A Method and System for Automatic Coding of Surgical Operation Records

Abstract

The present invention discloses a method and system for automatically coding surgical operation records, including: obtaining and preprocessing the surgical operation records of a patient; selecting the AI coding function, generating a surgical coding result and its corresponding evidence fragment based on a surgical coding model; auditing the coding result and its corresponding evidence fragment in the evidence interaction module, and correcting the coding results and evidence fragments with multiple coding, incorrect coding, and missing coding, and marking the reasons for the errors; manually adjusting the order of the evidence fragments; collecting typical surgical operation records and describing the reasons for collection; and storing the coding results and evidence fragments, the audited coding results and evidence fragments, the collected surgical operation records, and the reasons for collection in the database module. The present invention can reduce the manual coding burden, improve the efficiency of medical insurance settlement, and optimize the model performance through continuous learning.

Description

Technical Field

[0001] The present invention relates to the technical field of medical event recognition, and particularly to an automatic coding method and system for surgical operation records. Background Art

[0002] In the medical field, the standardization of medical terms is an important requirement in the medical field, including the standardization of disease names, surgical operation names, drug names, etc., which is of great significance for medical research, medical insurance payment, performance evaluation of public hospitals, etc. However, due to the differences in language usage habits of different medical institutions and different clinicians, the diagnosis and treatment information in various clinical medical data generally has the problems of non-standard and inconsistent language usage, making the processing work such as data archiving and classification very complex and difficult, consuming a large amount of manpower and material resources, and it is also difficult to mine or analyze it with the latest information technologies such as big data and artificial intelligence.

[0003] To solve this problem, automatic coding technology has become a new solution in the digital scenario of medical records. With the development of artificial intelligence technology, more and more people have begun to try to apply natural language processing technology to automatic coding tasks, but the application of natural language processing technology still faces many challenges. First, the complexity, diversity and multi-modal characteristics of surgical operation records increase the difficulty of automatic coding; second, the existing technologies are insufficient in accuracy when dealing with professional terms, semantic relationships and context information; in addition, the accuracy of coding results directly affects medical insurance payment and hospital performance evaluation. Therefore, there is an urgent need for an automatic coding method and system that can efficiently process surgical records, support multi-modal data fusion and introduce an artificial review mechanism to improve the accuracy and compliance of coding. Currently, there is no method and system for automatic coding of surgical operation records on the market that cover the above characteristics. Summary of the Invention

[0004] Aiming at the above-mentioned defects of the prior art, the purpose of the present invention is to provide an automatic coding method and system for surgical operation records, which can reduce the manual coding burden, improve the efficiency of medical insurance settlement, and optimize the model performance through continuous learning, aiming to solve the problem of weak interaction between coders and automatic coding systems in the prior art.

[0005] The present invention adopts the following technical solutions to solve the technical problems:

[0006] In a first aspect, an automatic coding method for surgical operation records includes the following steps:

[0007] Step S1: Access the hospital's medical record system through a standard interface, obtain and preprocess the surgical operation records of patients, and display the results in the record interaction module;

[0008] Step S2: Select the AI coding function in the toolbar module, generate the surgical coding results and their corresponding evidence segments based on the surgical coding model, and synchronously display them in the coding module and the evidence interaction module;

[0009] Step S3: Review the coding results in the coding module and their corresponding evidence segments in the evidence interaction module, correct the coding results and evidence segments with over - coding, mis - coding, and under - coding, and mark the reasons for the errors;

[0010] Step S4: Manually adjust the order of the coding results in the coding module and their corresponding evidence segments in the evidence interaction module;

[0011] Step S5: Collect the typical surgical operation records and describe the reasons for collection;

[0012] Step S6: Save the coding results and evidence segments given by the surgical coding model, the reviewed coding results and evidence segments, the collected surgical operation records, and the reasons for collection in the database module.

[0013] Further, in step S1, if the modality of the surgical operation record is the image modality, perform image - to - text recognition; if the modality of the surgical operation record is the voice modality, perform speech - to - text recognition, and finally display it in the record interaction module in the text modality.

[0014] Further, in step S2, the surgical coding model used to generate the automatic coding results and their corresponding evidence segments should be an open - source or closed - source large - language model or other natural language processing models that have been fine - tuned and trained on the coding task; the output format of the surgical coding model should include the surgical coding results and their corresponding evidence segments in the surgical operation record.

