Physical examination report concrete processing method and physical examination report interpretation method

Abstract

The invention relates to a physical examination report concrete processing method and a physical examination report interpretation method. The physical examination report concrete processing method comprises the following steps: S1, acquiring an image of a physical examination report to obtain a physical examination report image; s2, identifying the physical examination report image and extracting character information; s3, the character information is concluded and classified into basic information and to-be-judged information, the basic information comprises the age of the subject, and the to-be-judged information comprises a plurality of inspection items and inspection values associated with the corresponding inspection items; s4, according to the basic information, calling a reference range of a corresponding inspection item of a corresponding age in a standard library; s5, generating a distribution interval corresponding to the inspection item according to the called reference range of the inspection item; and S6, constructing a visual inspection graph based on the to-be-judged information and the distribution interval of the inspection items.

Description

Technical Field

[0001] The present invention relates to the field of information communication technology in a specific application field, and in particular to the information communication technology of medical reports. Background Art

[0002] Existing physical examination reports include blood routine, biochemistry, urine and other categories. Regardless of the type, the physical examination report is recorded in pure text, which makes it difficult to read and understand, and is not conducive to doctors or other medical staff to obtain key information. Doctors or other medical staff often need to spend a lot of time interpreting the report content, resulting in low work efficiency. Summary of the invention

[0003] In view of this, the present invention provides a method for processing a physical examination report and a method for interpreting a physical examination report, which are used to solve one of the problems in the prior art that the pure text form of the physical examination report leads to low work efficiency.

[0004] In order to achieve one, part, or all of the above purposes or other purposes, the present invention proposes:

[0005] A method for processing a physical examination report, comprising the following steps:

[0006] S1: Collect the image of the physical examination report to obtain the physical examination report image;

[0007] S2: Recognize the physical examination report image and extract text information;

[0008] S3: Summarize and classify the text information into basic information and information to be determined, wherein the basic information includes the age of the subject, and the information to be determined includes multiple test items and test values ​​associated with the corresponding test items;

[0009] S4: Call the reference range of the corresponding test items of the corresponding age in the standard library according to the basic information;

[0010] S5: Generate a distribution interval of the corresponding test item according to the reference range of the called test item;

[0011] S6: Construct a visual inspection graph based on the information to be determined and the distribution interval of the inspection items.

[0012] Furthermore, the inspection value associated with the inspection item includes actual counts of multiple inspection items and / or actual percentages of multiple inspection items, wherein the sum of the percentages of multiple inspection items of the same type is equal to 1, and the actual counts of multiple inspection items of the same type include the total actual counts of that type.

[0013] Furthermore, in step S4, the standard library includes the "Establishment of Reference Ranges for Clinical Laboratory Test Items" with standard number WS / T402-2012, and the reference ranges of the test items include the count reference ranges and / or percentage reference ranges of each test item.

[0014] Further, in step S5, five endpoint values ​​of the corresponding test items are calculated according to the reference range of the called test items: the median value, plus one standard deviation value, plus two standard deviation values, minus one standard deviation value and minus two standard deviation values; the distribution interval of the test items is established according to the five endpoint values; the distribution interval of the test items includes: interval A, interval B, interval C, interval D, interval E and interval F; wherein,

[0015] Interval A is less than minus two standard deviations;

[0016] Interval B is between minus one standard deviation and minus two standard deviations;

[0017] Interval C is between minus one standard deviation and the median value;

[0018] The interval D is between double the standard deviation and the median value;

[0019] Interval E is between the value of one standard deviation and the value of two standard deviations;

[0020] Interval F is greater than two times the standard deviation.

[0021] Further, the visual inspection graphics include heat maps, radar maps and pie charts;

[0022] A bar heat map is established based on the distribution interval of the actual count sum of multiple test items of the same type. The intervals A to F of the distribution intervals are arranged on the heat map, and different colors are assigned to each interval. The actual count sum of multiple test items of the same type is marked on the heat map with arrows;

[0023] A basic chart disk with five concentric rings is constructed based on the five endpoint values ​​of the actual reference counts of multiple inspection items of the same type, and the five rings constituting the basic chart disk correspond to the colors of each interval of the heat map; a radar chart and / or pie chart is constructed on the basic chart disk according to the actual counts and / or actual percentages of the inspection items of this type.

