Method and system for processing alignment of diagnosis and operation codes based on medical settlement list
By combining full-document data integration with a medical knowledge graph training module, the main diagnosis and surgical codes in the medical insurance settlement list are processed automatically, solving the problems of large workload and poor accuracy in traditional manual processing, and improving the efficiency and accuracy of filling out the medical insurance settlement list.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING UNISOUND INFORMATION TECH CO LTD
- Filing Date
- 2023-12-20
- Publication Date
- 2026-06-30
AI Technical Summary
Traditional manual code verification for major surgeries and diagnoses is labor-intensive, inaccurate, and lacks standardization, resulting in low efficiency in filling out medical insurance settlement lists.
By calling the full-document data docking module to connect with the hospital's HIS system in real time, basic data tables and standard medical record tables are generated. The medical knowledge graph training module is used to configure diagnosis and surgery dictionary tables. Combined with the code matching module and diagnosis-surgery score processing module, the system automatically outputs the medical insurance standard names and codes, and generates corresponding recommendation relationships for major diagnoses and surgeries.
It enables automatic alignment of medical insurance codes for primary diagnoses and surgeries, reducing doctors' workload and improving the efficiency and accuracy of filling out medical insurance settlement lists.
Smart Images
Figure CN117522347B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of medical data processing technology, specifically to a method and system for aligning diagnostic and surgical codes based on medical billing lists. Background Technology
[0002] A medical insurance settlement statement is a data list submitted by designated medical institutions to the medical insurance department when applying for expense settlement after providing inpatient, outpatient, and other medical services. Every insured patient receives an inpatient medical insurance settlement statement upon discharge, which records the patient's total hospitalization costs, out-of-pocket expenses, and expenses reimbursed by medical insurance.
[0003] Currently, the completion of primary surgeries and primary diagnoses is crucial in the generation of medical settlement statements, as this data directly impacts medical insurance payment outcomes and DRG and DIP enrollment results. Traditionally, medical staff manually verify the codes for primary diagnoses and surgeries, resulting in a heavy workload, poor accuracy and standardization, and low efficiency in completing medical insurance settlement statements. At present, there is a lack of technology that automatically verifies diagnostic and surgical codes against medical insurance codes based on the main principles of relevant departments. Summary of the Invention
[0004] To address this issue, the present invention provides a method and system for aligning diagnostic and surgical codes based on medical settlement lists, which solves the problems of low efficiency in filling out medical insurance settlement lists due to the large workload, poor accuracy and standardization of traditional manual code matching.
[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for aligning diagnostic and surgical codes based on medical billing lists, comprising:
[0006] The full-document data docking module is invoked to connect the full-document medical record with the hospital HIS system in real time, generating a basic data table and a standard document medical record table;
[0007] The medical knowledge graph training module is invoked to configure the diagnostic dictionary and surgical dictionary tables according to the set diagnostic selection criteria.
[0008] The code matching module is invoked, and the medical knowledge graph trained from the full medical record data is used to output the corresponding medical insurance standard name and code based on the input diagnosis name and surgery name.
[0009] The diagnosis-surgery score processing module is invoked to obtain the primary diagnosis score and the primary surgical score of each patient's ICD code based on the basic data table and the standard medical record table, and according to the medical knowledge graph training module.
[0010] The diagnosis-surgery alignment processing module is invoked to generate and display the corresponding recommendation relationship between the primary diagnosis and the primary surgery based on the primary diagnosis score of each patient's ICD code and the primary surgery score of the ICD-9-CM-3 standard.
[0011] As a preferred scheme for the diagnosis and surgical code alignment processing method based on medical settlement list, the fields of the basic data table include auto-incrementing ID, hospital number, patient name, gender, age, name of admitting department, name of doctor, whether deceased, whether surgery was performed, whether it is a difficult case, whether it is a blood transfusion case, whether the surgical level is equal to level three or four, stage of medical record, name of admitting ward, discharge diagnosis, whether transferred to another department, doctor ID, bed number, number of visits, whether it is a critical case and marked as a key case;
[0012] The fields of the standard medical record form include number, admission number, document number, electronic medical record number, document name, document creation time, and document operation time.
[0013] As a preferred solution for the diagnostic and surgical code alignment processing method based on medical billing lists, the diagnostic dictionary table is configured by a group of medical experts based on data and experience. The fields of the diagnostic dictionary table include ICD-10 disease code, disease name, general hospitalization duration, health hazards, treatment costs, and disease classification.
[0014] The fields of the surgical dictionary table include the surgical ICD-9-CM-3 code, surgical name, surgical risk, surgical difficulty, and surgical cost.