[0015] Further, in step S2, display the coding results output by the surgical coding model and their corresponding evidence segments one by one in the coding module and the evidence interaction module; the evidence segments in the evidence interaction module will be synchronously displayed on the record interaction module and be highlighted for prompt.

[0016] Further, in step S3, the error correction of the coding results and evidence segments includes the following types:

[0017] Over - coding: The surgical coding model gives coding results and their corresponding evidence segments outside the set of correct coding results. Select the delete coding function in the toolbar module, mark that this coding result is not in the set of correct coding results, and at the same time remove the display of the evidence segment corresponding to this coding result in the record interaction module, and mark the reason for the error as over - coding;

[0018] Mis-coding: It mainly includes three types: the coding result is correct but the corresponding evidence segment is wrong, the coding result is wrong but the corresponding evidence segment is correct, and both the coding result and the corresponding evidence segment are wrong. For mis-coding, in the coding module, select the correct coding result from the coding dictionary, and at the same time, modify the corresponding evidence segment in the evidence interaction module, and mark the reason for the error as mis-coding;

[0019] Missing coding: The surgical coding model does not give some coding results in the correct coding result set. Select the new coding function in the toolbar module, and select the evidence segment corresponding to the coding result in the record interaction module. The selected evidence segment will be synchronously displayed in the evidence interaction module and separated by special symbols. The surgical coding model will generate recommended codings based on the selected evidence segment, select the correct coding result from them, and mark the reason for the error as missing coding.

[0020] Further, in step S4, the adjustment of the order of the coding result and its corresponding evidence segment is mainly based on the surgical sorting model trained with the importance sorting data for medical insurance settlement. Use it to screen out the main surgery in a series of surgeries and place it at the top of the coding result.

[0021] Further, in step S6, save the coding result and the corresponding evidence segment given by the surgical coding model, the coding result and the corresponding evidence segment after manual review, and the surgical operation records and the reasons for collection in step S5 in the database module for storage; use these wrong cases and typical cases to optimize the performance of the surgical coding model and correct the model results using the method of retrieval enhancement generation.

[0022] In the second aspect, a surgical operation record automatic coding system for implementing the surgical operation record automatic coding method described in any one of the above, includes:

[0023] A record interaction module, used to display the patient's surgical operation records read from the standard interface, synchronously highlight the evidence segments corresponding to the coding results in the evidence interaction module, and after selecting a segment of the surgical operation record, append it to the corresponding evidence segment in the evidence interaction module;

[0024] An evidence interaction module, used to record the evidence segments corresponding to each coding result. When one coding result corresponds to multiple evidence segments, separate the evidence segments with special symbols. After appending or deleting evidence segments, the changes will be synchronously displayed in the record interaction module. When correcting errors, record the reasons for the errors in the evidence interaction module;

[0025] A coding module, used to record the coding results of the patient's surgical operation records, and the coding results should be the most appropriate surgical operation terms selected from the mapping dictionary;

[0026] A function bar module for providing automatic coding function, deleting coding function, adding new coding function and expanding functions.

[0027] A database module for saving the coding results given by the surgical coding model and the corresponding evidence segments, as well as the coding results after manual review and the corresponding evidence segments. The saved data is used for optimizing the model performance.

[0028] Furthermore, the evidence interaction module is associated with the coding module. The evidence segments corresponding to each coding result in the coding module should be in the same order in the evidence interaction module as the coding result in the coding module. When the coder rearranges the order, the coding result and its corresponding evidence segments should be moved synchronously; the record interaction module is synchronized with the evidence interaction module. The evidence segments recorded in the evidence interaction module should be highlighted synchronously in the record interaction module. For newly added or deleted coding results, the highlighting of the corresponding evidence segments should be updated or cancelled synchronously in the record interaction module.

