Clinical medical data visualization processing system

Abstract

The present invention discloses a clinical medical data visualization processing system, which includes collecting clinical medical data from various medical institutions from various platforms, and preliminarily organizing the clinical medical data of each medical institution. Since the data comes from different medical institutions, it is necessary to aggregate the processed clinical medical data to obtain aggregated data, calculate the similarity of the aggregated data using a cosine similarity model to obtain similarity data, and compare the similarity data with a similarity threshold, further analyze the similarity data, and determine the degree of visualization of the data by comparing the visualization ratio of the similarity data with a ratio threshold, which helps medical management agencies to better understand medical data and support decision-making, resource optimization and health management, while improving the efficiency and quality of visualization processing of medical data.

Description

Technical Field

[0001] The present invention relates to the technical field of data visualization, and in particular to a clinical medical data visualization processing system. Background Art

[0002] In the field of modern healthcare, the generation and accumulation of data is increasing rapidly, and the processing, management and analysis of medical data have become crucial tasks. In order to better understand, utilize and share clinical medical data, clinical medical data visualization processing systems have emerged. These systems integrate key technologies in the fields of medicine, information technology and data science to meet the growing needs of the healthcare industry, improve the quality of patient care, and support the scientificity and accuracy of medical decision-making.

[0003] The prior art has the following deficiencies:

[0004] In the existing technology, different hospitals and medical institutions usually store their medical data in different systems and databases. These data are stored in different places with different formats and standards. More importantly, medical data are often not interoperable, which means that the data of one medical institution cannot usually interact and share directly with the data of another medical institution. Health management agencies need to view local health data and conduct investigations and analyses in each hospital, which is a huge workload. At the same time, since the data are independent, the analysis dimensions are difficult to unify, and the data content is also different, it is difficult to achieve a unified data display, which makes the data readability poor. Summary of the invention

[0005] The purpose of the present invention is to provide a clinical medical data visualization processing system to solve the shortcomings of the background technology.

[0006] In order to achieve the above-mentioned object, the present invention provides the following technical solution: a clinical medical data visualization processing system, characterized in that it includes an information acquisition unit, a data processing unit, a comparison and analysis unit, and an analysis and processing unit;

[0007] Information collection unit: collects clinical medical data from various medical institutions from various platforms, preliminarily organizes the clinical medical data of each medical institution, and sends the organized data to the data processing unit;

[0008] Data processing unit: after receiving the processed clinical medical data, since the data comes from different medical institutions, it is necessary to aggregate the processed clinical medical data to obtain aggregated data, calculate the similarity of the aggregated data using the cosine similarity model, and send the similarity data to the comparison and analysis unit;

[0009] Comparison and analysis unit: compares the received similarity data with the similarity threshold, and sends the comparison and analysis results to the analysis and processing unit;

[0010] Analysis and processing unit: after receiving the comparison and analysis results sent by the comparison module, further analyze the similar data, and determine the degree of data visualization by comparing the quality coefficient of the similarity data with the ratio threshold.

[0011] In a preferred embodiment, after receiving the pre-processed medical data, since the data comes from various different medical institutions, it is necessary to perform aggregation processing on the processed clinical medical data.

[0012] In a preferred embodiment, the medical consultation number generated each time the patient visits the doctor is marked and saved so as to associate the records in the relevant data table with the same medical consultation event;

[0013] Aggregate medical data belonging to the same diagnosis and treatment event but obtained from different data tables, integrate related medical data from different data sources or data tables, and allow multiple related data rows to be merged into a single data row so as to combine them into a more complete medical data table.

[0014] In a preferred embodiment, after the aggregated data is obtained, the similarity of the aggregated data is calculated by using a cosine similarity model;

[0015] Represent each aggregate as a feature vector, where each dimension represents an aggregate or feature.

[0016] Perform standard normalization on the aggregated data of each dimension;

[0017] Use cosine similarity to calculate the similarity between two vector data. The expression is: In the formula, cos(x, y) represents the similarity of data, x i and yi represent the values ​​of the i-th feature dimension of the two data points respectively, and n is the total number of feature dimensions;

[0018] Compare the data similarity with the similarity threshold,

[0019] If the data similarity is ≥ the similarity threshold, a similarity signal is generated;

[0020] If the data similarity is less than the similarity threshold, no similarity signal is generated.

