority adjustment, the frequency correlation analysis of the information in the data set is carried out through data mining technology to construct a primary classification matrix, and dynamic priority adjustment is performed on this basis to form a dynamic priority classification matrix, which can not only accurately classify the data, but also adjust the classification rules according to the changes in the real-time data stream to ensure the dynamic adaptability and accuracy of the classification results. Through multi-layer feature extraction and priority allocation, the data can be accurately assigned to the corresponding archiving category, greatly improving the accuracy and efficiency of classification.

[0202] The present invention calculates the advanced feature vectors of each piece of data, including features such as medical history correlation, treatment effect trend and potential risk factors, to conduct in-depth analysis and standardized processing of the data. Combined with the dynamic priority classification matrix, the probability of archiving category assignment for each piece of data is calculated, and the data is assigned to the archiving category with the highest probability. Not only basic information is considered, but also advanced features are integrated to ensure the scientificity and accuracy of data assignment and optimize the archiving process.

[0203] The present invention is designed with a one-key batch archiving function. The data operator selects multiple groups of data that need to be archived in batches through the user interface, and the system automatically calls the batch processing algorithm for archiving. The data after preprocessing and format conversion is classified and archived through the batch processing algorithm. After completion, the system generates an archiving confirmation notification, which greatly simplifies the operation steps and improves the efficiency and accuracy of batch processing. It is particularly suitable for the rapid archiving of large amounts of data, greatly improving work efficiency.

[0204] The present invention significantly improves the timeliness, accuracy and operational efficiency of chest pain center data archiving through real-time monitoring and automatic archiving, intelligent classification algorithms, advanced feature vector analysis and one-click batch archiving, meets the needs of modern medical services for efficient, accurate and timely information management, and has important practical application value.

[0205] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for archiving chest pain center data, characterized in that: The steps include: S1. Use the medical information management system to monitor the data input of the chest pain center in real time, including patient information, diagnosis results, and treatment records, and automatically collect data through the data acquisition module to build a chest pain center data set; S2. Convert the format and clean the collected chest pain center data set, remove redundant information, and standardize the data format; S3, using an intelligent classification algorithm to classify the preprocessed chest pain center data set, assigning the data to corresponding filing categories, and automatically storing the classified data in a corresponding database or file system according to preset filing rules; S4. After the chest pain center data set is archived, the system automatically generates notification information, including a summary of the archived content and processing requirements, and automatically sends a notification to the designated data clerk via email, SMS or system message to remind him to carry out follow-up processing; S5. The data clerk selects multiple groups of data that need to be archived in batches through the user interface. With one-click operation, the system automatically calls the batch processing algorithm to batch archive the selected data; S6. After batch archiving is completed, the system automatically generates an archiving confirmation notification. The data clerk confirms the archiving result through the user interface. The system provides real-time status tracking function, and the data clerk can check the archiving status and processing progress of the data at any time; S7. During the archiving and transmission process, encryption algorithms are used to protect data to prevent data leakage and unauthorized access. The system performs security checks and data backups regularly.

2. A method for chest pain center data archiving according to claim 1, characterized in that: The S1 comprises the following sub-steps: S11. Use the medical information management system to monitor the data input of the chest pain center in real time, including patient information D p , Diagnosis result D d and treatment recordsD t ; S12. The patient data is collected through the data collection module built into the medical information management system. p , Diagnosis result D d and treatment recordsD t Automatically collect and generate the original data set D raw : D raw ={D p ,D d ,D t }; S13, for the original data set D raw Preprocess the original data set D raw The data in are sorted by timestamp T to construct a time series dataset D ts : D ts ={(T1,D raw1 ),(T2,D raw2 ),…,(T n ,D rawn )}; Among them, T i is the timestamp of the ith data record, D rawi is the i-th original data; S14. From the time series dataset D ts Extract feature data from the data set and construct chest pain center data set D c , including key patient informationI p , Diagnostic Information I d and treatment informationI t : D c ={I p ,I d ,I t }; Among them, I p Including basic information of patient ID, name and age, I d Include the diagnosis and date of diagnosis, t Include treatment plans and treatment dates.

3. A method for chest pain center data archiving according to claim 2, characterized in that: The S3 comprises the following sub-steps: S31. An intelligent classification algorithm based on correlation frequency analysis and dynamic priority adjustment was used to classify the preprocessed chest pain center data set D c To classify; S32. Using data mining technology to analyze the chest pain center data set D c Perform frequency correlation analysis on various types of information in the system and calculate the correlation frequency F of each type of information. af ; S33, based on the correlation frequency F af Construct the primary classification matrix M ic , key patient information p , Diagnostic Information I d and treatment informationI t Assign to the corresponding classification category; S34, the primary classification matrix M ic Perform dynamic priority adjustments and adjust classification rules based on changes in real-time data flows; S35, based on the dynamically adjusted priority, perform multi-dimensional feature mapping to generate a high-level feature vector F adv , including patient history relevance, treatment efficacy trends, and potential risk factors; S36, comprehensive high-level feature vector F adv and dynamic priority classification results, assigning the data to the final archiving category and generating the final classification result set C final ; S37, according to the preset archiving rules, the final classification result set C final The data in the file is automatically stored in the corresponding database or file system.

