Medical examination item reference interval suitability evaluation system

Abstract

The invention discloses a medical examination item reference interval suitability evaluation system. According to the medical examination item reference interval suitability evaluation system, through a preset reference interval and a reference interval obtained through calculation based on a set of physical examination data, the abnormal rate of the reference interval and the abnormal grade distribution of an examination result are evaluated, and the consistency between the preset reference interval and a literature reference interval of an examination item is also evaluated. And generating a suitability evaluation result of the preset reference interval of each test item. Therefore, the suitability evaluation system for the reference interval of the medical examination item can evaluate the suitability of the preset reference interval, and is of great significance to value medical treatment. The data extracted by the medical test item reference interval suitability evaluation system is from the test data of the real world, so that extra testees do not need to be recruited for detection, and the cost of evaluating the suitability of the reference interval can be greatly reduced.

Description

Technical Field

[0001] The present application relates to the field of reference interval assessment, and in particular to a reference interval suitability assessment system for medical test items. Background Art

[0002] The reference intervals of various test items used in medical laboratories are mainly derived from reagent instructions, health industry standards, authoritative literature or textbooks, etc. Due to differences in socioeconomic levels, regional living environments, and eating habits, the existing reference intervals of various test items may not be suitable for the population served by the laboratory. When the reference interval is too wide, it will lead to delays in the treatment of some patients. When the reference interval is too narrow, it will cause excessive examinations of patients and waste medical resources. Therefore, regular evaluation of whether the reference interval is appropriate is of great significance to value-based medicine.

[0003] At present, the suitability assessment of the reference interval is as follows: screen at least 20 or 60 qualified reference individuals, and conduct tests according to standard operating procedures to obtain preliminary test results; check and eliminate outliers in the preliminary test results; when the number of reference individuals in the preset reference interval after eliminating outliers accounts for ≥90%, the preset reference interval is deemed to have been verified; when the preset reference interval is verified, it is considered that the preset reference interval is appropriate.

[0004] However, the above-mentioned suitability assessment method for preset reference intervals is costly, cumbersome, and has a small amount of data. There is a bias in the selection of reference individuals, and it is not combined with real-world inspection big data or the latest research literature progress. The reliability of the assessment results is poor. There is an urgent need for new assessment schemes that can quickly and accurately assess the suitability of reference intervals. Summary of the invention

[0005] One advantage of the present application is that it provides a medical test item reference interval suitability assessment system, wherein the medical test item reference interval suitability assessment system can assess the suitability of a preset reference interval, which is of great significance to value-added medicine.

[0006] One advantage of the present application is that it provides a reference interval suitability assessment system for medical test items, wherein the data selected by the reference interval suitability assessment system for medical test items comes from real-world test data, and does not require additional recruitment of subjects for testing, which can greatly reduce the cost of assessing the suitability of reference intervals.

[0007] An advantage of the present application is that it provides a system for evaluating the suitability of reference intervals for medical test items, wherein the system for evaluating the suitability of reference intervals for medical test items can also evaluate the suitability of reference intervals in literature.

[0008] According to one aspect of the present application, a medical test item reference interval suitability assessment system is provided, which includes: A preset reference interval extraction module, used to extract a preset reference interval of at least one test item from a test item reference interval database; A physical examination data collection and analysis module, used to obtain a set of physical examination data and determine the reconstructed reference interval of the test item using the EP28 non-parametric method; A test data collection module, used to extract test data sets of the test items within a predetermined time period from a laboratory information system; A data grouping module, used for segmenting the test data set of the test items according to the three types of medical examination, outpatient and hospitalization to obtain a first test data subset, a second test data subset and a third test data subset; A reference interval abnormality rate evaluation module, used to respectively calculate the upper and lower abnormality rates of the first test data subset, the second test data subset, and the third test data subset relative to the preset reference interval and the reconstructed reference interval to obtain a reference interval abnormality rate evaluation result; The suitability management module is used to generate a suitability assessment result of the test item based on the reference interval abnormality rate assessment result.

[0009] In the medical test item reference interval suitability assessment system according to the present application, the reference interval abnormality rate assessment module includes: A preset reference interval abnormality rate evaluation unit, used to respectively calculate the upper limit abnormality rate of the preset reference interval and the lower limit abnormality rate of the preset reference interval corresponding to the first test data subset, the second test data subset and the third test data subset to obtain a preset reference interval abnormality rate evaluation result; The reconstructed reference interval abnormality rate assessment unit is used to respectively calculate the upper limit abnormality rate and the lower limit abnormality rate of the reconstructed reference interval corresponding to the first test data subset, the second test data subset and the third test data subset to obtain the reconstructed reference interval abnormality rate assessment result.

[0010] In the medical test item reference interval suitability assessment system according to the present application, the suitability management module includes: A consistency evaluation unit, configured to perform consistency evaluation analysis on the preset reference interval abnormality rate evaluation result and the reconstructed reference interval abnormality rate evaluation result to obtain a consistency evaluation result; The suitability assessment result determination unit is used to generate a suitability assessment result of the inspection item based on the consistency assessment result and the preset and reconstructed reference interval abnormality rate assessment results.

[0011] In the medical test item reference interval suitability assessment system according to the present application, the consistency assessment unit is further used to: Calculating the difference between the upper limit abnormality rate of the reconstructed reference interval and the upper limit abnormality rate of the preset reference interval and calculating the difference between the lower limit abnormality rate of the reconstructed reference interval and the lower limit abnormality rate of the preset reference interval to obtain a first difference and a second difference; The consistency evaluation result is generated based on a comparison between the first difference degree and the second difference degree and a preset threshold.

[0012] In the reference interval suitability assessment system for medical test items described in the present application, the consistency assessment unit is further used to: calculate the ratio between the upper limit abnormality rate of the preset reference interval and the lower limit abnormality rate of the reference interval of any two test data subsets among the first test data subset, the second test data subset and the third test data subset to obtain multiple abnormality rate ratios; based on the comparison between each abnormality rate ratio among the multiple abnormality rate ratios and the preset threshold value, generate the consistency assessment result.

[0013] In the medical test item reference interval suitability assessment system described in the present application, it also includes: an abnormality level judgment standard determination module, which is used to determine the abnormality level judgment standard based on the set of physical examination data; an abnormality level calculation module, which is used to analyze the second test data subset and the third test data subset based on the abnormality level standard to obtain the abnormality level distribution of outpatient test results and the abnormality level distribution of inpatient test results.

[0014] In the medical test item reference interval suitability assessment system according to the present application, the abnormal level judgment standard determination module is further used to: Determine the upper and lower limits of the normal level based on the level division condition that the set distribution of the physical examination data is greater than 2.5% or less than 97.5% on both sides or the level division condition that the set distribution of the physical examination data is less than 95% on one side; Determine the upper and lower limits of the mild level based on the level division condition that the set distribution of the physical examination data is greater than 1.5% and less than 2.5% on both sides or greater than or equal to 97.5% and less than 98.5% on one side, or the level division condition that the set distribution of the physical examination data is greater than or equal to 95% and less than 97% on one side; Determine the upper and lower limits of the moderate level based on the level division condition that the set distribution of the physical examination data is greater than 1.0% and less than or equal to 1.5% on both sides or greater than or equal to 98.5% and less than 99.0% on one side, or the level division condition that the set distribution of the physical examination data is greater than or equal to 97.0% and less than 98.0% on one side; Determine the upper and lower limits of the severe level based on the level classification condition that the set distribution of the physical examination data is greater than 0.5% and less than or equal to 1.0% on both sides or greater than or equal to 99.0% and less than 99.5% on one side, or the level classification condition that the set distribution of the physical examination data is greater than or equal to 98.0% and less than 99.0% on one side; The upper and lower limits of the extreme level are determined based on the level division condition that the set distribution of the physical examination data is less than or equal to 0.5% or greater than or equal to 99.5% on both sides or the level division condition that the set distribution of the physical examination data is greater than or equal to 99.0% on one side.