[0021] In a preferred embodiment, data with data similarity greater than or equal to a similarity threshold is regarded as similarity data. In order to ensure the quality of the similarity data, the similarity data needs to be further analyzed; the population belonging to the same age period in the similarity data is counted to obtain the proportion of the sample population similarity, that is, the similarity value of the sample population;

[0022] The total number of samples from the same hospital in the similarity data is counted to obtain the proportion of the number of samples from the hospital to the number of similarity data, that is, the deviation value of the sample data;

[0023] Add the similarity value of the sample population and the deviation value of the sample data, and then multiply by the influence weight to obtain the quality coefficient of the data;

[0024] Compare the quality factor of the data to a ratio threshold;

[0025] If the quality coefficient ≥ the ratio threshold, an adjustment signal is generated;

[0026] If the quality factor is less than the ratio threshold, a normal signal is generated.

[0027] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0028] 1. The present invention collects clinical medical data from various medical institutions from various platforms, and preliminarily organizes the clinical medical data of each medical institution. Since the data comes from different medical institutions, it is necessary to aggregate the processed clinical medical data to obtain aggregated data. The similarity of the aggregated data is calculated using the cosine similarity model, which helps to improve the utilization efficiency of medical resources, promote the interoperability of health data, and support better health decision-making and quality management.

[0029] 2. The present invention compares the received similarity data with the similarity threshold, regards the data with data similarity greater than or equal to the similarity threshold as similarity data, and conducts further analysis, and conducts a comprehensive analysis on the similarity values ​​of the sample population and the deviation values ​​of the sample data. By comparing the quality coefficient of the similarity data with the ratio threshold, the degree of data visualization is determined, which helps to optimize the efficiency of data analysis and visualization, improve the scientificity and basis of decision-making, and improve the quality of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0031] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Example

[0034] See also Figure 1 As shown, the clinical medical data visualization processing system described in this embodiment includes an information acquisition unit, a data processing unit, a comparison and analysis unit, and an analysis and processing unit;

[0035] The information collection unit collects clinical medical data from various medical institutions from various platforms, preliminarily organizes the clinical medical data of each medical institution, and sends the organized data to the data processing unit;

[0036] After receiving the processed clinical medical data, the data processing unit needs to aggregate the processed clinical medical data to obtain aggregated data, because the data comes from different medical institutions, calculate the similarity of the aggregated data using the cosine similarity model, and send the similarity data to the comparison and analysis unit;

[0037] The comparison and analysis unit compares the received data similarity with the similarity threshold, and sends the comparison and analysis result to the analysis processing unit;

[0038] After receiving the comparison analysis result sent by the comparison module, the analysis processing unit further analyzes the similar data and determines the visualization degree of the data by comparing the quality coefficient of the similarity data with the ratio threshold.

[0039] The main operations of the information collection unit include:

[0040] Access and extraction of data sources: connect to various data sources, which may include information systems, databases, data warehouses of health departments, etc. of different hospitals and medical institutions, and then extract medical data from the data sources, including patient visit records, medical history information, diagnosis reports, laboratory test results, imaging examination reports, etc.;

[0041] Preprocess the data: Perform preliminary cleaning and preprocessing on the extracted data, including removing duplicate data, processing missing values, standardizing data formats, and ensuring data accuracy and completeness;

[0042] Data transmission: Send the preprocessed data to the data processing unit.

[0043] The operations of the data processing unit include:

[0044] Extract and associate data: After receiving the pre-processed medical data, the data processing unit needs to aggregate the processed clinical medical data because the data comes from different medical institutions. For example, clinical medical data includes outpatient record sheets, drug bills, etc. Each data sheet contains several medical records. Since each medical record is generated by a patient, each medical record should have its corresponding medical record number. The medical record number generated each time the patient visits the hospital is marked and saved. The medical record number can be compiled based on the medical institution itself or compiled by all hospitals. The medical record number can be used to associate the records in the relevant data sheets with the same medical event.

[0045] When the medical order number is compiled by all hospitals, patients with the same type of disease can be managed uniformly based on the medical order number. For example, when the serial number of all hospitals is unified, the first letters of the serial number for patients with brain diseases can be universally NK. With the unified serial number, even if each medical institution uploads different formats and contents of medical data, the first letters of the medical order number are the same, so they can be classified as one type of data;

[0046] When the medical order number is compiled by each medical institution, the data format in the medical order number needs to be converted. Since the medical data of various medical institutions are obtained from multiple platforms, the types of medical data obtained are relatively diverse. Therefore, data conversion is performed based on various data standards in the medical data. For each related record, data conversion is performed to make the data have a consistent format and structure in the same data set, including data type conversion, date formatting, unit conversion, etc.