4. A method for chest pain center data archiving according to claim 3, characterized in that: The S32 includes the following sub-steps: S321、Use data mining technology to analyze the chest pain center data set D c Key patient information in I p , Diagnostic Information I d and treatment informationI t Perform frequency analysis and calculate the frequency of occurrence of each category of information f i , where i represents various types of information; Where δ(i,k) is the indicator function. When the kth record contains category information i, δ(i,k) = 1, otherwise it is 0. N is the total number of records in the data set. S322, according to the frequency f i Calculate the correlation frequency F between each category of information af , where the correlation frequency F af Indicates the frequency of two categories of information appearing together: in, is the i-th information item in the patient’s basic information, is the jth information item in the diagnostic information, δ(i, k) and δ(j, k) are indicator functions, indicating whether the kth record contains category information i and j; S323. Treatment Information I t Perform similar frequency association analysis to calculate patient data I p and treatment informationI t The correlation frequency between af : in, is the kth information item in the treatment information, δ(i,m) and δ(k,m) are indicator functions, indicating whether the mth record contains category information i and k; S324, diagnostic information I d and treatment informationI t Perform correlation frequency analysis and calculate the correlation frequency F between the two af : Among them, δ(j,n) and δ(k,n) are indicator functions, indicating whether the nth record contains category information j and k.

5. A method for chest pain center data archiving according to claim 4, characterized in that: The S33 comprises the following sub-steps: S331, based on the calculated association frequency F af , construct the primary classification matrix M ic , where the matrix element M ic (i,j) represents the degree of association between the i-th category information and the j-th category information: Among them, I i and I j Respectively represent each information item in the patient's basic information, diagnosis information and treatment information, and m and n are the total number of the patient's basic information and diagnosis information, respectively; S332, the primary classification matrix M ic Each element in is standardized to obtain the standardized matrix M ic_norm ; S333, according to the standardized primary classification matrix M ic_norm , key patient information p , Diagnostic Information I d and treatment informationI t Assign to the corresponding classification category and generate a preliminary classification result set C initial : Among them, Category n Indicates the nth classification category, Data m represents the mth data belonging to the category, and k represents the total number of classification categories; S334, the preliminary classification result set C initial Perform consistency checks to ensure that data in the same category have high similarity and relevance: Among them, |Category n |Indicates CategoryCategory n The number of elements in , Indicates Category n The average standardized correlation frequency value of the elements in the , and the consistency test result should be within the preset threshold range.

6. A method for chest pain center data archiving according to claim 5, characterized in that: The S34 comprises the following sub-steps: S341, based on the primary classification matrix M ic_norm and real-time data stream, calculate the dynamic priority P of each type of information i : Among them, α and β are priority adjustment coefficients, f i is the occurrence frequency of the i-th type of information, is the total occurrence frequency of all categories of information, M ic_norm (i,j) is the standardized association frequency between the i-th information and the j-th information, and n is the total number of information categories; S342, based on dynamic priority P i , for the primary classification matrix M ic_norm Adjust to form a dynamic priority classification matrix M dp : Among them, f i and f j is the frequency of occurrence of the corresponding category information; S343, dynamic priority classification matrix M dp Update, consider the impact of real-time data flow, and calculate the dynamic priority update value ΔP i : Among them, γ and δ are update coefficients, f j_new is the frequency of new occurrences of the i-th type of information in the real-time data stream, is the total occurrence frequency of all categories of information in the real-time data stream, M ic_norm_new (i, j) is the new normalized association frequency between the i-th information and the j-th information in the real-time data stream; S344, update the dynamic priority value ΔP i Applied to the dynamic priority classification matrix M dp , and obtain the updated dynamic priority classification matrix M dp_updated ; S345, according to the updated dynamic priority classification matrix M dp_updated , for the preliminary classification result set C initial Reclassify.

7. A method for chest pain center data archiving according to claim 6, characterized in that: The S36 comprises the following sub-steps: S361. Calculate the high-level feature vector F for each piece of data adv , including history-related R history , Treatment effect trend T effect and potential risk factors risk : F adv (i)={R history (i),T effect (i),F risk (i)}; Among them, i represents the i-th data; S362, for the advanced feature vector F adv Perform standardization to obtain the standardized high-level feature vector F adv_norm ; S363, based on the standardized high-level feature vector F adv_norm and the dynamic priority classification matrix M dp_updated , calculate the probability P of assigning each data item to a certain category category (i,j): Where i represents the i-th data, j represents the j-th archive category, k represents the dimension of the high-level feature vector, m is the number of dimensions of the high-level feature vector, and f k is the frequency of the kth feature, w jk is the weight of category j for feature k; S364, assign probability P according to filing category category (i,j), assign each piece of data to the archiving category with the highest probability max : Among them, Category max (i) indicates the final filing category to which the i-th data item is assigned; S365. Generate final classification result set C final : C final ={Category n ={Data m |Category max (m)=n},n=1,2,…,k}; Among them, Category n Indicates the nth archive category, Data m represents the mth piece of data belonging to the category, and k represents the total number of archived categories.

8. A method for chest pain center data archiving according to claim 7, characterized in that: The S5 comprises the following sub-steps: S51. The data officer selects multiple sets of data that need to be archived in batches through the user interface and generates the data set D to be archived. batch , where D batch Indicates all the selected data to be archived; S52, the medical information management system is based on the data set D to be archived batch Call batch processing algorithms to preprocess and convert data formats; S53, classifying and archiving the preprocessed batch data, and the system stores each piece of data into a corresponding database or file system according to the classification result; S54. After completing batch archiving, the medical information management system generates an archiving confirmation notification, which includes the specific data items and archiving status of the archive: Notify(D batch_processed )={Data i ,Status i |i∈[1,n]}; Among them, Notify is the notification function, Data i Indicates the i-th archived data, Status i Indicates the archiving status of the data, and n is the total number of batch data; S55. The data clerk confirms the archiving results through the user interface and records and adjusts according to the archiving confirmation notification.