[0015] In the medical test item reference interval suitability assessment system described in the present application, it also includes: a reference collection module for searching references; a reference grade assessment module for performing quality assessment on references to obtain reference quality grade assessment results; and a reference reference interval management module for extracting and managing relevant data on the recommended reference interval of the test item from the reference based on a large language model.

[0016] In the medical test item reference interval suitability assessment system according to the present application, the reference document reference interval management module is further used to: Calculating the bias ratio between the recommended reference interval of the test item and the reconstructed reference interval; When the bias ratio is greater than a preset threshold, it is determined that the consistency between the recommended reference interval of the test item and the reconstructed reference interval of the test item does not meet the preset requirement; When the bias ratio is less than or equal to a preset threshold, it is determined that the consistency between the recommended reference interval of the test item and the reconstructed reference interval of the test item meets the preset requirement.

[0017] Further objectives and advantages of the present application will be fully reflected through understanding of the following description and drawings.

[0018] These and other objects, features and advantages of the present application are fully reflected in the following detailed description, drawings and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components.

[0020] Figure 1It is a block diagram of a system for evaluating the suitability of reference intervals for medical test items according to an embodiment of the present application.

[0021] Figure 2 This is a schematic diagram of an interface for calculating the EP28 non-parametric method of the medical test item reference interval suitability assessment system according to an embodiment of the present application.

[0022] Figure 3 The figure illustrates an interface schematic diagram of a preset reference interval of a reference interval suitability assessment system for medical test items according to an embodiment of the present application.

[0023] Figure 4 The diagram illustrates another interface schematic diagram of a preset reference interval of the medical test item reference interval suitability assessment system according to an embodiment of the present application.

[0024] Figure 5 The figure illustrates a block diagram of an adaptability management module in a medical test item reference interval suitability assessment system according to an embodiment of the present application.

[0025] Figure 6 The figure illustrates an interface schematic diagram of abnormality rate level calculation of the reference interval suitability assessment system for medical test items according to an embodiment of the present application.

[0026] Figure 7 The diagram illustrates another interface schematic diagram of abnormality rate level calculation of the medical test item reference interval suitability assessment system according to an embodiment of the present application.

[0027] Figure 8 The figure illustrates a schematic interface diagram for determining abnormal grade standards of a reference interval suitability assessment system for medical test items according to an embodiment of the present application.

[0028] Fig. 9 The diagram illustrates another interface schematic diagram for determining abnormality grade standards of the medical test item reference interval suitability assessment system according to an embodiment of the present application.

[0029] Fig.10 The figure illustrates an interface schematic diagram of a reference interval literature list of a reference interval suitability assessment system for medical test items according to an embodiment of the present application.

[0030] Fig.11 The diagram illustrates another interface schematic diagram of reference interval literature content management of the reference interval suitability assessment system for medical test items according to an embodiment of the present application.

[0031] Fig.12 The diagram illustrates a schematic interface diagram of reference interval literature comparison of a reference interval suitability assessment system for medical test items according to an embodiment of the present application.

[0032] Fig.13 The diagram illustrates another interface schematic diagram of reference interval literature comparison of the reference interval suitability assessment system for medical test items according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0034] It is understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "one" cannot be understood as a limitation on the number. "Multiple" means greater than or equal to two.

[0035] Although ordinals such as "first," "second," and the like will be used to describe various components, those components are not limited herein. The term is used only to distinguish one component from another. For example, a first component may be referred to as a second component, and likewise, a second component may be referred to as a first component without departing from the teachings of the present application. The term "and / or" as used herein includes any and all combinations of one or more associated listed items.

[0036] The terms used herein are only used for the purpose of describing various embodiments and are not intended to be limiting. As used herein, the singular form is intended to include the plural form, unless the context clearly indicates an exception. It will also be understood that the terms "including" and / or "having" when used in this specification specify the presence of the described features, numbers, operations, components, elements, or combinations thereof, without excluding the presence or addition of one or more other features, numbers, operations, components, elements, or combinations thereof.

[0037] like Figures 1 to 13 As shown, a medical test item reference interval suitability assessment system according to an embodiment of the present application is illustrated. The medical test item reference interval suitability assessment system 1000 can assess the suitability of a preset reference interval, which is of great significance to value-based medicine. The data extracted by the medical test item reference interval suitability assessment system 1000 comes from real-world test data, and no additional subjects need to be recruited for testing, which can greatly reduce the cost of assessing the suitability of reference intervals. The medical test item reference interval suitability assessment system 1000 can also assess the suitability of reference intervals in the literature.

[0038] Specifically, Figure 1As shown, the medical test item reference interval suitability assessment system 1000 includes a preset reference interval extraction module 10, a physical examination data collection and analysis module 20, a test data collection module 30, a data grouping module 40, a reference interval abnormality rate assessment module 50 and a suitability management module 60, wherein the preset reference interval extraction module 10 is used to extract at least one preset reference interval of a test item from a test item reference interval database; the physical examination data collection and analysis module 20 is used to obtain a set of physical examination data and determine the reconstructed reference interval of the test item using the EP28 non-parametric method; the test data collection module 30 is used to extract the test items within a predetermined time period from the laboratory information system The test data set of the project; the data grouping module 40 is used to divide the test data set of the test project according to the three types of medical examinations, outpatient clinics and inpatient clinics to obtain a first test data subset, a second test data subset and a third test data subset; the reference interval abnormality rate evaluation module 50 is used to respectively calculate the upper and lower abnormality rates of the first test data subset, the second test data subset and the third test data subset relative to the preset reference interval and the reconstructed reference interval to obtain a reference interval abnormality rate evaluation result; the suitability management module 60 is used to generate a suitability evaluation result of the test project based on the reference interval abnormality rate evaluation result.

[0039] Specifically, during the operation of the preset reference interval extraction module, the preset reference interval of at least one test item is extracted from the test item reference interval database by the preset reference interval extraction module 10. The preset reference interval of at least one test item includes but is not limited to the preset reference interval of platelet count, the preset reference interval of total protein, the preset reference interval of albumin, the preset reference interval of alanine aminotransferase, the preset reference interval of aspartate aminotransferase, etc.

[0040] It is worth mentioning that the preset reference intervals of each of the test items can also be divided into multiple groups. For example, the preset reference intervals of the platelet count test items include the preset reference intervals of the platelet count test items of the first group, the preset reference intervals of the platelet count test items of the second group, the preset reference intervals of the platelet count test items of the third group, the preset reference intervals of the platelet count test items of the fourth group, the preset reference intervals of the platelet count test items of the fifth group, the preset reference intervals of the platelet count test items of the sixth group and the preset reference intervals of more groups of platelet count test items. In a specific example, the preset reference interval of each group corresponds to a group of test subjects, and the test subjects are grouped according to age and gender; for example, the preset reference interval of the platelet count test item of the first group is the preset reference interval of the platelet count test item of the test subject is a female group of 6 months to less than 1 year old; the preset reference interval of the platelet count test item of the second group is the preset reference interval of the platelet count test item of the test subject is a female group of 1 year old to less than 2 years old; the preset reference interval of the platelet count test item of the third group is the preset reference interval of the platelet count test item of the test subject is a female group of 2 years old to less than 6 years old. Preset reference interval; the preset reference interval of the platelet count test item of the fourth group is the preset reference interval of the platelet count test item of the group of female 6-<12 years old; the preset reference interval of the platelet count test item of the fifth group is the preset reference interval of the platelet count test item of the group of female 12-<18 years old; the preset reference interval of the platelet count test item of the sixth group is the preset reference interval of the platelet count test item of the group of female 18-<53 years old; the preset reference interval of the platelet count test item of other groups is the test object corresponding to other groups. It is also worth mentioning that in other examples, the data in the test item reference interval database can be grouped according to the test object first, and then grouped according to the test item type.