[0047] For example, the age field in one data table may be an integer, while the age field in another data table may be text. During the data conversion process, the data types of these fields need to be unified into the same type, and all the field data in the data table needs to be replaced with text data.

[0048] Data aggregation: Aggregate medical data from different data tables that belong to the same diagnosis and treatment event, and integrate related medical data from different data sources or data tables to combine them into a more complete medical record or data table. This helps to integrate information from different data sources, making it easier to analyze, understand and use;

[0049] For example, the data of different indicators of the same dimension in the data table are aggregated to form page display data. The dimension is the data object that the user wants to view, such as the date is year, month, day, the region is province, city, district, county, etc., and the medical unit is medical institution, hospital, department, doctor, etc. Therefore, the indicator data in the data table is aggregated according to the dimension.

[0050] For example, when the corresponding dimension is a medical institution in a certain month, if you want to query the expenditure on health care drugs, you can aggregate the expenditure on health care drugs for each doctor in each department of the medical institution on each day of the month to obtain the corresponding page display data.

[0051] In this case, data belonging to the same diagnosis and treatment event can be aggregated from different data tables to create a complete medical record that includes basic patient information, medical information, diagnosis, laboratory tests, imaging examinations, and drug prescriptions. This aggregated data set can better support doctors' diagnosis and treatment decisions, and also help medical research and quality management;

[0052] Data aggregation is the process of merging or summarizing related records into a more comprehensive medical record or data set. This allows multiple related data rows to be combined into a single data row for easier analysis and visualization. Suppose a patient undergoes multiple laboratory tests of the same type at different time points, and each test produces a numerical result. In data aggregation, the average of these results is calculated to obtain an average value that represents the patient's overall health status. For example, a patient has three blood pressure measurements, and the following data are obtained:

[0053] First measurement: Systolic blood pressure (Systolic) = 120 mmHg, diastolic blood pressure (Diastolic) = 80 mmHg;

[0054] Second measurement: Systolic blood pressure (Systolic) = 130 mmHg, diastolic blood pressure (Diastolic) = 85 mmHg;

[0055] The third measurement: Systolic blood pressure (Systolic) = 125 mmHg, diastolic blood pressure (Diastolic) = 78 mmHg;

[0056] By aggregating the data, the average systolic and average diastolic blood pressures of these three measurements can be calculated to obtain a more comprehensive blood pressure summary, with an average systolic blood pressure of 125 mmHg and an average diastolic blood pressure of 81 mmHg;

[0057] Calculate the similarity of aggregated data: After obtaining the aggregated data, the similarity of the aggregated data is calculated by using the cosine similarity model. For example, when the corresponding dimension of the patient is a medical institution in a certain month, you want to query the average systolic blood pressure of the corresponding blood pressure measurement patient, which mainly includes the following contents;

[0058] Represent each aggregate as a feature vector, where each dimension represents an aggregate or feature.

[0059] Perform standard normalization on the aggregated data of each dimension;

[0060] Use cosine similarity to calculate the similarity between two vectors. Cosine similarity is the cosine value of the angle between two vectors, ranging from -1 to 1. The closer the cosine similarity is to 1, the higher the similarity of the aggregated data.

[0061] In a specific implementation, the similarity of aggregated data is calculated by using cosine as an example.

[0062] For example, when comparing the conditions of all patients who had their blood pressure measured in a certain month in the local area, the corresponding indicator data is the blood pressure data of all patients who had their blood pressure measured in the local medical institutions in that month and their own corresponding blood pressure data, and the similarity between the data is calculated.

[0063] The calculation formula for cosine similarity is: In the formula, cos(x, y) represents the similarity of data, x i and i They respectively represent the values ​​of the i-th feature dimension of the two data points, and n is the total number of feature dimensions. After the similarity data is obtained, the similarity data is sent to the comparison and analysis unit.

[0064] The comparison and analysis unit compares the received data similarity with the similarity threshold;

[0065] If the data similarity is greater than or equal to the similarity threshold, the comparison and analysis unit predicts that the data to be compared have a high similarity, and generates a similarity signal. After receiving the similarity signal, the medical staff classifies the two patient data into one type of data and sends the similarity signal to the analysis and processing unit for further analysis.

[0066] If the data similarity is less than the similarity threshold, the comparison and analysis unit predicts that the data to be compared have a lower similarity, and no similarity signal is generated at this time. After not receiving the similarity signal, the medical staff does not summarize the group of data.

