Physical examination information and data association analysis system and method based on medical laboratory

Abstract

The invention provides a physical examination information and data association analysis system based on a medical laboratory. The physical examination information and data association analysis system comprises a data acquisition unit, a data annotation and arrangement unit, an association analysis unit and a visual display unit. The invention further provides a medical laboratory-based physical examination information and data association analysis method, which comprises the following steps of: acquiring physical examination personnel information and a detection result, and storing the physical examination personnel information and the detection result as original physical examination data; labeling and sorting the original physical examination data to obtain to-be-analyzed physical examination data; establishing a correlation analysis model; calculating and analyzing correlation; and the system displays a correlation analysis result. According to the invention, personnel information and detection data are collected and stored in combination with an existing medical examination laboratory management system, and on the basis of monotonicity and discontinuity characteristics of the personnel information and detection data of physical examination people, visual correlation analysis of personnel and regional personnel information and a detection item system can be realized; and the information is converted into effective and valuable health management suggestions which are simple and easy to understand, so that diseases are prevented.

Description

A Medical Laboratory-Based System and Method for Correlation Analysis of Physical Examination Information and Data Technical Field

[0001] This invention belongs to the field of data analysis, and in particular relates to a system and method for analyzing the correlation between physical examination information and data in a medical laboratory. Background Technology

[0002] Traditional chronic disease management often relies on regular follow-up visits by doctors and patient self-reporting. This approach is not only inefficient but also struggles to accurately capture changes in patients' health status, resulting in limited management effectiveness. Meanwhile, with the rapid development of medical testing technology, health check-up centers can offer an increasingly comprehensive range of tests, from routine biochemical indicators to specific disease markers. This health check-up information and test data contain a wealth of information about the health status of healthy individuals, patients, and potential patients. However, effectively combining and analyzing this information and data, and transforming it into valuable health management recommendations, has become a major challenge.

[0003] Current medical laboratory management systems are primarily used for personnel information collection and data management, but they cannot perform effective and complex calculations and analyses on the collected personnel information and test data. Report interpretation relies heavily on medical staff; the interpretation content lacks visualization, making it difficult to understand. Report interpretation varies from person to person, and errors, omissions, and incomplete information are unavoidable, increasing the workload of medical staff. Individual medical test data cannot be efficiently utilized or analyzed from multiple dimensions, hindering timely and comprehensive health maintenance. Regional personnel test data cannot be systematically and visually correlated with regional personnel information, impeding the integration and efficient utilization of regional medical testing resources and hindering regional disease prediction and early warning. Currently, most correlation analysis formulas are applicable to calculations between two factors; formulas for correlation analysis with three or more factors are severely lacking, limiting application scenarios and making them unsuitable for multi-factor (three or more factors) correlation analysis of examinee information and data. This is another reason why information and data cannot be transformed into valuable health management recommendations. Summary of the Invention

[0004] One object of the present invention is to provide a system and method for analyzing physical examination information and data in a medical laboratory, and to provide at least the advantages described below.

[0005] This invention provides a system and method for analyzing the correlation between physical examination information and data in a medical laboratory. It combines existing medical laboratory management systems to collect and store personnel information and test data. Based on the monotonous and discontinuous nature of personnel information and test data in the physical examination population, it can realize the system's visualized correlation analysis between individual and regional personnel information and test items, transforming it into effective, valuable, simple and easy-to-understand health management suggestions to prevent the occurrence of diseases.