[0041] During the operation of the physical examination data acquisition and analysis module 20, it first obtains a set of physical examination data, and processes the set of physical examination data using the EP28 non-parametric method to determine a reconstructed reference interval for at least one test item, such as Figure 2As shown. In addition to the EP28 non-parametric method, other suitable methods for establishing reference intervals such as the EP28 parametric method, refineR, TMC, Kosmic, etc. may also be used. Those skilled in the art should be aware that the EP28 non-parametric method includes the exclusion of abnormal physical examination data. Specifically, the abnormal physical examination data exclusion process includes: deleting incomplete data, selecting only the most recent result from multiple test results of the same individual, deleting data with positive results (chest X-ray, ultrasound, CT, etc.), and using the LAVE method to exclude data that exceeds the reference interval (such as WBC, Hb, MCV, MCHC, ALT, GGT, BUN, Cr, CEA, AFP, CA19-9, etc.). After using the Tukey method to exclude out-of-threshold values, the remaining set of physical examination data includes n test data. The n test data can be arranged in ascending order, and the n test data after ascending order can be used separately , , …, express, , To test the minimum value in the project data, is the maximum value in the test item data. Divide the n test data into 100 equal parts, and the number corresponding to the r% rank is the rth percentile, represented by the symbol Pr. The rank of the reference lower limit value and the reference upper limit value of the reconstructed reference interval can be represented by P 2.5 and P 97.5 Indicates that, where is calculated by the following formula: and If the calculated values ​​are not integers, they can be rounded to the nearest integer. The confidence interval for the lower limit of the reconstructed reference interval is P1-P5, and the confidence interval for the upper limit of the reconstructed reference interval is P 95 -P 99 .

[0042] Accordingly, the reconstructed reference interval of each test item of the physical examination category can be obtained by using the EP28 non-parametric method, for example, the reconstructed reference interval of the platelet count of the physical examination category, the reconstructed reference interval of the total protein of the physical examination category, the reconstructed reference interval of the albumin test item of the physical examination category, the reconstructed reference interval of the alanine aminotransferase test item of the physical examination category, the reconstructed reference interval of the aspartate aminotransferase test item of the physical examination category, etc. Accordingly, the reconstructed reference interval of each test item of the physical examination category can be divided into multiple groups of reconstructed reference intervals of the test item, for example, the reconstructed reference interval of the platelet count of the physical examination category includes the reconstructed reference interval of the platelet count of the first group of the physical examination category, the reconstructed reference interval of the platelet count of the second group of the physical examination category, the reconstructed reference interval of the platelet count of the third group of the physical examination category, the reconstructed reference interval of the platelet count of the fourth group of the physical examination category, the reconstructed reference interval of the platelet count of the fifth group of the physical examination category, the reconstructed reference interval of the platelet count of the sixth group of the physical examination category, and the reconstructed reference interval of the platelet count of more groups of the physical examination category. For example, the reconstructed reference interval of each grouping of the physical examination category corresponds to a group of test subjects, and the test subjects are grouped according to age and gender; for example, the reference interval of platelet count of the first grouping of the physical examination category is that the test subjects are female 6 months - <1 year old; the reference interval of platelet count of the second grouping of the physical examination category is that the test subjects are female 1 year old - <2 years old; the reference interval of platelet count of the third grouping of the physical examination category is that the test subjects are female 2 years old - <6 years old; the reference interval of platelet count of the fourth grouping of the physical examination category is that the test subjects are female 6 years old - <12 years old; the reference interval of platelet count of the fifth grouping of the physical examination category is that the test subjects are female 12 years old - <18 years old; the reference interval of platelet count of the sixth grouping of the physical examination category is that the test subjects are female 18 years old - <53 years old; the reference intervals of platelet count of other groups of the physical examination category correspond to the test subjects of other groups.

[0043] During the operation of the test data collection module, the test data set of at least one test item within a predetermined time period is extracted from the laboratory information system through the test data collection module 30. In particular, compared with the existing reference interval suitability assessment process, test data from the real world can be extracted from the laboratory information system, and there is no need to recruit additional subjects for testing, so as to greatly reduce the cost of assessing the suitability of the reference interval.

[0044] In a specific implementation, the test data collection module 30 first extracts a test data set within a predetermined time period from the laboratory information system, and then groups the test data set within the predetermined time period according to the test subjects (in a specific example, the test subjects are grouped according to age and gender), such as Figure 3 and Figure 4As shown, the data is then grouped according to the type of medical consultation, and then grouped according to the type of test items.

[0045] Similarly, the test data set within the predetermined time period can be divided into multiple grouped test data subsets, for example, a first grouped test data subset, a second grouped test data subset, a third grouped test data subset, a fourth grouped test data subset, a fifth grouped test data subset, a sixth grouped test data subset, and more grouped test data subsets. The first grouped test data subset is that the test subject is a female 6 months to less than 1 year old; the second grouped test data subset is that the test subject is a female 1 year old to less than 2 years old; the third grouped test data subset is that the test subject is a female 2 years old to less than 6 years old; the fourth grouped test data subset is that the test subject is a female 6 years old to less than 12 years old; the fifth grouped test data subset is that the test subject is a female 12 years old to less than 18 years old; the sixth grouped test data subset is that the test subject is a female 18 years old to less than 53; and other grouped test data subsets are test data subsets of other groups.

[0046] The test data subset of each group includes a first category test item subset for physical examination, a second category test item subset for outpatient visit type, and a third category test item subset for hospitalization type. For example, the test data subset of the first group for which the test subjects are females aged 12-<18 years old includes a first category test item subset, a second category test item subset, and a third category test item subset; the test data subset for which the test subjects are females aged 18-<53 years old includes another first category test item subset, another second category test item subset, and another third category test item subset.

[0047] The test item subset of each type of medical consultation in each grouped test data subset includes the test data of at least one test item. Accordingly, the first test item subset of each grouped test data subset includes at least one single test item data subset of the physical examination type; the second test item subset of each grouped test data subset includes at least one single test item data subset of the outpatient type; the third test item subset of each grouped test data subset includes at least one single test item data subset of the inpatient type; for example, the first test item subset of the first grouped test data subset of the grouped test object is a female 18-<53 years old, and the medical consultation type is a physical examination includes the platelet count test item test data under the physical examination type of the grouped test object is a female 18-<53 years old. It should be understood that the test data set within a predetermined time period can also be extracted from the laboratory information system and first divided according to the grouping of the test objects, the test objects are grouped according to age and gender, and then divided according to the test item data, and then divided according to the medical consultation type.

[0048] Correspondingly, in the process of dividing the inspection data set of each inspection item according to the three types of medical consultations, namely physical examination, outpatient clinic and hospitalization, to obtain the first inspection data subset, the second inspection data subset and the third inspection data subset, the first inspection data subset in the inspection data set of each inspection item is the inspection data subset whose medical consultation type is physical examination; the second inspection data subset in the inspection data set of each inspection item is the inspection data subset whose medical consultation type is outpatient clinic; and the third inspection data subset in the inspection data set of each inspection item is the inspection data subset whose medical consultation type is hospitalization.