[0029] In a third aspect, a terminal device includes a memory, a processor, and a program of an automatic coding method for surgical operation records stored in the memory and executable on the processor. When the processor executes the program of the automatic coding method for surgical operation records, the steps of the automatic coding method for surgical operation records described in any one of the above are implemented. Beneficial effects

[0030] The present invention provides an automatic coding method and system for surgical operation records. By automatically generating coding results through an AI model and combining a manual review mechanism, the coding efficiency and accuracy are significantly improved, multi-modal data processing is supported, and functions such as manual error correction, order rearrangement, and continuous optimization of the model are provided. The system design is user-friendly and has strong function extensibility, effectively solving the problem of medical data standardization, providing high-quality data support for medical research, medical insurance payment, and hospital performance evaluation, and promoting the digital transformation of the medical industry. Description of the drawings

[0031] Figure 1 is a flowchart of the automatic coding method of the present invention.

[0032] Figure 2 is a relationship diagram of each system module of the present invention. Detailed implementation manners

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention. Embodiment

[0034] Reference Figure 1 , this embodiment provides an automatic coding method for surgical operation records, including the following steps:

[0035] Step S1: Access the hospital's medical record system through a standard interface, obtain and preprocess the patient's surgical operation records, and display the results in the record interaction module;

[0036] In the preprocessing of the input surgical records, if the modality of the surgical operation record is the image modality, perform image text recognition; if the modality of the surgical operation record is the voice modality, perform speech text recognition, and finally display it in the text modality in the record interaction module. If a patient has undergone multiple surgeries during this hospitalization, the record interaction module will also display the surgical operation records of multiple surgeries for subsequent coding and correction.

[0037] Step S2: Select the AI coding function in the toolbar module, generate a surgical coding result based on the surgical coding model, save the coding result and its corresponding evidence segment in the coding module and the evidence interaction module respectively, and synchronously display the evidence segment in the record interaction module;

[0038] Specifically, the surgical coding model used to generate the automatic coding result and its corresponding evidence segment should be an open-source or closed-source large language model or other natural language processing models that have been fine-tuned and trained on the coding task; the output format of the surgical coding model should include the surgical coding result and its corresponding evidence segment in the surgical operation record.

[0039] For example, the format of the instruction data for constructing the coding task is as follows:

[0040] Input: "Which standard surgical terms are contained in the following text, and which segments in the text do they correspond to? Output in json format\n{Text modality surgical record data}";

[0041] Output: "{"{Standard surgical term 1}": ["{Text segment 1 corresponding to the standard surgical term 1}",…],…}".

[0042] Further optimize the technical solution. First, the system retrieves the historical surgical operation records and their corresponding coding results that are most similar to the current surgical operation record text from the vector database to fully utilize the experience of existing data to optimize the coding process of new data. In this way, the system can perform reference matching based on historical coding knowledge to improve the accuracy and consistency of coding. Subsequently, the system inputs the current surgical operation record text and the retrieved most similar historical coding results into the automatic coding module. On this basis, the system constructs specific prompts and calls the large language model to generate new coding results to ensure the intelligence and automation of the coding process.

[0043] Specifically, the core data stored in the vector database includes the surgical operation record text, its vectorized representation, and the correct coding results reviewed by the coder. The construction of the vector database follows the following steps: First, for each surgical operation record, an embedding model that supports multiple languages and is optimized for sentence similarity (such as bge-m3) is used to encode the preprocessed text to generate a high-dimensional text vector representation to ensure the efficiency and accuracy of the retrieval process. Subsequently, a vector database is established based on the generated text vector representation, and the surgical operation record text, the corresponding text vector, and the correct coding results confirmed by the coder are stored. At the same time, an index is constructed on the text vector field to support subsequent efficient and accurate similarity retrieval.

[0044] After retrieving the similar historical surgical operation records and their corresponding coding results, this step uses a specific template to assemble prompts to guide the large language model for text classification. The structural composition of the template-assembled prompts is as follows:

[0045] "{Role definition label}: {Statement defining the role of the large language model as a surgical operation record coder}\n{Example label}:\n{Example surgical operation record and its corresponding coding result}\n {Input label}: {Statement guiding the large model to code the surgical operation record}\n{Input surgical operation data}\n{Coding result output label}: "

[0046] Among them, {Example text and classification result} can include a single example or multiple retrieved similar historical surgical operation records and their corresponding coding results.

