Electrocardiogram report diagnosis conclusion sequence detection method, equipment and medium

Abstract

The invention relates to an electrocardio report diagnosis conclusion sequence detection method and device and a medium, and the method comprises the steps: constructing an electrocardio diagnosis entry sequence table which comprises each standard diagnosis entry and a corresponding standard sequence code; obtaining a manual diagnosis conclusion and splitting the manual diagnosis conclusion into a plurality of diagnosis conclusions according to rows; for each split diagnosis conclusion, matching the split diagnosis conclusion with a standard diagnosis entry in an electrocardiogram diagnosis entry sequence table, extracting a standard sequence code corresponding to the matched standard diagnosis entry, and binding the standard sequence code with the corresponding diagnosis conclusion; sorting all the extracted standard sequence codes; and judging whether the sequences of the bound diagnosis conclusions are consistent or not based on the sequences of the standard sequence codes, and if not, adjusting. According to the method, conclusion writing in the electrocardiogram report diagnosis process can be standardized, and quality control checking is carried out on all diagnosed report conclusions afterwards, so that the accuracy of electrocardiogram diagnosis is improved.

Description

Technical Field

[0001] The present invention relates to the field of electrocardiogram report analysis, and in particular to a method, device and medium for sequential detection of electrocardiogram report diagnostic conclusions. Background Art

[0002] An electrocardiogram (ECG) is a noninvasive test method for recording the electrical activity of the heart. It uses electrodes on the surface of the skin to capture and record the tiny electrical impulses generated by the heart every time it beats. The heart's electrical conduction system is responsible for controlling the rhythm and rate of the heartbeat. This process begins with the heart's natural pacemaker, the sinoatrial node. The electrical impulse generated by the sinoatrial node first propagates to the atria, causing atrial contraction. This stage is manifested as a P wave on the electrocardiogram. Subsequently, the electrical impulse is transmitted to the His bundle through the atrioventricular node, and then to the ventricles through the left and right bundle branches, causing ventricular contraction. This stage is manifested as a QRS complex wave on the electrocardiogram. Finally, ventricular repolarization produces a T wave, marking the end of a heartbeat cycle. The order of electrocardiogram conduction also determines the order of electrocardiogram interpretation and report writing. How to ensure the accuracy of electrocardiogram interpretation is crucial for clinical practice. Due to the different levels and habits of different diagnostic doctors or because of manual selection of entries and lack of attention when writing, it is easy to appear out of order, which may not only lead to misleading diagnostic conclusions, but also have a negative impact on doctors' diagnosis and treatment. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes a method, device and medium for detecting the sequence of electrocardiogram report diagnosis conclusions.

[0004] The specific plan is as follows:

[0005] A method for sequentially detecting electrocardiogram report diagnosis conclusions comprises the following steps:

[0006] S1: Construct an ECG diagnostic term sequence table, which includes each standard diagnostic term and the corresponding standard sequence code. The standard sequence code is composed of the diagnostic category sequence number a and the term sequence number b;

[0007] S2: Obtain manual diagnosis conclusions and split them into multiple diagnosis conclusions by row;

[0008] S3: for each split diagnosis conclusion, after matching it with the standard diagnosis terms in the ECG diagnosis terms sequence table, extract the standard sequence code corresponding to the matched standard diagnosis terms, and bind the standard sequence code to the corresponding diagnosis conclusion;

[0009] S4: sort all the extracted standard sequence codes in ascending order according to the diagnostic category serial number a, and in ascending order according to the entry serial number b if the diagnostic category serial numbers a are the same;

[0010] S5: Sort each diagnostic conclusion according to the order of the bound standard sequence codes, and determine whether the sorted order is the same as the arrangement order of the diagnostic conclusion in the manual diagnosis conclusion before splitting. If they are the same, mark the order as qualified and end; otherwise, adjust the row where the diagnostic conclusion is located according to the order of the bound standard sequence codes, and prominently mark the adjusted diagnostic conclusion.