[0049] Specifically, during the operation of the reference interval abnormality rate evaluation module 50, the upper and lower abnormality rates of the first test data subset, the second test data subset, and the third test data subset relative to the preset reference interval and the reconstructed reference interval are calculated to obtain the reference interval abnormality rate evaluation result. For ease of explanation, a specific test item is used as an example for exemplary explanation, such as platelet count.

[0050] In a specific example, the reference interval abnormality rate assessment module includes: a preset reference interval abnormality rate assessment unit and a reconstructed reference interval abnormality rate assessment unit, wherein the preset reference interval abnormality rate assessment unit is used to respectively calculate the upper limit abnormality rate and the lower limit abnormality rate of the preset reference interval corresponding to the first test data subset, the second test data subset and the third test data subset to obtain a preset reference interval abnormality rate assessment result; the reconstructed reference interval abnormality rate assessment unit is used to respectively calculate the upper limit abnormality rate and the lower limit abnormality rate of the reconstructed reference interval corresponding to the first test data subset, the second test data subset and the third test data subset to obtain a reconstructed reference interval abnormality rate assessment result.

[0051] Specifically, the preset reference interval abnormality rate evaluation unit is further used to calculate the proportion of the number of test data exceeding the upper limit value of the preset reference interval in the first test data subset, the second test data subset and the third test data subset of the test item, respectively, to obtain the upper limit abnormality rate of the preset reference interval corresponding to the first test data subset, the second test data subset and the third test data subset. Here, the proportion is the proportion of the number of test data exceeding the upper limit value of the preset reference interval divided by the cardinality of each test data subset. Similarly, the preset reference interval abnormality rate evaluation unit is further used to calculate the proportion of the number of test data below the lower limit value of the preset reference interval in the first test data subset, the second test data subset and the third test data subset of the test item, respectively, to obtain the lower limit abnormality rate of the preset reference interval corresponding to the first test data subset, the second test data subset and the third test data subset.

[0052] Correspondingly, the reconstructed reference interval abnormality rate assessment unit can calculate the upper limit abnormality rate and the lower limit abnormality rate of the reconstructed reference interval corresponding to the first inspection data subset, the second inspection data subset and the third inspection data subset in an operating mode similar to that of the preset reference interval abnormality rate assessment unit, which will not be expanded here for the sake of text conciseness.

[0053] like Figure 5 As shown, in an embodiment of the present application, the suitability management module 60 includes a consistency assessment unit 61 and a suitability assessment result determination unit 62, wherein the consistency assessment unit 61 is used to perform a consistency assessment analysis on the preset reference interval abnormality rate assessment result and the reconstructed reference interval abnormality rate assessment result to obtain a consistency assessment result; and the suitability assessment result determination unit 62 is used to generate a suitability assessment result of the inspection item based on the consistency assessment result and the preset and reconstructed reference interval abnormality rate assessment results.

[0054] In an embodiment of the present application, the operating logic of the consistency evaluation unit 61 is as follows: calculate the difference between the upper limit abnormality rate of the reconstructed reference interval and the upper limit abnormality rate of the preset reference interval, and calculate the difference between the lower limit abnormality rate of the reconstructed reference interval and the lower limit abnormality rate of the preset reference interval to obtain a first difference and a second difference, and, based on the comparison between the first difference and the second difference and the preset threshold, generate the consistency evaluation result.

[0055] In a specific example, the difference between the upper limit abnormality rate of the reconstructed reference interval and the upper limit abnormality rate of the preset reference interval is calculated, that is, the evaluated abnormality rate is compared with the reference interval abnormality rate obtained by the EP28 non-parametric method. If the difference is greater than 50%, it is inappropriate, and if it is less than 50%, it may be appropriate.

[0056] In another embodiment of the present application, the operating logic of the consistency evaluation unit 61 is as follows: first, the ratio between the upper limit abnormality rate of the preset reference interval and the lower limit abnormality rate of the reference interval of any two test data subsets in the first test data subset, the second test data subset, and the third test data subset is calculated to obtain a plurality of abnormality rate ratios; then, based on the comparison between each abnormality rate ratio in the plurality of abnormality rate ratios and a preset threshold value, the consistency evaluation result is generated. Specifically, in a specific example, when the abnormality rate of outpatient and inpatient treatment differs too much or too little from the abnormality rate of physical examination, the reference interval may be inappropriate. For example, when the abnormality rate of outpatient treatment is 5 times higher than that of physical examination or the abnormality rate of inpatient treatment is 20 times higher than that of physical examination, the reference interval may be inappropriate.

[0057] It is worth mentioning that, in specific implementation, the judgment range can be established according to the characteristics of different projects, population distribution, and hospital specialty characteristics, which is not limited to this application.

[0058] In a specific example, the conditions of age and gender in the reference interval are set to query the data from October 22, 2024 to November 22, 2024 in the laboratory information system, and the PLT reference interval is calculated according to the three different types of visits: physical examination, outpatient, and hospitalization (male: 83-303 × 10 9 / L, female: 101-320×10 9 / L) upper or lower limit abnormal rate, and then recalculate the reference interval (male: 137-354×10 9 / L, female 144-384×10 9 / L) upper or lower limit abnormal rate.

[0059] The suitability assessment results showed that the preset reference interval of PLT was significantly lower than the reference interval of the EP28 nonparametric method and references. Figure 7 The upper and lower limits of the preset reference intervals for physical examination, outpatient, and hospitalization were shown to have abnormal rates of 15.75%, 13.82%, 10.56% and 0.16%, 2.71%, 18.27%, respectively. The extreme rate of abnormal grade distribution in hospitalized patients accounted for 20.51%. The appropriateness of the reference interval for PLT needs further study.

[0060] like Figure 1As shown, in a preferred embodiment of the present application, the medical test item reference interval suitability assessment system 1000 further includes an abnormality level judgment standard determination module 70 and an abnormality level calculation module 80. The abnormality level judgment standard determination module 70 is used to determine the abnormality level judgment standard based on the set of physical examination data. The abnormality level calculation module 80 is used to analyze the second test data subset and the third test data subset based on the abnormality level judgment standard to obtain the abnormality level distribution of the outpatient test results and the abnormality level distribution of the inpatient test results.

[0061] In a specific example, the abnormal level judgment standard determination module 70 determines five levels (such as Figure 6 , Figure 7 , Figure 8 and Fig. 9 The upper and lower limit values ​​of the physical examination data (as shown) are normal, slightly abnormal, moderately abnormal, severely abnormal and extremely abnormal, respectively. Among them, the physical examination data that does not belong to the normal level is considered to be abnormal physical examination data, that is, the abnormal physical examination data includes physical examination data of slightly abnormal level, moderate abnormal level, severely abnormal level and extremely abnormal level.