[0047] In some specific embodiments, the specific content of the template is determined according to the structural composition of the template-assembled prompts as follows:

[0048] "You are an excellent surgical operation record coding expert. You are familiar with various surgical operations and their codings. Now you need to identify the surgical operation coding and its evidence from the input surgical operation record, and you should output it in json format. You can refer to the examples provided in

Example

[0049]

Example

[0050] Example 1: {Surgical operation record 1}

[0051] Output 1: {Coding result}

[0052] Example 2: {Surgical operation record 2}

[0053] Output 2: {Coding result}

[0054]

Data to be classified

[0055] Which standard surgical terms are contained in the following text, and which fragments in the text do they correspond to? Output in JSON format.

[0056] {Input surgical operation record}

[0057]

Output

[0058] After the output of the surgical coding model, specifically, the system first endeavors to parse the JSON - formatted text output by the surgical coding model. Once it is found that the text cannot be directly converted into the standard JSON format, the system will automatically enable predefined rules to correct the text to ensure that a structurally complete and compliant JSON text is finally obtained.

[0059] Next, in the successfully parsed JSON content, for each recorded surgical term, the system will compare and verify it with the built - in standard surgical term library. If a surgical term cannot find a corresponding match in the standard term library, the system uses the Jaccard Similarity as a measurement index to calculate the similarity degree of the term with all entries in the standard term library and selects the closest one as the candidate match. The Jaccard Similarity calculation formula is:

[0060]

[0061] Where A is the character set of the surgical terms generated by the model, B is the character set of the standard surgical terms in the standard surgical term library, represents the set A and the set B is the number of elements in the intersection of the two sets, that is, the number of common characters; represents the set A and the set B is the number of elements in the union of the two sets, that is, the total number of all different characters in the two sets.

[0062] To ensure data consistency and accuracy, the system sets a similarity threshold for the above process. If, after comparative analysis, even the standard surgical term with the highest similarity fails to meet this threshold requirement, it indicates that the surgical record and its associated evidence fragments may lack sufficient precision or applicability, and the system will choose to ignore this record to maintain the quality and reliability of the entire data.

[0063] After processing the output results of the surgical coding model, the system will display the coding results output by the surgical coding model and their evidence fragments one by one in the coding module and the evidence interaction module respectively; the evidence fragments in the evidence interaction module will be synchronously displayed on the record interaction module and be highlighted for prompt.

[0064] Step S3: The coder reviews the coding results in the coding module and the corresponding evidence fragments of the coding results in the evidence interaction module, and can correct errors such as over - coding, mis - coding, and under - coding for the coding results and evidence fragments. For the coding results with errors, the coder can mark the reasons for the errors.

[0065] Specifically, the error correction work covers the following situations:

[0066] Over - coding: When the coding results generated by the surgical coding model exceed the set of correct coding results, that is, there are redundant coding results and their corresponding evidence fragments, the coder needs to manually delete these unnecessary codings. Such errors may be caused by the AI failing to correctly perform "merged coding", incorrect annotation of the text by the AI, incorrect writing by the doctor in the surgical record, etc. In addition, other unforeseen factors may also lead to such problems. All such situations are collectively referred to as "over - coding".

[0067] Mis - coding: If the surgical coding model provides coding results and corresponding evidence fragments that are similar but inaccurate to the set of correct coding results, the coder needs to manually modify these coding results and adjust their evidence fragments accordingly. This type of error is usually caused by the AI's inaccurate recognition of the surgical approach, incorrect annotation of the text by the AI, or the doctor's non - standard writing of the surgical record. In addition, there may be other factors leading to this type of error, and such situations are collectively classified as "mis - coding".

[0068] Under - coding: If the surgical coding model fails to provide some necessary parts of the set of correct coding results, the coder can use the insert coding function in the toolbar module to add the missing coding results and their related evidence fragments. This situation may be caused by the AI failing to recognize the content that needs additional coding, failing to fully cover the marked text, or omissions in the surgical record content provided by the doctor. In addition, there are other possible reasons for such errors, which are collectively referred to as "under - coding".

[0069] In addition to the above classifications, coders can also add detailed remarks for each type of error to more precisely describe the specific circumstances of the error and the basis for correction, thereby ensuring the professionalism and accuracy of the entire coding process. In this way, not only can the quality of the data be improved, but also reliable support can be provided for subsequent data analysis and medical decision-making.