[0006] The technical solution of the present invention is as follows: a medical laboratory-based physical examination information and data correlation analysis system, comprising: a data acquisition unit, used to acquire physical examination personnel information and test results, and store them as raw physical examination data; a data annotation and organization unit, used to annotate and organize the raw physical examination data to obtain physical examination data to be analyzed; a correlation analysis unit, used to perform correlation analysis on the physical examination data to be analyzed and obtain analysis results; and a visualization display unit, used to display the analysis results; wherein, the correlation analysis unit includes a data filtering module, a data sorting module, and a data analysis module; the data filtering module selects two parallel first target features from the physical examination data to be analyzed. The data analysis module first classifies and filters the physical examination data to be analyzed based on the first target feature to obtain preliminary screening results. The data sorting module sorts the data once based on the numerical value of the second target feature to obtain a first sorting number Ai. Then, it selects the third target feature to sort the preliminary screening results a second time to obtain a second sorting number Bi. The data filtering module classifies and filters the preliminary screening results based on the third target feature to obtain a second screening result and counts the number Ci and Di of those results that respectively possess two fourth target features C and D. The data analysis module establishes a correlation analysis model among the first target feature, the second target feature, the third target feature, and the fourth target feature. , , CN(A, B) represents the relationship between A and B, and CN(C, D) represents the relationship between C and D. The correlation between the first target feature, the second target feature, the third target feature, and the fourth target feature is calculated and analyzed based on the magnitude of CN(A, B), CN(C, D), and CN, and the analysis results are obtained.

[0007] A method for analyzing the correlation between medical laboratory examination information and data includes the following steps: acquiring information on examinees and their test results, and storing them as raw examination data; labeling and organizing the raw examination data to obtain examination data to be analyzed; selecting two parallel first target features from the examination data to be analyzed and classifying and filtering the data according to the first target features to obtain preliminary filtering results; sorting the data once according to the numerical value of the second target features to obtain a first sorting number Ai; then selecting a third target feature to sort the preliminary filtering results a second time to obtain a second sorting number Bi; classifying and filtering the preliminary filtering results according to the third target feature to obtain a second filtering result and counting the number Ci and Di of those results that respectively possess two fourth target features C and D; and establishing a correlation analysis model among the first target features, the second target features, the third target features, and the fourth target features. , , CN(A, B) represents the relationship between A and B, and CN(C, D) represents the relationship between C and D. The correlation between the first target feature, the second target feature, the third target feature, and the fourth target feature is calculated and analyzed based on the magnitude of CN(A, B), CN(C, D), and CN, and the analysis results are obtained.

[0008] Preferably, in the method for analyzing the correlation between medical laboratory examination information and data, the process of labeling and organizing the original examination data to obtain the examination data to be analyzed includes the following steps: performing data desensitization on the original examination data; then cleaning and standardizing the data; and finally labeling and organizing the data.

[0009] Preferably, in the aforementioned method for analyzing physical examination information and data based on medical laboratories, two of the first target features are gender, which are the same as the two fourth target features; the second target feature is the test result, and the third target feature is age. Specifically, the method includes the following steps: Label 1 represents female, 0 represents male, and categories are formed according to gender, with labels 0 grouped into one category and labels 1 grouped into another; A represents the test result, B represents the age of the examinee for that test; Ai represents the sequence number of the test result, Bi represents the sequence number of the examinee's age for that test; (Ai-Bi) represents the difference between the sequence number of the test result and the corresponding sequence number of the examinee's age; n is the total number of people participating in the test; i=1 indicates the first in the sequence. The sum of the average of the subtractions between the sequence number of the test results for all men and women in the database and their corresponding age sequence numbers; This refers to the relationship between the test results and age, with a value range of [-1, 1]; Ci and Di represent the number of people labeled 0 and 1 in the same age group, respectively; i is the sorting number. This represents the difference between the number of men and women in the same age group. This is the sum of the differences between the number of men and women in different age groups; CN(C, D) represents the difference in the number of men and women in different age groups, and its value ranges from [-1, 1]. CN represents the correlation between the item and age and gender for the same item, with a value range of [-2, 2].