[0011] Further, the format of the standard sequence code is a.b; Step S4 uses the bubble sort algorithm to sort all standard sequence codes in ascending order during sorting.

[0012] Further, the Jaccard similarity matching algorithm is used when matching the diagnostic conclusion with the standard diagnostic terms in the electrocardiogram diagnosis term list.

[0013] Further, the obtained manual diagnosis conclusion is the data input by the doctor in real time; Steps S2 - S5 are executed every time a new row of diagnostic conclusion is input.

[0014] Further, the obtained manual diagnosis conclusion comes from historical reports; multiple historical reports are obtained, and based on the manual diagnosis conclusions in each historical report, the method of Steps S2 - S5 is used to identify the reports with qualified orders in each historical report, adjust the reports with unqualified orders, and calculate and display the corresponding qualification rate based on the proportion of reports with qualified orders in the historical reports.

[0015] An electrocardiogram report diagnostic conclusion order detection terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method in the above - mentioned embodiment of the present invention.

[0016] A computer - readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps of the method in the above - mentioned embodiment of the present invention.

[0017] By adopting the above - mentioned technical solution, the present invention can standardize the conclusion writing in the electrocardiogram report diagnosis process, and conduct quality control verification on all diagnosed report conclusions afterwards to improve the accuracy of electrocardiogram diagnosis. Brief Description of the Drawings

[0018] Figure 1 Shown is the flowchart of the method in Embodiment 1 of the present invention.

[0019] Figure 2 Shown is the schematic diagram of the real - time detection application in this embodiment.

[0020] Figure 3 Shown is the schematic diagram of the post - event detection application in this embodiment. Detailed Implementation Modes

[0021] To further illustrate each embodiment, the present invention provides accompanying drawings. These drawings are part of the disclosure of the present invention, mainly used to illustrate the embodiments, and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation modes and the advantages of the present invention.

[0022] The present invention will be further described below in conjunction with the accompanying drawings and specific implementation modes.

[0023] Embodiment 1:

[0024] The embodiment of the present invention provides a method for detecting the order of electrocardiogram report diagnosis conclusions. As Figure 1 shown, the method includes the following steps:

[0025] S1: Construct an electrocardiogram diagnosis entry order table, which includes each standard diagnosis entry and the corresponding standard order code. The standard diagnosis entry is the keyword corresponding to the diagnosis conclusion, and the standard order code is jointly composed of the diagnosis category number a and the entry number b. The diagnosis category numbers a of different standard diagnosis entries under the same diagnosis category are the same, and the entry numbers b are different.

[0026] As Figure 1 shown is a schematic diagram of the electrocardiogram diagnosis entry order table adopted in this embodiment. The format of the standard order code therein is a.b. Through this coding format, the sorting of the standard order codes can be conveniently carried out according to the size.

[0027] Standard sequence code Diagnostic category Standard diagnostic entry 1.0 Heart rhythm category -- 1.1 Heart rhythm category Sinus rhythm 1.2 Heart rhythm category Normal electrocardiogram 1.3 Heart rhythm category Sinus arrhythmia 1.4 Heart rhythm category Sinus bradycardia …… 2.0 Critical value -- 2.1 Critical value Acute myocardial infarction 2.2 Critical value Pulmonary embolism 2.3 Critical value Third-degree atrioventricular block …… 5.0 Atrioventricular block -- 5.1 Atrioventricular block First-degree atrioventricular block 5.2 Atrioventricular block Second-degree atrioventricular block ……

[0028] S2: Obtain the manual diagnosis conclusion and split it into multiple diagnosis conclusions line by line.

[0029] The presentation of the manual diagnosis conclusion in the report is usually one line corresponding to one diagnosis conclusion. Therefore, after obtaining the manual diagnosis conclusion, it can be split into multiple diagnosis conclusions line by line.