[0070] During the process of error correction, the coder can select specific surgical record texts in the record interaction module and append them to the evidence segments corresponding to the relevant coding results. This function ensures that all necessary information is accurately included in the evidence segments, facilitating subsequent review and processing.

[0071] Step S4: The coder can manually adjust the order of the coding results in the coding module and the corresponding evidence segments in the evidence interaction module;

[0072] Specifically, after completing the correction of the output results of the surgical coding model, the coder can manually rearrange the surgical coding results according to the output of the surgical sorting model. The main purpose of this function is to optimize the sorting of the coding results generated by the surgical coding model according to the importance of medical insurance settlement. Specifically in terms of operation, the coder can click on a certain coding result and drag it up and down to adjust its order to achieve the most reasonable arrangement. Usually, the coding of the main surgery is placed at the top of all coding results because the main surgery often has a crucial impact on the settlement of the overall medical expenses.

[0073] In this way, the system not only supports the precise correction of the original coding results but also allows for the flexible adjustment of the order of the coding results according to actual needs, thus better meeting the requirements in aspects such as medical insurance settlement. Such a design fully takes into account the professionalism and complexity of medical data processing, helping to improve the efficiency and accuracy of the entire workflow. In addition, this flexible adjustment mechanism also facilitates dealing with the possible differences in specific requirements between different regions or institutions, enhancing the adaptability and practicality of the system.

[0074] Step S6: The coder saves the coding results and evidence segments given by the surgical coding model, the coding results and evidence segments after the coder's review, the surgical operation records collected by the coder, and the reasons for collection in the database module.

[0075] Further optimize the technical solution, save the coding results given by the surgical coding model and the corresponding evidence segments, the coding results after manual review by the coder and the corresponding evidence segments, as well as the surgical operation records and collection reasons collected by the coder in the database module for storage; these error cases and typical cases can be used to optimize the performance of the surgical coding model and correct the model results using the method of retrieval-augmented generation.

[0076] Specifically: the system will first accurately write the coding results processed by the coder into the hospital's medical record system database, ensuring that all updated coding information can be reflected in the medical records in a timely manner, providing a reliable basis for clinical decision-making, medical insurance settlement, and patient management.

[0077] At the same time, the system will also record the coding results initially generated by the surgical coding model, including the coding content and its corresponding evidence segments, and will detail all error types marked by the coder and their specific reasons. In this way, not only can we comprehensively understand the performance of the surgical coding model, but also identify common error patterns, laying a foundation for subsequent data analysis and model optimization. These detailed records support the evaluation of the performance of the surgical coding model from multiple perspectives, helping to make targeted adjustments and optimizations, thereby continuously improving the accuracy and efficiency of the surgical coding model.

[0078] In addition, the detailed records also support the internal quality control process and external audit requirements of the hospital. They provide the necessary documentary support for checking the compliance, accuracy, and consistency of the coding work, helping to improve the overall quality of medical services. By saving the original output of the surgical coding model and the correction records of the coder, the system enables subsequent data analysis, making it possible to continuously improve the surgical coding model based on actual operation feedback. This method effectively combines the advantages of artificial intelligence and professional judgment, promoting the development of the medical information management system to a higher level, not only improving work efficiency but also enhancing data reliability. Embodiment

[0079] Reference Figure 2 Furthermore, the present invention also provides an automatic coding system for surgical operation records for implementing the automatic coding method for surgical operation records described in any one of the above, including:

[0080] A record interaction module for displaying the patient's surgical operation records read from the standard interface, synchronously highlighting the evidence segments corresponding to the coding results in the evidence interaction module, and after selecting a segment of the surgical operation record, appending it after the corresponding evidence segment in the evidence interaction module;

[0081] An evidence interaction module, which is used to record the evidence segments corresponding to each coding result. When a coding result corresponds to multiple evidence segments, the evidence segments are separated by special symbols. After adding or deleting evidence segments, the changes will be synchronously displayed in the record interaction module. When correcting errors, the coder can record the reasons for the errors in the evidence interaction module;

[0082] A coding module, which is used to record the coding results of the patient's surgical operation records. The coding results should be the most appropriate surgical operation terms selected from the mapping dictionary, and the mapping dictionary refers to the standard surgical operation terms and their corresponding codes issued by national functional departments or professional associations;

[0083] A function bar module, which is used to provide the above-mentioned automatic coding function, delete coding function, add coding function and can be functionally extended, such as a favorite function that can mark special surgical operation records and their coding results, and an AI dialogue function that obtains coding information by communicating with a generative artificial intelligence model, etc.;

[0084] A database module, which is used to save the coding results given by the surgical coding model and the corresponding evidence segments, as well as the coding results and the corresponding evidence segments after manual review by the coder, and the saved data is used to optimize the model performance.