[0062] In this specific example, the abnormal level judgment standard determination module is further used to: determine the upper and lower limits of the normal level based on the level division condition that the set distribution of the physical examination data is greater than 2.5% or less than 97.5% on both sides or the level division condition that the set distribution of the physical examination data is less than 95% on one side; determine the upper and lower limits of the mild level based on the level division condition that the set distribution of the physical examination data is greater than 1.5% and less than or equal to 2.5% or greater than or equal to 97.5% and less than 98.5% on both sides or the level division condition that the set distribution of the physical examination data is greater than or equal to 95% and less than 97% on one side; determine the upper and lower limits of the mild level based on the set distribution of the physical examination data is greater than 1.0% and less than or equal to 1.5% or greater than or equal to 98.5% and less than 97% on both sides. The upper and lower limits of the moderate level are determined based on the grading condition of 9.0% or the grading condition that the set distribution of the physical examination data is greater than or equal to 97.0% and less than 98.0% on one side; the upper and lower limits of the severe level are determined based on the grading condition that the set distribution of the physical examination data is greater than 0.5% and less than 1.0% or greater than or equal to 99.0% and less than 99.5% on both sides or the grading condition that the set distribution of the physical examination data is greater than or equal to 98.0% and less than 99.0% on one side; and, the upper and lower limits of the extreme level are determined based on the grading condition that the set distribution of the physical examination data is less than or equal to 0.5% or greater than or equal to 99.5% on both sides or the grading condition that the set distribution of the physical examination data is greater than or equal to 99.0% on one side.

[0063] In this specific example, the operating logic of the abnormality level calculation module 80 is as follows: based on the abnormality level standard, the proportions of normal, mildly abnormal, moderately abnormal, severely abnormal and extremely abnormal test data in the second test data subset and the third test data subset are counted, and in this way, the abnormality level of the outpatient test results and the abnormality level of the inpatient test results are determined.

[0064] In a specific example, for the data of a group of test items in a certain period of time in the laboratory, the data with the type of medical examination as physical examination is screened out and the abnormal level of the test results of outpatients and inpatients is calculated based on the distribution of physical examination big data. Then, the distribution of physical examination big data is used as the basis for the division of abnormal levels. Normal, the bilateral range of the physical examination data distribution is >2.5% or <97.5%, and the unidirectional range is <95%. Mild, the bilateral range of the physical examination data distribution is 1.5-2.5% or 97.5-98.5%, and the unidirectional range is 95-97%. Moderate, the bilateral range of the physical examination data distribution is 1.0-1.5% or 98.5-99.0%, and the unidirectional range is 97.0-98.0%. Severe, the bilateral range of the physical examination data distribution is 0.5-1.0% or 99.0-99.5%, and the unidirectional range is 98.0-99.0%. Extremely, the bilateral range of the physical examination data distribution is ≤0.5 or ≥99.5%, and the unidirectional range is ≥99.0%. Then, the number of test results of the previous day is updated regularly every day through a cyclic algorithm. The cumulative percentage of the result value is calculated by counting the proportion of the number of results lower than the result value to the total number. The population percentage is classified and counted according to 0.5, 1, 1.5, 2, 2.5, 3, 4, 5, 6...95, 96, 97, 97.5, 98, 98.5, 99.5, 100. After obtaining the population percentage of each physical examination item, the result value corresponding to the percentage used to divide the abnormal level can be obtained.

[0065] An actual example is as follows: On a certain day, the platelet count test result is 109×10 9 / L has 5 values ​​in total. If the value 109×10 already exists in the previously counted cumulative percentage 9 / L, the item quantity is updated, plus the cumulative quantity of 27, the total should be 32, the result is 109×10 9 / L and below, there are 104, with a cumulative percentage of 0.501%. If it does not exist, the value is 109×10 9 / L, then add the result value, the quantity is 5, and then calculate the cumulative percentage.

[0066] It is worth mentioning that when the suitability of preset reference intervals of multiple test items is managed, multiple threads can be used to evaluate the suitability of preset reference intervals of multiple test items through the above-mentioned medical test item reference interval suitability evaluation system 1000. It is also worth mentioning that in the process of suitability evaluation of reference intervals, the abnormal level evaluation results can also be used as inclusion indicators to more comprehensively evaluate the actual suitability of reference intervals, which is not the subject of this application.

[0067] like Figure 1 As shown, in this preferred embodiment of the present application, the medical test item reference interval suitability assessment system 1000 also manages the suitability of the reference interval in combination with reference documents. It is worth mentioning that managing the suitability of the reference interval in combination with reference documents is an option.

[0068] Specifically, Figure 5 As shown, the medical test item reference interval suitability assessment system 1000 also includes a reference collection module 90, a reference grade assessment module 100 and a reference reference interval management module 110. The reference collection module 90 is used to search for references. The reference grade assessment module 100 is used to perform quality assessment on references to obtain reference quality grade assessment results. The reference reference interval management module 110 is used to extract and manage relevant data on the recommended reference interval of at least one test item in the reference based on a large language model.

[0069] Correspondingly, the medical test item reference interval suitability assessment system 1000 also searches for references through the reference collection module 90, performs quality assessment on the references through the reference grade assessment module 100 to obtain reference quality grade assessment results, and extracts and manages relevant data on the recommended reference interval for at least one test item in the references based on a large language model through the reference reference interval management module 110.

[0070] In the process of searching for references through the reference collection module 90, you can link to online databases and library resources through links, and search for references from major document databases, such as the China National Knowledge Infrastructure document database, Wanfang database, Wiley database, etc. You can also add references (such as Fig.11As shown). Convert keywords (test item name, test system, reference interval, etc.) into high-dimensional feature vectors, and use these vectors to capture the semantic and syntactic information in the keywords. Then calculate the similarity between the high-dimensional feature vector and the high-dimensional feature vector corresponding to each corpus knowledge text block, retrieve the most relevant corpus knowledge text library, and sort the search results according to the similarity to obtain several preliminary screening documents based on the similarity results; further, they can be screened according to partition, impact factor, number of citations, publication time, and document type to obtain several target documents. Support importing external documents into the document library by uploading files.

[0071] That is, in a specific example of the present application, the process of searching for references includes the steps of: S1: Enter the reference search keywords; S2: performing semantic embedding coding on the reference search keyword to obtain a semantic embedding coding vector of the reference search keyword; S3: extract a collection of corpus knowledge text blocks from the corpus knowledge base; S4: performing semantic encoding on each corpus knowledge text block in the set of corpus knowledge text blocks respectively to obtain a set of semantic embedding encoding vectors of the corpus knowledge text blocks; S5: Calculate the similarity between the reference search keyword semantic embedding coding vector and each corpus knowledge text block semantic embedding coding vector in the set of corpus knowledge text block semantic embedding coding vectors to obtain a set of similarities; S6: Sort the similarity set to obtain several preliminary screening documents.

[0072] In a preferred embodiment, in order to improve the calculation accuracy of similarity, the process of calculating the similarity between the semantic embedding coding vector of the reference search keyword and the semantic embedding coding vector of each corpus knowledge text block in the set of semantic embedding coding vectors of the corpus knowledge text block includes the following steps: S51: performing semantic fine-grained interactive coding on the semantic embedding coding vector of the reference search keyword and the semantic embedding coding vector of the corpus knowledge text block to obtain a search keyword-corpus knowledge text block bidirectional fine-grained semantic association coding vector; S52: Input the search keyword-corpus knowledge text block bidirectional fine-grained semantic association encoding vector into a decoder-based similarity estimation module to obtain the similarity.

[0073] In this specific example, semantic fine-grained interactive encoding is performed on the reference search keyword semantic embedding encoding vector and the corpus knowledge text block semantic embedding encoding vector, including: S511: Performing principal component analysis on the semantic embedding coding vector of the corpus knowledge text block to obtain a set of principal component feature coding vectors of the corpus knowledge text block; this process is expressed by the formula: in, represents the semantic embedding encoding vector of the corpus knowledge text block, represents the transpose of a vector, represents the length of the semantic embedding encoding vector of the corpus knowledge text block, represents the covariance matrix, The set of sets of principal component feature encoding vectors representing corpus knowledge text blocks, , , Represents the first, second and The principal component feature encoding vector of the corpus knowledge text block, Represents the total number of principal component feature encoding vectors of corpus knowledge text blocks, represents a diagonal matrix, represents the diagonal elements, , , Represents the first, second, and third diagonal of a diagonal matrix characteristic values.