[0010] Preferably, in the aforementioned method for analyzing physical examination information and data based on medical laboratories, the two first target features are the test results of item 1 and item 2; the second target feature is the test result; the third target feature is age; and the two fourth target features are gender. Specifically, the method includes the following steps: A represents the test result of item 1; B represents the test result of item 2; Ai represents the sequence number of different individuals' test results of item 1 arranged from highest to lowest; Bi represents the sequence number of different examinees' test results of item 2 arranged from highest to lowest; (Ai-Bi) represents the difference between the sequence number of the same individual's test result of item 1 and its corresponding sequence number of the test result of item 2; i=1 represents the first item in the sequence of item 1, and so on, with n being the last item, which is the total number of people participating in the test for that item. The sum of the average values ​​of the subtraction between the sequence numbers of the test results for item 1 and the test results for item 2 in the database; CN(A, B) represents the relationship between the test results of item 1 and item 2, with a value range of [-1, 1]. Label 1 represents female gender, and 0 represents male gender. Ci and Di represent the number of people labeled 0 and 1 in the same age group, respectively, and are arranged in descending order of age. i is the sorting number. This represents the difference between the number of males and females in the same age group; the ages of the examinees of different genders are sorted from largest to smallest, with the oldest being sorted higher and the youngest being sorted lower. i=1 represents the first in the sort, and so on, with n being the last, which is the total number of people participating in the project. This is the sum of the differences between the number of men and women in different age groups; CN(C, D) represents the difference in the number of men and women in different age groups, and its value ranges from [-1, 1]. CN represents the correlation between different items and with gender and age, with a value range of [-2, 2].

[0011] Combined with system computation, it can be applied to multi-factor (more than 3 factors) correlation analysis. The variables can be continuous or non-continuous data, and the variables can also have a monotonic relationship. The analysis results can be visualized by the system.

[0012] The present invention has the following beneficial effects: (1) Visual analysis of the correlation between various items, integrating all test items, reducing human error and omissions, and simplifying the workload of medical staff and optimizing test reports through system software, making the test report content easier for the test subjects to understand; (2) Complex calculation and precise diversity analysis of data, which can realize multi-angle analysis of different data of the same person while linking personnel information, and transform information and data into valuable health management suggestions; (3) Through the correlation analysis of information and data, data is linked with personnel information, realizing the effective analysis and display of local personnel test data, and providing a basis for the monitoring of local health information. (4) The system software provides effective evidence; (5) The system software analyzes the detection data in real time from multiple dimensions, which is more comprehensive, optimizes medical resources, reduces the probability of diagnostic errors, and enhances the timeliness of the detection results; (6) It lays the foundation for the construction of models for disease prevention and early warning for individuals and regions, as well as the supervision of regional medical detection data; (7) The management and multi-dimensional analysis of data and information are conducive to the integration of regional medical resources and the systematic collection and inheritance of medical diagnostic experience, realizing the online visualization sharing and display of regional medical diagnostic experience; (8) The calculation formula of this invention can be continuous or discontinuous data, and the variables can also be monotonic, with a wide range of applications and no restrictions on application scenarios. It can assist in the correlation analysis of information and data in various scenarios.

[0013] Other advantages, objectives and features of the present invention will become apparent in part from the following description, and in part from those skilled in the art through study and practice of the invention. Attached Figure Description

[0014] Figure 1 is a flowchart of the method for analyzing physical examination information and data based on medical laboratory provided by the present invention; Figure 2 is a flowchart of the analysis process of one embodiment of the method for analyzing physical examination information and data based on medical laboratory provided by the present invention; Figure 3 is a flowchart of the analysis process of another embodiment of the method for analyzing physical examination information and data based on medical laboratory provided by the present invention. Detailed Implementation

[0015] The present invention will be further described in detail below with reference to embodiments, so that those skilled in the art can implement it based on the description.

[0016] It should be understood that terms such as “having,” “comprising,” and “including” as used herein do not imply the presence or addition of one or more other elements or combinations thereof.

[0017] Existing medical laboratory information management systems can only collect information and manage basic data, but cannot perform correlation and precise analysis of collected personnel information and test data. The interpretation of test reports in existing systems mainly relies on medical staff, and the interpretation content cannot be visualized, making it difficult to understand. Individual and regional test data cannot be systematically and visually correlated with regional personnel information, which is not conducive to the integration and efficient utilization of regional medical testing resources, nor can it achieve disease development prediction and early warning. Currently, most correlation analysis calculation formulas are applicable to calculations between two factors, and there is a serious shortage of correlation analysis formulas for three or more factors. Moreover, the application scenarios are limited, and they are not suitable for multi-factor (three or more factors) correlation analysis of test personnel information and data.

[0018] This invention pushes structured data (such as blood routine, tumor markers and other indicators) to the analysis engine through a microservice interface; the system analysis engine calls statistical analysis software, applies physical examination information and data correlation analysis calculation formulas to perform multi-factor analysis on the target object; the system visualization rendering layer is based on the system front-end framework to transform the analysis results into various types of charts.