[0085] Specifically, the evidence interaction module is associated with the coding module. The evidence segments corresponding to each coding result in the coding module should be in the same order in the evidence interaction module as the coding result in the coding module. When the coder rearranges the order, the coding result and its corresponding evidence segments should be moved synchronously; the record interaction module is synchronized with the evidence interaction module. The evidence segments recorded in the evidence interaction module should be synchronously highlighted in the record interaction module. For the added or deleted coding results, the highlighting of the corresponding evidence segments should be updated or cancelled synchronously in the record interaction module. Embodiment

[0086] This embodiment provides a terminal device, which includes a memory, a processor, and a program of an automatic coding method for surgical operation records stored in the memory and executable on the processor. When the processor executes the program of the automatic coding method for surgical operation records, the steps of the automatic coding method for surgical operation records described in any one of the above are implemented.

[0087] The terminal device may include one or more processors, a memory, and a computer program stored in the memory and executable on the one or more processors. For example, it is a surgical operation record automatic coding system. When the one or more processors execute the computer program, each step in the embodiments of a surgical operation record automatic coding method can be implemented. Alternatively, when the one or more processors execute the computer program, the functions of each module in the embodiments of a surgical operation record automatic coding system can be implemented, which is not limited herein.

[0088] In one embodiment, 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, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0089] In one embodiment, the memory may be an internal storage unit of the electronic device, such as the hard disk or memory of the electronic device. The memory may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory may also include both the internal storage unit and the external storage device of the electronic device. The memory is used to store the computer program and other programs and data required by the terminal device. The memory may also be used to temporarily store the data that has been output or will be output.

[0090] Those skilled in the art can understand that the structure of the above-mentioned terminal device is only a part of the structure related to the solution of the present invention, and does not constitute a limitation on the terminal device to which the solution of the present invention is applied. The specific terminal device may include more or fewer components than those described in the above requirements, or combine some components, or have a different component arrangement.

[0091] In the description of this specification, the descriptions referring to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for automatically encoding surgical operation records, characterized in that: The steps include: Step S1: Access the hospital's medical record system through a standard interface, obtain and pre-process the patient's surgical operation records, and display the results in the record interaction module; Step S2: Select the AI ​​coding function in the toolbar module, generate the surgical coding results and their corresponding evidence fragments based on the surgical coding model, and display them synchronously in the coding module and the evidence interaction module; Step S3: reviewing the coding results in the coding module and the corresponding evidence fragments in the evidence interaction module, and correcting the errors of the coding results and evidence fragments that are over-coded, wrongly coded, or omitted, and marking the causes of the errors; Step S4: manually adjusting the coding results in the coding module and the order of the corresponding evidence fragments in the evidence interaction module; Step S5: Collect typical surgical operation records and describe the reasons for collection; Step S6: storing the coding results and evidence fragments given by the surgical coding model, the reviewed coding results and evidence fragments, the collected surgical operation records and the reasons for collection in the database module; In step S3, the error correction performed on the encoding result and the evidence fragment includes the following types: Multiple coding: The surgical coding model gives a coding result outside the correct coding result set and its corresponding evidence fragment. Select the delete coding function in the toolbar module to mark the coding result as not in the correct coding result set. At the same time, the evidence fragment corresponding to the coding result is removed from the record interaction module and the error cause is marked as multiple coding; Wrong coding: mainly includes three types: the coding result is correct but the corresponding evidence segment is wrong, the coding result is wrong but the corresponding evidence segment is correct, and there are errors in both the coding result and the corresponding evidence segment. For wrong coding, the correct coding result is selected from the coding dictionary in the coding module, and the corresponding evidence segment is modified in the evidence interaction module, and the error cause is marked as wrong coding; Omission: The surgical coding model does not give some coding results in the correct coding result set. Select the new coding function in the toolbar module, and select the evidence segment corresponding to the coding result in the record interaction module. The selected evidence segment will be synchronously displayed in the evidence interaction module and separated by special symbols. The surgical coding model will generate recommended codes based on the selected evidence segment, select the correct coding result from it, and mark the cause of the error as omission.