[0030] S3: For each split diagnosis conclusion, after matching it with the standard diagnosis entry in the electrocardiogram diagnosis entry order table, extract the standard order code corresponding to the matched standard diagnosis entry, and bind the standard order code to the corresponding diagnosis conclusion.

[0031] In this embodiment, the Jaccard similarity matching algorithm is used for matching. In specific implementation, the text of the diagnosis conclusion to be matched and the standard diagnosis entry can be converted into word sets, and then the Jaccard similarity is calculated:

[0032]

[0033] Among them, A and B respectively represent the word sets of each diagnostic conclusion and standard diagnostic entry.

[0034] The standard sequence code corresponding to the standard diagnostic entry can be found in the electrocardiogram diagnostic entry sequence table.

[0035] S4: Sort all the extracted standard sequence codes in ascending order according to the diagnostic category number a from small to large, and when the diagnostic category number a is the same, sort them in ascending order according to the entry number b.

[0036] In this embodiment, since the format of the standard sequence code is a.b, it can be directly sorted in ascending order by the bubble sort algorithm for all standard sequence codes.

[0037] S5: Sort each diagnostic conclusion according to the order of the bound standard sequence code, and determine whether the sorted order is consistent with the arrangement order in the manual diagnostic conclusion before splitting. If it is consistent, mark the order as qualified and end; otherwise, adjust the row where the diagnostic conclusion is located according to the order of the bound standard sequence code, and perform a prominent annotation on the adjusted diagnostic conclusion (such as changing the font color to red).

[0038] There are two application methods in the implementation process of the above method:

[0039] (1) Real-time detection

[0040] The manual diagnostic conclusion obtained in this application scenario is the data input by the doctor in real time. In this scenario, whenever a new line of diagnostic conclusion is input, the steps of S2 - S5 are executed once, so that the doctor can timely know whether the filling position of the newly filled (one line) diagnostic conclusion is correct. As Figure 2 shown is a real-time monitoring scenario.

[0041] (2) Post-event detection

[0042] The manual diagnostic conclusion obtained in this application scenario comes from historical reports. In this scenario, multiple historical reports are obtained. Based on the manual diagnostic conclusions in each historical report, the method of steps S2 - S5 is used to identify the reports with qualified order in each historical report, and the reports with unqualified order are adjusted. Based on the proportion of the reports with qualified order in the historical reports, the corresponding qualification rate is calculated and displayed. The historical reports can be the historical reports of the same doctor, so that the qualification rate of a certain doctor can be counted, or they can be the historical reports of the same hospital, so that the qualification rate of a certain hospital can be counted. The specific application method can be set according to requirements. As Figure 3 shown is a post-event detection scenario.

[0043] The following uses an example to illustrate the application of the above method.

[0044] The obtained manual diagnosis conclusion is split into three diagnosis conclusions, namely: first-degree atrioventricular block A1, sinus rhythm A2, and acute inferior wall myocardial infarction A3, corresponding to the first row, the second row, and the third row respectively. The Jaccard similarity matching algorithm is used to match with the standard diagnosis terms in the electrocardiogram diagnosis term sequence table, and the matching results are as follows: the standard sequence code of the term matched by A1 is 5.1, the standard sequence code of the term matched by A2 is 1.1, and the standard sequence code of the term matched by A3 is 2.1. After ascending sorting of 5.1, 1.1, and 2.1 using the bubble sorting algorithm, the result is 1.1, 2.1, 5.1. Therefore, the sorting of the bound diagnosis results should be A2, A3, A1, which is inconsistent with the arrangement order in the manual diagnosis conclusion before splitting. Therefore, the diagnosis conclusion is marked as unqualified, and A2 is adjusted to the first row, A3 is adjusted to the second row, and A1 is adjusted to the third row.

[0045] Embodiment 2:

[0046] The present invention also provides an electrocardiogram report diagnosis conclusion sequence detection terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above method embodiment of Embodiment 1 of the present invention are implemented.