[0019] This invention provides a medical laboratory-based physical examination information and data correlation analysis system, comprising: a data acquisition unit for acquiring physical examination personnel information and test results, and storing them as raw physical examination data; a data annotation and organization unit for annotating and organizing the raw physical examination data to obtain physical examination data to be analyzed; a correlation analysis unit for performing correlation analysis on the physical examination data to be analyzed and obtaining analysis results; and a visualization display unit for displaying the analysis results; wherein, the correlation analysis unit includes a data filtering module, a data sorting module, and a data analysis module; the data filtering module selects two parallel first target features from the physical examination data to be analyzed and... The data to be analyzed is classified and filtered according to the first target feature to obtain preliminary filtering results. The data sorting module sorts the data once according to the numerical value of the second target feature to obtain a first sorting number Ai. Then, the preliminary filtering results are sorted a second time according to the third target feature to obtain a second sorting number Bi. The data filtering module classifies and filters the preliminary filtering results according to the third target feature to obtain a second filtering result and counts the number Ci and Di of those results that respectively possess two fourth target features C and D. The data analysis module establishes a correlation analysis model among the first target feature, the second target feature, the third target feature, and the fourth target feature. , , CN(A, B) represents the relationship between A and B, and CN(C, D) represents the relationship between C and D. The correlation between the first target feature, the second target feature, the third target feature, and the fourth target feature is calculated and analyzed based on the magnitude of CN(A, B), CN(C, D), and CN, and the analysis results are obtained.

[0020] As shown in Figure 1, the present invention provides a method for analyzing physical examination information and data association based on medical laboratory, including the following steps: (1) Systematic access to laboratory information and data: The standardized system interface of the laboratory physical examination information and data association analysis system supports seamless connection and data synchronization of personnel information and test results, as well as background storage; a standardized data interface is designed to access the collected personnel information and test results through the data access layer of the laboratory physical examination information and data association analysis system, and store them in the background database, while triggering a data desensitization mechanism (such as hiding sensitive information such as personnel ID number and name); a structured storage scheme for routine physical examination data and special test item data is designed and implemented, including data table design, index optimization, etc.

[0021] (2) Processing and conversion of laboratory information and data: Based on the goal of laboratory physical examination information and data association analysis, the system labels and organizes personnel information and test results; the system data processing layer cleans the raw data (removes duplicate values ​​and fills in missing items) and standardizes and converts it (unifies indicator units and formats), and pushes structured data (such as blood routine, tumor markers and other indicators) to the analysis engine through the microservice interface; (3) The system applies the calculation formula of laboratory physical examination information and data association analysis, and displays the system graphically based on the result report. The system analysis engine calls the statistical analysis software to label and organize the information and data of the examinees, applies the calculation formula of physical examination information and data association analysis to perform multi-factor analysis on the target object, and the system visualization rendering layer transforms the analysis results into multiple types of charts based on the system front-end framework. At the same time, it supports the overall overview of the large screen display, the personalized filtering charts of the query page, and the export of the report of the statistical page, realizing the multi-scenario application of data visualization.

[0022] Specifically, the process is as follows: Information on examinees and their test results are obtained and stored as raw physical examination data; the raw physical examination data is labeled and organized to obtain physical examination data to be analyzed; two parallel first target features are selected from the physical examination data to be analyzed, and the data is classified and filtered according to the first target features to obtain preliminary filtering results; the data is sorted once according to the numerical value of the second target feature to obtain a first sorting number Ai; then, a third target feature is selected to sort the preliminary filtering results a second time to obtain a second sorting number Bi; the preliminary filtering results are classified and filtered according to the third target feature to obtain a second filtering result, and the number of results Ci and Di that respectively possess two fourth target features C and D is counted; a correlation analysis model is established between the first target feature, the second target feature, the third target feature, and the fourth target feature. , , CN(A, B) represents the relationship between A and B, and CN(C, D) represents the relationship between C and D. The correlation between the first target feature, the second target feature, the third target feature, and the fourth target feature is calculated and analyzed based on the magnitude of CN(A, B), CN(C, D), and CN, and the analysis results are obtained.