2. The method for automatic coding of surgical operation records according to claim 1, characterized in that: In step S1, if the modality of the surgical operation record is an image modality, image text recognition is performed; if the modality of the surgical operation record is a sound modality, voice text recognition is performed, and finally the record is displayed in the text modality in the record interaction module.

3. The method for automatic coding of surgical operation records according to claim 2, characterized in that: In step S2, the surgical coding model used to generate automatic coding results and their corresponding evidence fragments should be an open source or closed source large language model or other natural language processing model that has been fine-tuned and trained on the coding task; the output format of the surgical coding model should include the surgical coding results and their corresponding evidence fragments in the surgical operation records.

4. The method for automatic coding of surgical operation records according to claim 1, characterized in that: In step S2, the coding results output by the surgical coding model and their corresponding evidence fragments are displayed one by one in the coding module and the evidence interaction module; the evidence fragments in the evidence interaction module will be synchronously displayed on the record interaction module and highlighted.

5. The method for automatic coding of surgical operation records according to claim 1, characterized in that: In step S4, the order of the coding results and their corresponding evidence fragments is adjusted mainly based on the surgery ranking model trained with the medical insurance settlement importance ranking data, which is used to screen out the main surgery in a series of surgeries and put it at the top of the coding results.

6. The method for automatic coding of surgical operation records according to claim 1, characterized in that: In step S6, the coding results and corresponding evidence fragments given by the surgical coding model, the coding results and corresponding evidence fragments after manual review, and the surgical operation records and reasons for collection collected in step S5 are saved in the database module for storage; These wrong examples and typical cases are used to optimize the performance of the surgical coding model and the model results are corrected using retrieval-enhanced generation.

7. An automatic coding system for surgical operation records, characterized in that: A method for automatically encoding surgical operation records according to any one of claims 1 to 6, comprising: The record interaction module is used to display the patient surgical operation records read from the standard interface, and simultaneously highlight the evidence fragments corresponding to the encoding results in the evidence interaction module. After selecting a surgical operation record fragment, it is appended to the corresponding evidence fragment in the evidence interaction module; The evidence interaction module is used to record the evidence fragments corresponding to each coding result. When a coding result corresponds to multiple evidence fragments, special symbols are used to separate the evidence fragments. After adding or deleting evidence fragments, the changes will be synchronously displayed in the recording interaction module. When correcting errors, the causes of the errors will be recorded in the evidence interaction module. The coding module is used to record the coding result of the patient's surgical operation record. The coding result should be the most appropriate surgical operation noun selected from the mapping dictionary; Function bar module, used to provide automatic encoding function, delete encoding function, add encoding function and perform function expansion; The database module is used to save the coding results and corresponding evidence fragments given by the surgical coding model and the coding results and corresponding evidence fragments after manual review. The saved data is used for tuning the model performance.

8. The automatic coding system for surgical operation records according to claim 7, characterized in that: The evidence interaction module is associated with the encoding module, and the evidence fragment corresponding to each encoding result in the encoding module should be in the same order in the evidence interaction module as the encoding result in the encoding module. When the coder rearranges the order, the encoding result and its corresponding evidence fragment should be moved synchronously; the record interaction module is synchronized with the evidence interaction module, and the evidence fragment recorded in the evidence interaction module should be synchronously highlighted in the record interaction module. For newly added or deleted encoding results, the highlighting of the corresponding evidence fragment should be synchronously updated or cancelled in the record interaction module.

9. A terminal device, characterized in that: The terminal device includes a memory, a processor, and a program of a method for automatic encoding of surgical operation records stored in the memory and executable on the processor. When the processor executes the program of the method for automatic encoding of surgical operation records, the steps of the method for automatic encoding of surgical operation records as described in any one of claims 1 to 6 are implemented.

Images