[0024] Furthermore, when multiple inspection items of the same type include both the actual counts and the actual percentages of each inspection item, multiple sector-shaped areas with the same center, different central angles and different radii are established on the basic chart disk. The multiple sector-shaped areas form a pie chart of this type. The multiple sector-shaped areas correspond to multiple inspection items of the inspection type. The central angle of the corresponding sector-shaped area is determined according to the percentage of the inspection item, and the radius of the corresponding sector-shaped area is determined according to the actual count of the inspection item.

[0025] Furthermore, when multiple inspection items of the same type only have actual counts of each inspection item, the number of endpoints of the outer contour polygon of the radar chart is determined according to the number of each item of this type, and the actual counts of each inspection item are distributed on the radar chart and connected in sequence with straight lines to form an irregular closed loop graph.

[0026] Furthermore, text information of the standard corresponding inspection items can be displayed outside each end point of the radar chart and each sector area of ​​the pie chart, the text information including the name of the inspection item, the actual count or actual percentage, the count reference range or the percentage reference range, and the actual count or actual percentage falling into interval A is given a downward arrow mark, and the actual count or actual percentage falling into interval F is given an upward arrow mark.

[0027] A method for interpreting a physical examination report, wherein a visual inspection graph constructed according to the above method calls corresponding symptom manifestations, feelings of illness, condition analysis and nutritional recommendations in a database.

[0028] Implementing the embodiments of the present invention will have the following beneficial effects:

[0029] The concrete processing method of the physical examination report extracts information from the original pure text and pure data physical examination report, compares and analyzes the extracted basic information and the information to be determined with the standard library, and then constructs a variety of vivid visual graphics to display the same type of inspection items in one figure, which is convenient for comparing the same type of inspection items and intuitively displaying the inspection results, so that the staff or the examinees can easily obtain the information of this inspection and draw corresponding conclusions, which greatly improves the work efficiency of the staff and also lowers the reading threshold of the physical examination report for the examinees. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 is a flow chart of the present invention;

[0032] Figure 2 The reference range of the adult blood routine test items of the present invention;

[0033] Figure 3 The reference range of the children's blood routine test items of the present invention;

[0034] Figure 4 It is a visualization graph of white blood cells in a blood test of the present invention;

[0035] Figure 5 It is a visualized graph of red blood cells and platelets in the blood routine test of the present invention. DETAILED DESCRIPTION

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present invention; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present invention or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0037] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0038] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.

[0039] See attached Figure 1 - Attachment Figure 5 This embodiment discloses a method for processing a physical examination report, which includes the following steps:

[0040] S1: Collect the image of the physical examination report to obtain the physical examination report image;

[0041] S2: Recognize the physical examination report image and extract text information;

[0042] S3: Summarize and classify the text information into basic information and information to be determined, wherein the basic information includes the age of the subject, and the information to be determined includes multiple test items and test values ​​associated with the corresponding test items;

[0043] In this embodiment, the image can be obtained by taking photos or the like, and the text information in the image can be extracted with the help of existing AI technology to achieve the effect of summarization and classification.

[0044] The test values ​​associated with the test items include actual counts of multiple test items and / or actual percentages of multiple test items, wherein the sum of the percentages of multiple test items of the same type is equal to 1, and the actual counts of multiple test items of the same type include the total actual counts of this type; in this embodiment, the physical examination report of a routine blood test is taken as an example for explanation, and specifically white blood cells, red blood cells and platelets can be used as major categories of test items for explanation, for example, for white blood cells, there are test items such as white blood cell count, neutrophil count and percentage, lymphocyte count and percentage, monocyte count and percentage, eosinophil count and percentage, basophil count and percentage, and corresponding actual counts and actual percentages, wherein the white blood cell count is the total actual count of this type, and the sum of the percentages of each test item in the major category of white blood cells is equal to 1.