[0074] It should be understood that principal component analysis first converts the high-dimensional semantic embedding encoding vector of the corpus knowledge text block into a low-dimensional but more compact and information-rich representation - that is, a set of principal component feature encoding vectors of the corpus knowledge text block. This process is not just a simple dimensionality reduction operation, it is actually a deep information purification of the original data. In this process, the information originally scattered in the high-dimensional space is reorganized and concentrated on a set of ordered principal component axes. This means that a small number of head principal components can capture most of the variation information in the data, while those redundant or noisy information are naturally filtered out. For example, when building a document retrieval system, by performing principal component analysis on each text block in the corpus, the potential multicollinearity problem within the text can be effectively eliminated, making the differences between different text blocks more obvious, thereby improving the relevance and accuracy of the retrieval results. In addition, due to the reduction of feature dimensions, the time cost of model training will be greatly reduced, and the risk of overfitting can also be reduced, because fewer features mean fewer model parameters, thereby reducing model complexity.

[0075] S512: performing linear transformation on each principal component feature coding vector of the corpus knowledge text block in the set of principal component feature coding vectors of the corpus knowledge text block to obtain a set of principal component linear transformation feature coding vectors of the corpus knowledge text block, wherein each principal component linear transformation feature coding vector of the corpus knowledge text block in the set of principal component linear transformation feature coding vectors of the corpus knowledge text block has the same characteristic scale as the semantic embedding coding vector of the reference search keyword; the process is expressed by the formula: in, Express Perform a linear transformation, Represents the set of principal component linear transformation feature encoding vectors of corpus knowledge text blocks, , , Indicates the first, second and The principal component feature encoding vector of a corpus knowledge text block.

[0076] It should be understood that through linear transformation, the scale of the principal component feature encoding vector of each corpus knowledge text block can be adjusted so that they can be compared and interacted under the same reference frame. This scale adjustment is not only to make the data of different modalities closer in value, but more importantly to ensure that in the process of information fusion, the data of each modality can fairly contribute its unique information, rather than over-amplifying or ignoring the information of some modalities due to scale differences.

[0077] S513: performing inter-modal independence coding on each corpus knowledge text block principal component feature coding vector in the set of the reference search keyword semantic embedding coding vector and the corpus knowledge text block principal component feature coding vector to obtain a set of search keyword-corpus knowledge text block principal component inter-modal independence coding matrices; this process is expressed by the formula: in, Indicates The principal component feature encoding vector of the corpus knowledge text block, and is a feature mapping function, such as a linear mapping or a nonlinear kernel function, represents the semantic embedding coding vector of the reference search keyword, represents the length of the semantic embedding encoding vector of the reference search keyword, Indicates The encoding matrix of the inter-modal independence of the principal components of the search keyword-corpus knowledge text block.

[0078] It should be understood that through inter-modal independence encoding, an optimized space can be created in which search keywords and each text block in the corpus are represented in a new and more refined way, that is, a set of search keyword-corpus knowledge text block principal component inter-modal independence encoding matrices is formed. This encoding method is not just a formal combination of two types of vectors, but is based on a deep understanding of the relationship between them, emphasizing the differences and unique contributions of the two in terms of expression content. Specifically, when comparing search keywords with a large number of corpus knowledge text blocks, directly fusing these vectors may cause some problems, such as some high-dimensional features may be highly correlated between different modalities, which will lead to information duplication and increase the complexity of the model. Through inter-modal independence encoding, we can identify those features that are truly independent, so as to use these features more effectively to enhance the performance of the model. This method encourages the model to focus on those parts that provide unique information between different modalities, rather than simply superimposing all available information. Through inter-modal independence encoding, the system can better identify which documents contain not only terms directly related to the query terms, but also unique information that can supplement and expand the meaning of the query terms. This method helps to improve the relevance of search results, so that the documents presented to users are not only superficial matches, but also high-quality resources that are closely connected to the query intent in a deeper sense. In addition, this encoding strategy helps to balance the importance of different modalities, ensuring that no modality dominates the final decision due to its intrinsic characteristics (such as scale). In this way, both search keywords and text blocks in the corpus can play their maximum role within their due scope, and together provide users with more accurate and valuable search results.

[0079] S514: Based on the set of the search keyword-corpus knowledge text block principal component modality independence coding matrix, calculate the set of search keyword-corpus knowledge text block principal component modality independence soft constraint factors; this process is expressed by the formula: in, represents the square of the F-norm of the matrix, Indicates A soft constraint factor for the independence of the principal components of search keyword-corpus knowledge text blocks.

[0080] It should be understood that the soft constraint factor of inter-modal independence between the search keyword and each corpus knowledge text block is calculated. This process essentially creates a dynamic adjustment mechanism that allows the model to adaptively weigh the importance of each modality based on the specific circumstances of the input data. Specifically, the soft constraint factor provides a flexible way for the model to emphasize the independence between modalities while also taking into account the inevitable correlation between them. This flexibility is crucial for processing complex data in the real world, because actual data often contains information that is both complementary and overlapping to some extent. In addition, the dynamic nature of the soft constraint factor means that it can adjust its behavior as the input changes. If a particular query term is particularly relevant to certain types of documents, the soft constraint factor can automatically adapt to this situation to ensure that the most relevant documents are given priority. In this way, the system can maintain high accuracy and relevance whether it is processing highly specialized queries or broad subject searches.

[0081] S515: Inputting each corpus knowledge text block principal component feature coding vector in the set of the reference search keyword semantic embedding coding vector and the corpus knowledge text block principal component feature coding vector into a feature interaction response unit to obtain a set of fine-grained response interaction coding vectors between the search keyword and the corpus knowledge text block principal component modality; this process is expressed by the formula: in, It means point multiplication by position. Represents by position vector, means division by position, represents a cascade function, Indicates A weight matrix, Indicates A bias vector, Indicates A fine-grained response interaction encoding vector between the principal component modalities of a search keyword-corpus knowledge text block.

[0082] It should be understood that when these vectors are input into the feature interaction response unit, the system begins to perform fine-grained feature interactions. This is not just a simple vector addition or dot product operation, but a deep exploration of the complex relationships and potential patterns between different modal features. Specifically, the feature interaction response unit explores the multi-level associations between the search keywords and each text block, including but not limited to semantic similarities, thematic overlaps, and subtle connections in the context. This fine-grained interaction does not just stay at the surface level, it also goes deep into the feature dimension level to explore nonlinear relationships and hierarchical structures. This means that the system can capture deeper information in the document. Ultimately, the set of fine-grained response interaction encoding vectors between the search keyword-corpus knowledge text block principal component modalities generated through this process provides a more comprehensive and sophisticated representation. These encoding vectors not only reflect the direct match between the query terms and the documents, but also reveal a more complex interaction and complementary relationship between the two.

[0083] S516: Based on the set of the soft constraint factors of independence between the search keyword and the principal component modalities of the corpus knowledge text block, the set of fine-grained response interaction encoding vectors between the search keyword and the principal component modalities of the corpus knowledge text block is dynamically and adaptively aggregated to obtain the interaction response encoding vector; this process is expressed by the formula: in, represents the normalized exponential function, Represents the interaction response encoding vector.