[0067] The main operations of the analysis and processing unit include:

[0068] When the analysis processing unit receives the similarity signal sent by the comparison analysis unit, the analysis processing unit starts, and the data with data similarity greater than or equal to the similarity threshold is regarded as similarity data. In order to ensure the quality of the similarity data, it is necessary to further analyze the similarity data, and conduct a comprehensive analysis on the similarity value of the sample population and the deviation value of the sample data;

[0069] Count the people of the same age group in the similarity data to get the proportion of similarity of the sample population, that is, the similarity value of the sample population. For example, count the proportion of the total number of medical data samples of the elderly in the similarity data to the total number of samples; count the total number of samples from the same hospital in the similarity data to get the proportion of the number of samples from the hospital to the number of similarity data, that is, get the deviation value of the sample data;

[0070] It should be noted that sample data with high similarity may come from the same hospital or data provided by the same attending physician. In order to ensure that the data can represent the regionality, the smaller the sample deviation value, the more representative the data.

[0071] The similarity value of the sample population and the deviation value of the sample data are added together, and then multiplied by the influence weight to obtain the quality coefficient of the data. In this application, the quality coefficient of the data is compared with the ratio threshold;

[0072] If the quality coefficient is ≥ the ratio threshold, the analysis and processing unit predicts that the similarity data quality is average, and an adjustment signal is generated at this time. After receiving the adjustment signal, the staff will not push and display the data to the health management agency, and will make corresponding adjustments to the data;

[0073] If the quality coefficient is less than the ratio threshold, the analysis and processing unit predicts that the similarity data quality is high, and a normal signal is generated at this time. After receiving the normal signal, the staff can visualize the data to the health management agency.

[0074] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0075] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0076] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0077] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0078] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0079] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0082] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0083] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A clinical medical data visualization processing system, characterized by: It includes an information collection unit, a data processing unit, a comparison and analysis unit, and an analysis and processing unit; Information collection unit: collects clinical medical data from various medical institutions from various platforms, preliminarily organizes the clinical medical data of each medical institution, and sends the organized data to the data processing unit; Data processing unit: after receiving the processed clinical medical data, since the data comes from different medical institutions, it is necessary to aggregate the processed clinical medical data to obtain aggregated data, calculate the similarity of the aggregated data using the cosine similarity model, and send the similarity data to the comparison and analysis unit; Comparative analysis unit: compares the similarity of the received data with the similarity threshold, and sends the comparative analysis result to the analysis processing unit. After obtaining the aggregated data, the similarity of the aggregated data is calculated by using the cosine similarity model; Represent each aggregate as a feature vector, where each dimension represents an aggregate or feature. Perform standard normalization on the aggregated data of each dimension; Use cosine similarity to calculate the similarity between two vector data. The expression is: In the formula, cos(x, y) represents the similarity of data, x i and i Respectively represent the values ​​of the i-th feature dimension of two data points, and n is the total number of feature dimensions; Compare the data similarity with the similarity threshold, If the data similarity is ≥ the similarity threshold, a similarity signal is generated; If the data similarity is less than the similarity threshold, no similarity signal is generated; Analysis and processing unit: after receiving the comparison and analysis results sent by the comparison module, further analyze the similar data, and determine the degree of data visualization by comparing the quality coefficient of the similarity data with the ratio threshold.

2. The clinical medical data visualization processing system according to claim 1, characterized in that: After receiving the pre-processed medical data, since the data comes from different medical institutions, the processed clinical medical data needs to be aggregated.

3. The clinical medical data visualization processing system according to claim 2, characterized in that: The medical record number generated each time the patient visits the hospital is marked and saved. The medical record number is used to associate the records in the relevant data table with the same medical record event. Aggregate medical data belonging to the same diagnosis and treatment event but obtained from different data tables, integrate related medical data from different data sources or data tables, and allow multiple related data rows to be merged into a single data row so as to combine them into a more complete medical data table.

4. The clinical medical data visualization processing system according to claim 1, characterized in that: Data with data similarity greater than or equal to the similarity threshold is regarded as similarity data. In order to ensure the quality of similarity data, it is necessary to further analyze the similarity data. The population in the same age period in the similarity data is counted to obtain the proportion of similarity of the sample population, that is, the similarity value of the sample population; The total number of samples from the same hospital in the similarity data is counted to obtain the proportion of the number of samples from the hospital to the number of similarity data, that is, the deviation value of the sample data; Add the similarity value of the sample population and the deviation value of the sample data, and then multiply by the influence weight to obtain the quality coefficient of the data; Compare the quality factor of the data to a ratio threshold; If the quality coefficient ≥ the ratio threshold, an adjustment signal is generated; If the quality factor is less than the ratio threshold, a normal signal is generated.

Images