[0045] S4: Call the reference range of the corresponding test items of the corresponding age in the standard library according to the basic information;

[0046] The standard library includes the "Establishment of Reference Ranges for Clinical Laboratory Test Items" with the standard number WS / T402-2012. The reference ranges of the test items include the count reference ranges and / or percentage reference ranges of the test items. It should also be noted that the reference ranges can be divided into two major categories, adults and children, according to the different basic information. On this basis, the reference ranges of the corresponding test items are called. Figure 2 and attached Figure 3 The reference ranges for each blood test item in different age groups are given.

[0047] S5: Generate the distribution interval of the corresponding test item according to the reference range of the called test item. Specifically, calculate the five endpoint values ​​of the corresponding test item according to the reference range of the called test item: the middle value, plus one standard deviation value, plus two standard deviation values, minus one standard deviation value and minus two standard deviation values; establish the distribution interval of the test item according to the five endpoint values; the distribution interval of the test item includes: interval A, interval B, interval C, interval D, interval E and interval F; wherein,

[0048] Interval A is less than minus two standard deviations;

[0049] Interval B is between minus one standard deviation and minus two standard deviations;

[0050] Interval C is between minus one standard deviation and the median value;

[0051] The interval D is between double the standard deviation and the median value;

[0052] Interval E is between the value of one standard deviation and the value of two standard deviations;

[0053] Interval F is greater than two times the standard deviation.

[0054] After obtaining the actual counts of the test items in the physical examination report, based on the above distribution interval, the actual counts are placed in a specific interval and stored, and a corresponding mark is given in the subsequent graphics.

[0055] S6: Construct a visual inspection graph based on the information to be determined and the distribution interval of the inspection items; the visual inspection graph includes a heat map, a radar map and a pie chart.

[0056] A bar heat map is established based on the distribution interval of the actual count sum of multiple test items of the same type. Intervals A to F of the distribution interval are arranged on the heat map, and different colors are assigned to each interval. The actual count sum of multiple test items of the same type is marked on the heat map with arrows. Specifically, a data visualization graph of continuous data differences within a certain range is intuitively displayed through color differences or depths of the heat map. In this embodiment, a bar heat map is used for display. For example, the rightmost interval F may be displayed in red or dark red, the middle interval C and interval D may be displayed in green or light green, and the leftmost interval A may be displayed in purple or dark purple. A gradient color transition is used in the border areas between the intervals to improve the aesthetics of the heat map and the prompt effect when the data is abnormal.

[0057] A basic chart disk with five concentric rings is constructed based on the five endpoint values ​​of the actual reference counts of multiple inspection items of the same type, and the colors of the five rings constituting the basic chart disk correspond to the colors of each interval of the heat map; a radar chart and / or a pie chart is constructed on the basic chart disk according to the actual counts and / or actual percentages of the inspection items of this type; in different application scenarios, a separate radar chart can be used for display, or a radar chart and a pie chart can be used in combination for display.

[0058] For example, when multiple inspection items of the same type include both the actual counts and the actual percentages of each inspection item, multiple sector-shaped areas with the same center, different central angles and different radii are established on the basic chart plate. The multiple sector-shaped areas form a pie chart of this type. The multiple sector-shaped areas correspond to multiple inspection items of this inspection type. The central angle of the corresponding sector-shaped area is determined according to the percentage of the inspection item, and the radius of the corresponding sector-shaped area is determined according to the actual count of the inspection item.

[0059] Furthermore, when multiple inspection items of the same type only have actual counts of each inspection item, the number of endpoints of the outer contour polygon of the radar chart is determined according to the number of each item of this type, and the actual counts of each inspection item are distributed on the radar chart and connected in sequence with straight lines to form an irregular closed loop graph.

[0060] Specifically, text information of the standard corresponding inspection items can be provided outside each end point of the radar chart and each sector area of ​​the pie chart. The text information includes the name of the inspection item, the actual count or actual percentage, the count reference range or the percentage reference range, and the actual count or actual percentage falling into interval A is given a downward arrow mark, and the actual count or actual percentage falling into interval F is given an upward arrow mark.