[0084] It should be understood that, using the previously calculated set of soft constraint factors for independence between the search keyword and the main component modalities of the corpus knowledge text block, the system begins to dynamically and adaptively aggregate the fine-grained response interaction encoding vectors between the search keyword and the main component modalities of the corpus knowledge text block. The core of this process is to dynamically adjust the contribution weights of each fine-grained response according to the soft constraint factors, so as to selectively fuse the most relevant feature information. This dynamic adjustment mechanism enables the system to flexibly respond to the characteristics of different input data. For example, when a query term is particularly relevant to a specific type of document, the system will automatically increase the weight of this type of document in the final aggregation result. On the contrary, if some documents contain relevant information of some query terms but deviate greatly from the query intent as a whole, their weights will be reduced accordingly. This ensures that the interaction response encoding vector generated in the end not only contains the direct matching information between the query term and the document, but also reflects the more complex complementary relationship between the two. In addition, the dynamic adaptive aggregation process can effectively reduce the impact of redundant information. Because the soft constraint factors emphasize the independence and complementarity between modalities, the system tends to retain those parts that provide unique perspectives and information, while suppressing repeated or irrelevant information. In this way, the final interaction response encoding vector is not only more compact and refined, but also has higher discrimination and expressiveness.

[0085] In the process of evaluating the quality of references by the reference grade evaluation module 100 to obtain the reference quality grade evaluation results, the target content of the document can be extracted and / or translated by using document content extraction and translation technology. PDF documents can be scanned by optical character recognition (OCR) technology to convert them into editable text. Foreign documents can be translated by using an encoder-decoder architecture with the help of a deep learning model, in which the encoder converts the source language text into an intermediate text of a vector sequence, and the decoder translates this intermediate text to generate a target text. At the same time, the model uses an attention mechanism to understand semantics more accurately and generate translation results that are more consistent with the expression habits of the target language. The large language model is trained by a large corpus of medical documents, and professional optimization in the medical field enhances the understanding and translation capabilities of medical terms. The large language model is used to automatically retrieve documents and extract reference interval-related data, avoiding manual search of documents and manual search of content in documents, saving time and energy for researchers.

[0086] Furthermore, the page layout detection model can be used to determine the reading order of the text, and the cleaning and formatting algorithms can be used to process the text blocks, such as the functional classification of abstract sentences, the functional identification of chapters, and the functional identification of citations, that is, to identify the attributes or relationships of one or more types of knowledge units, and then use combination and post-processing algorithms to improve the quality of the text. Finally, the natural language processing (NLP) technology and machine learning in the PDF parsing library can be used to extract the structured information in the literature, such as: detection year, region, population race, detection instrument, detection method, reference interval method, reference interval, and confidence interval. After extracting these fields, they are automatically entered into the system to form a document library for management. In addition, since medical literature contains some unstructured information, including inclusion criteria, exclusion criteria, etc., it is necessary to extract and organize this information into structured information for comparative analysis.

[0087] Through the classification model of machine learning, the literature that studies the reference intervals of the same type of test items is classified into one category. The graph neural network is used to analyze the literature citation network and academic social network to enhance the understanding of the relationship and influence between the literature. The pre-trained language model is used for deeper text understanding and analysis to improve the accuracy of literature quality assessment, as shown in Table 1.

[0088] In order to make a more accurate assessment of the quality of the literature, different literature can be rated as A, B, C, and D according to the literature quality evaluation standard checklist. The overall A level means that all the quality evaluation standards of a literature have reached the A level; B level means that the lowest level reached in the quality evaluation standard is B level; C level means that the lowest level reached in the quality evaluation standard is C level; D level means that the lowest level reached in the quality evaluation standard is D level. Among them, the D level indicates that the reference interval evaluated in the literature should not be used in clinical practice.

[0089] Table 1 Reference interval literature quality evaluation checklist Subsequent data processing can be performed on references with higher quality levels. In the process of extracting and managing the relevant data on the recommended reference interval of at least one test item in the reference based on the large language model by the reference reference interval management module 110, in the document library, the document name, document quality, impact factor, publication date, journal, author, full text, abstract, citation, etc. can be browsed; the project name, unit, nationality, instrument (such as Fig.11As shown), reagents, test methods, regions, reference interval establishment methods, threshold values, inclusion and exclusion criteria, and reference intervals grouped by gender and age are managed; in addition, the literature library can be associated, and there is a one-to-many relationship between literature and projects, and they are classified into one category according to the same project name; the recommended reference intervals of the same test item in different literature can be displayed in the form of generated pictures. The abnormal rate and abnormal level of the reference interval in the real-world data of different types of medical treatment (physical examination, outpatient, and hospitalization) can be analyzed separately by importing data from the laboratory information system, that is, the abnormal rate and abnormal level of the reconstructed reference interval corresponding to the first test data subset, the second test data subset, and the third test data subset are analyzed and displayed in pictures.

[0090] In a specific example, the reference interval management module 110 extracts and manages the relevant data of the recommended reference interval of at least one test item in the reference based on the large language model, including: evaluating the consistency of the test item with the recommended reference interval based on the reference. Its operation logic is as follows: By calculating the bias ratio between the reference interval of the reference literature and the reference interval of the test item, the quality of the reference interval is automatically evaluated to determine whether the reference interval is appropriate and to display it visually.

[0091] Among them, LL0, UL0 and Me0 represent the lower limit, upper limit and median of the reference interval of the test item, and LL, UL and Me represent the lower limit, upper limit and median of the reference interval in the literature. LL or BR UL If it is greater than 0.375, it means that the bias is relatively large, and the reference interval of the test item is less consistent with the reference interval in the literature. Otherwise, it means that the bias is relatively small, and the reference interval of the test item is more consistent with the reference interval in the literature. The reference comparison results are visualized in a graphical way, such as Fig.12 , Fig.13 As shown, the reference list is displayed on the left side of the graph, including author (English), year, gender, age and gestational period, and the reference intervals with a bias ratio greater than 0.375 are displayed in red. BR Me For reference only, no consistency judgment criteria are set.

[0092] Based on the region and ethnicity of the reference interval research, the detection instruments and methods, the reference interval establishment method, the population grouping and sample size, etc., combined with the current status of the laboratory's test items, the upper and lower limits of the recommended reference interval for a certain test item can be selected or estimated (median or mode).

[0093] That is, its technical logic is abstractly summarized as follows: the bias ratio between the upper limit value of the preset reference interval of each group corresponding to each type of test data subset of each test item and the upper limit value of the recommended reference interval of the group corresponding to the type of test data subset of the test item is calculated according to the following formula: in, SD RI Indicates the base value; UL 0 represents the upper limit of the recommended reference interval for a group corresponding to a subset of test data for a test item; LL 0 represents the lower limit of the recommended reference interval for a group corresponding to a subset of test data for a test item; BR UL Indicates the bias ratio of the upper limit value of a preset reference interval for a group corresponding to a type of test data subset of a test item relative to the upper limit of the recommended reference interval for the group corresponding to the type of test data subset of the test item; UL Indicates the upper limit value of a preset reference interval of a group corresponding to a type of test data subset of a test item; The bias ratio between the lower limit of the preset reference interval of each test item and the lower limit of the recommended reference interval of the test item is calculated according to the following formula: in, BR LL The bias ratio of the lower limit value of the preset reference interval of a group corresponding to a type of test data subset of a test item relative to the lower limit value of the recommended reference interval of the group corresponding to the type of test data subset of the test item; LL Indicates the lower limit value of a preset reference interval of a group corresponding to a type of test data subset of a test item; BR Me The bias ratio of the median of a preset reference interval of a group corresponding to a subset of test data of a test item relative to the median of a recommended reference interval of the group corresponding to the subset of test data of the test item; Me Represents the median of a preset reference interval for a group of test data subsets for a test item.