[0023] Figure 2 shows the correlation analysis between the same item and age and gender, which includes the following steps: The correlation analysis formula is as follows: ;Formula 1: Formula 1: Label 1 represents female, 0 represents male. Categorize by gender, with those labeled 0 grouped into one category and those labeled 1 into another. Based on the number of people labeled 1, sort the test results of items labeled 0 by the age of the examinees from highest to lowest; that is, the larger the value of the test result / age, the higher the sorting sequence number. Following the sequence number labeled 0, sort the test results of items labeled 1 by the age of the examinees from highest to lowest; that is, the larger the value of the test result / age, the higher the sorting sequence number. When A represents the test result, B represents the age of the examinee for that item; Ai represents the sequence number of the test result, and Bi represents the sequence number of the examinee's age for that item; (Ai-Bi) represents the difference between the sequence number of the test result and the corresponding sequence number of the examinee's age. For example: the average of the highest sequence number of a male test result minus the sequence number of the corresponding examinee's age; Formula 2: , where n is the total number of people participating in the project testing, that is, the first index value of the gender ranking of the test results for the same project. i=1 indicates the first in the ranking. , is the sum of the average of the subtraction between the sequence number of the test result for all men and women in the database and the corresponding age sequence number.

[0024] Formula 3: CN(A, B) represents the relationship between A and B, that is, the relationship between the test result and age. The value range is [-1, 1]. The closer the CN(A, B) result is to 1, the higher the test result value and the older the age; the closer the CN(A, B) result is to -1, the higher the test result value and the younger the age.

[0025] Formula 4: Ci and Di represent the number of people marked with 0 and 1 respectively in the same age group. The data is segmented by age and arranged from oldest to youngest. i is the sorting number. This represents the difference between the number of men and women in the same age group.

[0026] Formula 5: The participants' ages are sorted from oldest to youngest, with older participants ranked higher and younger participants ranked lower. i=1 represents the first participant in the sort, and so on, with n representing the last participant, which is the total number of participants in the project. This represents the sum of the differences between the number of men and women in different age groups.

[0027] Formula 6: CN(C,D) represents the relationship between C and D, i.e., the difference in the number of men and women in different age groups. The value range is [-1,1]. The closer the CN(C,D) result is to 1, the more men there are in different age groups; the closer the CN(C,D) result is to -1, the more women there are in different age groups; a CN(C,D) result of 0 indicates that the number of men and women is equal in different age groups.

[0028] formula CN represents the correlation between the item and age and gender, with a value range of [-2, 2]. The closer the CN result is to 2, the higher the item's test result value, the older the age, and the more males and fewer females in different age groups. The closer the CN result is to -2, the higher the item's test result value, the younger the age, and the fewer males and more females in different age groups. The closer the CN result is to 1, the higher the item's test result value, the older the age, and the closer the number of males and females in different age groups. The closer the CN result is to -1, the higher the item's test result value, the younger the age, and the closer the number of males and females in different age groups.

[0029] As shown in Figure 3, the correlation analysis between different items and with gender and age includes the following steps: The correlation analysis formula is as follows: , Formula 1: Formula 1: A represents the test result of item 1, and B represents the test result of item 2; Ai represents the sequence number of different individuals' test results of item 1 arranged from high to low, and Bi represents the sequence number of different individuals' test results of item 2 arranged from high to low; (Ai-Bi) represents the difference between the sequence number of an individual's test result of item 1 and its corresponding sequence number of test result of item 2. For example: Zhang San's test result sequence number minus the average of his corresponding test result sequence number of item 2.

[0030] Formula 2: i=1 represents the first item in the sequence of items 1, and so on, with n being the last item, which is the total number of people involved in the testing of that item. , is the sum of the average of the subtraction between the sequence numbers of the detection results of item 1 and the detection results of item 2 in the database.

[0031] Formula 3: CN(A, B) represents the relationship between A and B, that is, the relationship between the detection results of item 1 and item 2. The value range is [-1, 1]. The closer the CN(A, B) result is to 1, the greater the positive correlation between item 1 and item 2; the closer the CN(A, B) result is to -1, the greater the negative correlation between item 1 and item 2.