[0061] As attached Figure 4 As shown, when the same type of test items are white blood cells in a routine blood test, the total actual count is the white blood cell count, the actual count of each item is the actual count of neutrophils, lymphocytes, monocytes, eosinophils and basophils in the white blood cells, and the percentage of each item is the percentage of neutrophils, lymphocytes, monocytes, eosinophils and basophils in the white blood cells. At this time, the white blood cell count can be displayed in the form of a heat map, and the distribution range of the actual white blood cell count is calculated according to the reference range of the actual white blood cell count. A heat map is constructed based on the interval A-interval F of the distribution interval, and the actual count of the tested white blood cells is marked on the heat map; then based on The actual count of white blood cells, i.e., the five endpoint values ​​of the sum of the actual counts of this type, establish a basic chart with five concentric circles. On the basic chart, since neutrophils, lymphocytes, monocytes, eosinophils and basophils among the white blood cells have actual counts and actual percentages, the actual percentages of neutrophils, lymphocytes, monocytes, eosinophils and basophils are used to establish multiple sector areas with different central angles on the basic chart, and the radius of the corresponding sector area is determined according to the absolute value of the corresponding actual counts of the test items such as neutrophils, lymphocytes, monocytes, eosinophils and basophils, so as to create a visual pie chart of the white blood cells.

[0062] As attached Figure 5As shown, when the same type of test items are red blood cells in a routine blood test, the actual count sum is the actual count of red blood cells, and the actual counts of each item are the hemoglobin content, hematocrit, mean red blood cell volume, mean hemoglobin amount, mean hemoglobin concentration, red blood cell distribution width CV and red blood cell distribution width SD. At this time, eight test items can be selected based on the actual count of red blood cells, hemoglobin content, hematocrit, mean red blood cell volume, mean hemoglobin amount, mean hemoglobin concentration, red blood cell distribution width CV and red blood cell distribution width SD. Since red blood cells do not have percentages, red blood cells are displayed using a radar chart. An octagonal radar chart is constructed based on the eight test items. Five endpoint values ​​of red blood cells are calculated based on the actual count of red blood cells and the reference range of the count of red blood cells. Five basic chart plates with eight-framed ring structures are determined based on the five endpoint values ​​of red blood cells. On the basis of the above, and based on the actual counts of the corresponding test items, their positions on the line connecting the corresponding endpoints and the center of the basic chart plate are determined. Finally, the corresponding positions of the eight test items are connected to form an irregular closed loop chart. When the test type is platelets in a blood routine, the method of creating a radar chart is the same as that of red blood cells, which is not described here.

[0063] Based on the above method, this embodiment also provides a method for interpreting a physical examination report, and the visual inspection graphics constructed according to the above method call the corresponding symptom manifestations, feelings of illness, condition analysis and nutritional recommendations in the database. The database can be the symptom manifestations, feelings of illness, condition analysis and nutritional recommendations of different types of different data of each project created in advance by medical staff, and finally the corresponding symptom manifestations, feelings of illness, condition analysis and nutritional recommendations are matched in the database according to the inspection results.

[0064] In general, the concrete processing method of the physical examination report extracts information from the original pure text and pure data physical examination report, compares and analyzes the extracted basic information and information to be determined with the standard library, and then constructs a variety of vivid visual graphics to display similar test items in one figure, which is convenient for comparing similar test items and intuitively displaying the test results, so that the staff or the examinees can easily obtain the information of this test and draw corresponding conclusions, which greatly improves the work efficiency of the staff and also lowers the reading threshold of the physical examination report for the examinees.

[0065] Obviously, the embodiments described above are only some embodiments of the present invention, rather than all embodiments. The preferred embodiments of the present invention are given in the accompanying drawings, but they do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific embodiments, or to perform equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of the present invention, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present invention.