[0094] In a specific example, the preset threshold is equal to 0.375. or If the value is greater than 0.375, it is determined that the consistency assessment result is that the consistency between the recommended reference interval of the test item and the reconstructed reference interval of the test item does not meet the preset requirements; when and If it is less than or equal to 0.375, it is determined that the consistency assessment result is that the consistency between the recommended reference interval of the test item and the reconstructed reference interval of the test item meets the preset requirements. BR Me For reference only, no consistency judgment criteria are set.

[0095] In summary, the reference interval suitability assessment system 1000 for medical test items according to the embodiment of the present application is explained. The reference interval suitability assessment system 1000 for medical test items groups the test data according to gender and age, and establishes reference intervals corresponding to each age group of different genders, which can improve the accuracy of the reference intervals to a certain extent. The collection of test data of the subject objects in the reference interval suitability assessment system 1000 for medical test items comes from the real medical records of real patients. In this way, on the one hand, the data source is reliable, and on the other hand, there is no need to specially recruit subjects for testing in order to conduct parameter interval experiments, which can improve feasibility and reduce costs to a certain extent.

[0096] The present application and its implementation methods are described above, and such description is not restrictive. The drawings show only one implementation method of the present application, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it and design structural methods and embodiments similar to the technical solution without creative design without departing from the inventive purpose of the present application, they should all fall within the protection scope of the present application.

Claims

1. A reference interval suitability assessment system for medical test items, characterized in that: include: A preset reference interval extraction module, used to extract a preset reference interval of at least one test item from a test item reference interval database; A physical examination data collection and analysis module, used to obtain a set of physical examination data, and process the set of physical examination data using the EP28 non-parametric method to determine the reconstructed reference interval of the test item; A test data collection module, used to extract test data sets of the test items within a predetermined time period from a laboratory information system; A data grouping module, used for segmenting the test data set of the test items according to the three types of medical examination, outpatient and hospitalization to obtain a first test data subset, a second test data subset and a third test data subset; A reference interval abnormality rate evaluation module, used to respectively calculate the upper and lower abnormality rates of the first test data subset, the second test data subset, and the third test data subset relative to the preset reference interval and the reconstructed reference interval to obtain a reference interval abnormality rate evaluation result; The suitability management module is used to generate a suitability assessment result of the test item based on the reference interval abnormality rate assessment result.

2. The medical test item reference interval suitability evaluation system according to claim 1, characterized in that: The reference interval abnormality rate assessment module includes: A preset reference interval abnormality rate evaluation unit, used to respectively calculate the upper limit abnormality rate of the preset reference interval and the lower limit abnormality rate of the preset reference interval corresponding to the first test data subset, the second test data subset and the third test data subset to obtain a preset reference interval abnormality rate evaluation result; The reconstructed reference interval abnormality rate assessment unit is used to respectively calculate the upper limit abnormality rate and the lower limit abnormality rate of the reconstructed reference interval corresponding to the first test data subset, the second test data subset and the third test data subset to obtain the reconstructed reference interval abnormality rate assessment result.

3. The medical test item reference interval suitability evaluation system according to claim 2, characterized in that: The suitability management module comprises: A consistency evaluation unit, configured to perform consistency evaluation analysis on the preset reference interval abnormality rate evaluation result and the reconstructed reference interval abnormality rate evaluation result to obtain a consistency evaluation result; A suitability assessment result determination unit is used to generate a suitability assessment result of the inspection item based on the consistency assessment result, the preset reference interval abnormality rate assessment result and the reconstructed reference interval abnormality rate assessment result.

4. The medical test item reference interval suitability evaluation system according to claim 3, characterized in that: The consistency assessment unit is further used for: Calculating the difference between the upper limit abnormality rate of the reconstructed reference interval and the upper limit abnormality rate of the preset reference interval and calculating the difference between the lower limit abnormality rate of the reconstructed reference interval and the lower limit abnormality rate of the preset reference interval to obtain a first difference and a second difference; The consistency evaluation result is generated based on a comparison between the first difference degree and the second difference degree and a preset threshold.

5. The medical test item reference interval suitability evaluation system according to claim 3, characterized in that: The consistency assessment unit is further used for: Calculating the ratio between the upper limit abnormality rate of the preset reference interval or the lower limit abnormality rate of the preset reference interval of any two test data subsets among the first test data subset, the second test data subset and the third test data subset to obtain a plurality of abnormality rate ratios; The consistency evaluation result is generated based on a comparison between each abnormality rate ratio of the multiple abnormality rate ratios and a preset threshold.

6. The medical test item reference interval suitability evaluation system according to claim 1, characterized in that: Also includes: An abnormality level judgment standard determination module, used to determine the abnormality level judgment standard based on the set of physical examination data; The abnormality level calculation module is used to analyze the second test data subset and the third test data subset based on the abnormality level standard to obtain the abnormality level distribution of the outpatient test results and the abnormality level distribution of the inpatient test results.

7. The medical test item reference interval suitability evaluation system according to claim 6, characterized in that: The abnormal level judgment standard determination module is further used to: Determine the upper and lower limits of the normal level based on the level division condition that the set distribution of the physical examination data is greater than 2.5% or less than 97.5% on both sides or the level division condition that the set distribution of the physical examination data is less than 95% on one side; Determine the upper and lower limits of the mild level based on the level division condition that the set distribution of the physical examination data is greater than 1.5% and less than 2.5% on both sides or greater than or equal to 97.5% and less than 98.5% on one side, or the level division condition that the set distribution of the physical examination data is greater than or equal to 95% and less than 97% on one side; Determine the upper and lower limits of the moderate level based on the level division condition that the set distribution of the physical examination data is greater than 1.0% and less than or equal to 1.5% on both sides or greater than or equal to 98.5% and less than 99.0% on one side, or the level division condition that the set distribution of the physical examination data is greater than or equal to 97.0% and less than 98.0% on one side; Determine the upper and lower limits of the severe level based on the level classification condition that the set distribution of the physical examination data is greater than 0.5% and less than or equal to 1.0% on both sides or greater than or equal to 99.0% and less than 99.5% on one side, or the level classification condition that the set distribution of the physical examination data is greater than or equal to 98.0% and less than 99.0% on one side; The upper and lower limits of the extreme level are determined based on the level division condition that the set distribution of the physical examination data is less than or equal to 0.5% or greater than or equal to 99.5% on both sides or the level division condition that the set distribution of the physical examination data is greater than or equal to 99.0% on one side.

8. The medical test item reference interval suitability evaluation system according to claim 1, characterized in that: Also includes: Reference collection module, used to search for references; A reference document quality assessment module, used for performing quality assessment on the reference document to obtain a reference document quality assessment result; The reference reference interval management module is used to extract and manage relevant data on the recommended reference interval of the test item from the reference based on the large language model.

9. The medical test item reference interval suitability evaluation system according to claim 8, characterized in that: The reference document reference interval management module is further used to: Calculating the bias ratio between the recommended reference interval of the test item and the reconstructed reference interval; When the bias ratio is greater than a preset threshold, it is determined that the consistency between the recommended reference interval of the test item and the reconstructed reference interval of the test item does not meet the preset requirement; When the bias ratio is less than or equal to a preset threshold, it is determined that the consistency between the recommended reference interval of the test item and the reconstructed reference interval of the test item meets the preset requirement.

Images