[0032] Formula 4: The label 1 represents female and 0 represents male. Ci and Di represent the number of people labeled 0 and 1 in the same age group, respectively. The data is segmented by age and sorted from oldest to youngest. i is the sorting number. This represents the difference between the number of men and women in the same age group.

[0033] Formula 5: The ages of the participants, regardless of gender, are sorted from oldest to youngest, with older participants ranked higher and younger participants ranked lower. i=1 represents the first participant in the sort, and so on, with n representing the last participant, which is the total number of participants in this project. This represents the sum of the differences between the number of men and women in different age groups.

[0034] Formula 6: CN(C, D) represents the relationship between C and D, i.e., the difference in the number of men and women in different age groups. The value range is [-1, 1]. The closer the CN(C, D) result is to 1, the more men there are in different age groups; the closer the CN(C, D) result is to -1, the more women there are in different age groups; a CN(C, D) result of 0 indicates that the number of men and women is equal in different age groups.

[0035] formula The CN value represents the correlation between different items and with gender and age, ranging from -2 to 2. The closer the CN value is to 2, the stronger the positive correlation between the two items, and the more males and fewer females are in different age groups. The closer the CN value is to -2, the stronger the negative correlation between the two items, and the fewer males and more females are in different age groups. The closer the CN value is to 1, the stronger the positive correlation between the two items, and the closer the number of males and females is in different age groups. The closer the CN value is to -1, the stronger the negative correlation between the two items, and the closer the number of males and females is in different age groups.

[0036] The medical laboratory physical examination information and data correlation analysis method provided by this invention is combined with the existing medical testing laboratory management system. Through system calculation, it completes the correlation analysis of a large amount of physical examination personnel information and test results, and visualizes the analysis results.

[0037] This invention can perform batch analysis on the correlation between three factors stored in the system: gender and age of personnel and project test results, and finally display the results in a visual graphic through the system.

[0038] This invention performs batch analysis on the correlation between the detection results of different items stored in the system and four factors: gender and age of the personnel, and finally displays the results in a visual graphic through the system.

[0039] This invention can perform correlation analysis between personnel information and detection data.

[0040] This invention can perform correlation analysis of three or more factors (multi-factor) between personnel information and detection data.

[0041] This invention can be applied to multifactor correlation analysis.

[0042] This invention can be applied to multifactor correlation analysis, where the variables can be continuous or non-continuous data, and the variables can also have a monotonic relationship.

[0043] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details.

Claims

1. A medical laboratory-based physical examination information and data correlation analysis system, characterized in that, include: The data acquisition unit is used to acquire information about the examinees and the test results, and to store them as raw physical examination data. The system comprises a data annotation and organization unit for annotating and organizing the original physical examination data to obtain the physical examination data to be analyzed; a correlation analysis unit for performing correlation analysis on the physical examination data to be analyzed and obtaining the analysis results; and a visualization unit for displaying the analysis results. The correlation analysis unit includes a data filtering module, a data sorting module, and a data analysis module. The data filtering module selects two parallel first target features from the physical examination data to be analyzed and classifies and filters the data according to the first target features to obtain preliminary filtering results. The data sorting module sorts the data according to the numerical value of the second target feature to obtain a first sorting number Ai, and then selects a third target feature to sort the preliminary filtering results a second time to obtain a second sorting number Bi. The data filtering module classifies and filters the preliminary filtering results according to the third target feature to obtain a second filtering result and counts the number Ci and Di of each of the results possessing two fourth target features C and D respectively. The data analysis module establishes a correlation analysis model between the first target feature, the second target feature, the third target feature, and the fourth target feature. ， ， CN(A, B) represents the relationship between A and B, and CN(C, D) represents the relationship between C and D. The correlation between the first target feature, the second target feature, the third target feature, and the fourth target feature is calculated and analyzed based on the magnitudes of CN(A, B), CN(C, D), and CN, to obtain the analysis results.