Claims

1. A method for processing a physical examination report, characterized in that: The method comprises the following steps: S1: Collect the image of the physical examination report to obtain the physical examination report image; S2: Recognize the physical examination report image and extract text information; S3: Summarize and classify the text information into basic information and information to be determined, wherein the basic information includes the age of the subject, and the information to be determined includes multiple test items and test values ​​associated with the corresponding test items; S4: Call the reference range of the corresponding test items of the corresponding age in the standard library according to the basic information; S5: Generate a distribution interval of the corresponding test item according to the reference range of the called test item; S6: Construct a visual inspection graph based on the information to be determined and the distribution interval of the inspection items.

2. The method according to claim 1, characterized in that The inspection values ​​associated with the inspection items include actual counts of multiple inspection items and / or actual percentages of multiple inspection items, where the sum of the percentages of multiple inspection items of the same type is equal to 1, and the actual counts of multiple inspection items of the same type include the total actual counts of that type.

3. The method according to claim 2, characterized in that In step S4, the standard library includes the "Establishment of Reference Ranges for Clinical Laboratory Test Items" with standard number WS / T402-2012, and the reference ranges of the test items include the count reference range and / or percentage reference range of each test item.

4. The method according to claim 3, characterized in that In step S5, five endpoint values ​​of the corresponding test item are calculated according to the reference range of the called test item: the median value, plus one standard deviation value, plus two standard deviation values, minus one standard deviation value and minus two standard deviation values; The distribution intervals of the test items are established according to the five endpoint values; the distribution intervals of the test items include: interval A, interval B, interval C, interval D, interval E and interval F; wherein, Interval A is less than minus two standard deviations; Interval B is between minus one standard deviation and minus two standard deviations; Interval C is between minus one standard deviation and the median value; The interval D is between double the standard deviation and the median value; Interval E is between the value of one standard deviation and the value of two standard deviations; Interval F is greater than two times the standard deviation.

5. The method according to claim 3, characterized in that: The visual inspection graphics include heat maps, radar maps and pie charts; A bar heat map is established based on the distribution interval of the actual count sum of multiple test items of the same type. The intervals A to F of the distribution intervals are arranged on the heat map, and different colors are assigned to each interval. The actual count sum of multiple test items of the same type is marked on the heat map with arrows; A basic chart disk with five concentric rings is constructed based on the five endpoint values ​​of the actual reference counts of multiple inspection items of the same type, and the five rings constituting the basic chart disk correspond to the colors of each interval of the heat map; a radar chart and / or pie chart is constructed on the basic chart disk according to the actual counts and / or actual percentages of the inspection items of this type.

6. The method according to claim 5, characterized in that When multiple inspection items of the same type include both the actual counts and the actual percentages of each inspection item, multiple sector-shaped areas with the same center, different central angles and different radii are established on the basic chart plate. The multiple sector-shaped areas form a pie chart of this type. The multiple sector-shaped areas correspond to multiple inspection items of this inspection type. The central angle of the corresponding sector-shaped area is determined according to the percentage of the inspection items, and the radius of the corresponding sector-shaped area is determined according to the actual counts of the inspection items.

7. The method according to claim 6, characterized in that When multiple inspection items of the same type only have the actual counts of each inspection item, the number of endpoints of the outer polygon of the radar chart is determined according to the number of each item of this type, and the actual counts of each inspection item are distributed on the radar chart and connected in sequence with straight lines to form an irregular closed loop graph.

8. The method according to claim 7, characterized in that Text information of the standard corresponding inspection items can be displayed outside each end point of the radar chart and each sector area of ​​the pie chart. The text information includes the name of the inspection item, the actual count or actual percentage, the count reference range or the percentage reference range, and the actual count or actual percentage falling into interval A is given a downward arrow mark, and the actual count or actual percentage falling into interval F is given an upward arrow mark.

9. A method for interpreting a physical examination report, characterized in that: The visual inspection graph constructed according to the method described in any one of claims 1 to 8 calls up corresponding symptom manifestations, illness feelings, disease analysis and nutritional recommendations in the database.

Images