[0047] Furthermore, as an executable solution, the electrocardiogram report diagnosis conclusion sequence detection terminal device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electrocardiogram report diagnosis conclusion sequence detection terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above composition structure of the electrocardiogram report diagnosis conclusion sequence detection terminal device is only an example of the electrocardiogram report diagnosis conclusion sequence detection terminal device, and does not constitute a limitation on the electrocardiogram report diagnosis conclusion sequence detection terminal device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electrocardiogram report diagnosis conclusion sequence detection terminal device may also include input / output devices, network access devices, buses, etc. The embodiments of the present invention do not make limitations in this regard.

[0048] Further, as an executable solution, the so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the electrocardiogram report diagnosis conclusion sequence detection terminal device, and connects various parts of the entire electrocardiogram report diagnosis conclusion sequence detection terminal device through various interfaces and lines.

[0049] The memory can be used to store the computer program and / or module. By running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory, the processor realizes various functions of the electrocardiogram report diagnosis conclusion sequence detection terminal device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0050] The present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method in the above embodiments of the present invention are realized.

[0051] If the modules / units integrated in the electrocardiogram report diagnosis conclusion sequence detection terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), and software distribution medium, etc.

[0052] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, those skilled in the art should understand that various changes can be made to the present invention in terms of form and details without departing from the spirit and scope of the present invention defined by the appended claims. All such changes are within the protection scope of the present invention.

Claims

1. A method for detecting the sequence of electrocardiogram report diagnosis conclusions, characterized in that: The following steps are involved: S1: Construct an ECG diagnostic term sequence table, which includes each standard diagnostic term and the corresponding standard sequence code. The standard sequence code is composed of the diagnostic category sequence number a and the term sequence number b; S2: Obtain manual diagnosis conclusions and split them into multiple diagnosis conclusions by row; S3: for each split diagnosis conclusion, after matching it with the standard diagnosis terms in the ECG diagnosis terms sequence table, extract the standard sequence code corresponding to the matched standard diagnosis terms, and bind the standard sequence code to the corresponding diagnosis conclusion; S4: sort all the extracted standard sequence codes in ascending order according to the diagnostic category serial number a, and in ascending order according to the entry serial number b if the diagnostic category serial numbers a are the same; S5: Sort each diagnostic conclusion in the order of the bound standard sequence coding, and determine whether the sorted order is consistent with the arrangement order in the manual diagnostic conclusion before splitting. If they are consistent, the marking order is qualified and the process ends; otherwise, adjust the row where the diagnostic conclusion is located in the order of the bound standard sequence coding, and mark the adjusted diagnostic conclusion prominently.

2. The method for detecting the sequence of electrocardiogram report diagnosis conclusions according to claim 1, characterized in that: The format of the standard sequence code is ab; in step S4, a bubble sort algorithm is used to sort all the standard sequence codes in ascending order.

3. The method for detecting the sequence of electrocardiogram report diagnosis conclusions according to claim 1, characterized in that: The Jaccard similarity matching algorithm is used to match the diagnosis conclusion with the standard diagnosis terms in the ECG diagnosis term sequence table.

4. The method for detecting the sequence of electrocardiogram report diagnosis conclusions according to claim 1, characterized in that: The artificial diagnosis conclusion obtained is the data input by the doctor in real time; each time a new line of diagnosis conclusion is input, steps S2-S5 are executed once.

5. The method for detecting the sequence of electrocardiogram report diagnosis conclusions according to claim 1, characterized in that: The manual diagnosis conclusions obtained come from historical reports; multiple historical reports are obtained, and based on the manual diagnosis conclusions in each historical report, the method of steps S2-S5 is used to identify the reports with qualified sequences in each historical report, and the reports with unqualified sequences are adjusted. Based on the proportion of reports with qualified sequences in the historical reports, the corresponding pass rate is calculated and displayed.

6. A terminal device for sequential detection of electrocardiogram report diagnosis conclusions, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the methods of claims 1 to 5 when executing the computer program.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images