2. A method for correlation analysis of physical examination information and data from medical laboratories, characterized in that, Includes the following steps: Information on examinees and test results are obtained and stored as raw physical examination data; the raw physical examination data is labeled and organized to obtain the physical examination data to be analyzed. Two parallel first target features are selected from the physical examination data to be analyzed, and the data is classified and filtered according to the first target features to obtain preliminary screening results. The data is then sorted first according to the numerical value of the second target feature to obtain a first sorting number Ai. A third target feature is then selected to sort the preliminary screening results a second time to obtain a second sorting number Bi. The preliminary screening results are then classified and filtered according to the third target feature to obtain a second screening result, and the number of results Ci and Di that respectively possess two fourth target features C and D is counted. A correlation analysis model is established among the first target feature, the second target feature, the third target feature, and the fourth target feature. ， ， CN(A, B) represents the relationship between A and B, and CN(C, D) represents the relationship between C and D. The correlation between the first target feature, the second target feature, the third target feature, and the fourth target feature is calculated and analyzed based on the magnitudes of CN(A, B), CN(C, D), and CN, to obtain the analysis results.

3. The method for correlation analysis of physical examination information and data based on medical laboratories as described in claim 2, characterized in that, The process of labeling and organizing the original physical examination data to obtain the physical examination data to be analyzed includes the following steps: data anonymization processing of the original physical examination data; cleaning and standardization transformation; and labeling and organization.

4. The method for correlation analysis of physical examination information and data based on medical laboratories as described in claim 3, characterized in that, Two of the first target features are gender, which is the same as the two fourth target features; the second target feature is the detection result; and the third target feature is age. Specifically, the following steps are included: Label 1 represents female, and 0 represents male; categories are formed according to gender, with labels 0 grouped into one category and labels 1 grouped into another; A represents the project detection result, and B represents the age of the person being tested for that project; Ai represents the sequence number of the project detection result, and Bi represents the sequence number of the age of the person being tested for that project; (Ai-Bi) represents the difference between the sequence number of the project detection result and the corresponding sequence number of the age of the person being tested; n is the total number of people participating in the project detection; i=1 indicates the first in the sequence. The sum of the average of the subtractions between the sequence number of the test results for all men and women in the database and their corresponding age sequence numbers; This refers to the relationship between the test results and age, with a value range of [-1, 1]; Ci and Di represent the number of people labeled 0 and 1 in the same age group, respectively; i is the sorting number. This represents the difference between the number of men and women in the same age group. This is the sum of the differences between the number of men and women in different age groups; CN(C, D) represents the difference in the number of men and women in different age groups, with a value range of [-1, 1]. CN represents the correlation between the item and age and gender for the same item, with a value range of [-2, 2].

5. The method for correlation analysis of physical examination information and data based on medical laboratories as described in claim 3, characterized in that, The first two target features are the test results of item 1 and item 2; the second target feature is the test result; the third target feature is age; and the two fourth target features are gender. Specifically, the process includes the following steps: A represents the test result of item 1, and B represents the test result of item 2; Ai represents the sequence number of different individuals' test results of item 1 arranged from highest to lowest; Bi represents the sequence number of different individuals' test results of item 2 arranged from highest to lowest; (Ai-Bi) represents the difference between the sequence number of the individual's test result of item 1 and its corresponding sequence number of the test result of item 2; i=1 represents the first item in the item 1 arrangement, and so on, with n being the last item, which is the total number of people participating in the item test. , is the sum of the average of the subtraction of the sequence numbers of the test results of item 1 and item 2 in the database; CN(A, B) represents the relationship between the test results of item 1 and item 2, with a value range of [-1, 1]. Label 1 represents female and 0 represents male. Ci and Di represent the number of people labeled 0 and 1 in the same age group, respectively, and are arranged in descending order of age. i is the sorting number. This represents the difference between the number of males and females in the same age group; the ages of the examinees of different genders are sorted from largest to smallest, with the oldest being sorted higher and the youngest being sorted lower. i=1 represents the first in the sort, and so on, with n being the last, which is the total number of people participating in the project. This is the sum of the differences between the number of men and women in different age groups; CN(C, D) represents the difference in the number of men and women in different age groups, and its value ranges from [-1, 1]. CN represents the correlation between different items and with gender and age, with a value range of [-2, 2].

Images