[0015] As a preferred method for aligning diagnosis and surgery codes based on medical settlement lists, the following steps are taken: obtaining the hospital's medical record surgery name, surgery code, hospital's medical record diagnosis name, and diagnosis code from the hospital's medical record; obtaining the medical insurance version of the medical record surgery name and code, medical insurance version diagnosis name, and diagnosis code from the medical insurance bureau; establishing a surgery comparison table and a diagnosis comparison table; and providing recommendations based on confidence scores.
[0016] As a preferred method for aligning diagnostic and surgical codes based on medical billing lists, the calculation method for the primary diagnostic score of the diagnostic ICD code and the primary surgical score of the ICD-9-CM-3 standard is as follows:
[0017] Add one point if the patient's diagnostic cost exceeds the diagnostic cost in the diagnostic configuration table, add one point if the health hazard is high, add one point if the hospital stay is longer than the general hospital stay for the disease, add one point if the patient's surgical cost exceeds the surgical cost in the diagnostic configuration table, add one point if the surgical difficulty is high, add one point if the surgical risk is high.
[0018] Based on the admission records, diagnosis and surgery list on the homepage of the hospital's HIS system, a score is generated to produce a patient diagnosis score sheet and a surgery score sheet.
[0019] As a preferred method for aligning diagnosis and surgical codes based on medical billing lists, the patient diagnosis scoring table stores the patient's name, hospitalization record number, age, diagnosis name, diagnosis code, and diagnosis score.
[0020] As a preferred method for aligning diagnosis and surgical codes based on medical billing lists, the surgical score table stores the patient's name, hospitalization record number, age, surgical name, surgical code, and surgical score.
[0021] As a preferred method for aligning diagnosis and surgery codes based on medical billing lists, the inpatient serial number is used to associate the patient's diagnosis score table and the surgery score table, and the scores of diagnosis and surgery are sorted in reverse order to return each patient's name, inpatient serial number, and the correspondence between diagnosis and surgery.
[0022] This invention also provides a diagnostic and surgical code alignment processing system based on medical billing statements, comprising:
[0023] The full-document data integration module is used to connect with the hospital's HIS system in real time to generate basic data tables and standard document medical record tables.
[0024] The medical knowledge graph training module is used to configure diagnostic and surgical dictionary tables based on the set diagnostic selection criteria.
[0025] The coding module is used to generate a medical knowledge graph based on the full medical record data, and output the corresponding medical insurance standard name and code according to the input diagnosis name and surgery name.
[0026] The diagnosis-surgery score processing module is used to derive the primary diagnosis score and the primary surgical score of each patient's ICD code based on the basic data table and the standard medical record form, and according to the medical knowledge graph training module.
[0027] The diagnosis-surgery alignment processing module generates and displays the corresponding recommendation relationship between the primary diagnosis and the primary surgery based on the primary diagnosis score of each patient's ICD code and the primary surgery score of the ICD-9-CM-3 standard.
[0028] As a preferred solution for a diagnosis and surgical code alignment processing system based on medical billing lists, the full-document data interface module includes:
[0029] The fields in the basic data table include auto-incrementing ID, hospital number, patient name, gender, age, name of admitting department, doctor's name, whether the patient is deceased, whether surgery was performed, whether the case is a difficult case, whether the case is a blood transfusion case, whether the surgical level is equal to level three or four, stage of the case, name of the admitting ward, discharge diagnosis, whether the patient was transferred to another department, doctor's ID, bed number, number of visits, whether the case is a critical case, and cases marked as key cases.
[0030] The fields of the standard medical record form include number, admission number, document number, electronic medical record number, document name, document creation time, and document operation time.
[0031] As a preferred solution for a diagnosis and surgical code alignment processing system based on medical billing statements, the medical knowledge graph training module includes:
[0032] The diagnostic dictionary table was configured by a group of medical experts based on data and experience. The fields of the diagnostic dictionary table include ICD-10 disease code, disease name, general hospitalization duration, health hazards, treatment costs, and disease classification.
[0033] The fields of the surgical dictionary table include the surgical ICD-9-CM-3 code, surgical name, surgical risk, surgical difficulty, and surgical cost.
[0034] As a preferred solution for a diagnostic and surgical code alignment processing system based on medical billing statements, the code matching module includes:
[0035] Obtain the hospital's medical records containing the name of the surgery, surgery code, diagnosis name, and diagnosis code; obtain the medical insurance records from the medical insurance bureau containing the name of the surgery, surgery code, diagnosis name, and diagnosis code; establish a surgery comparison table and a diagnosis comparison table, and provide recommendations based on confidence scores.
[0036] As a preferred solution for a diagnosis and surgery code alignment processing system based on medical billing statements, the diagnosis-surgery score processing module includes:
[0037] The calculation methods for the primary diagnostic score of the ICD code and the primary surgical score of the ICD-9-CM-3 standard are as follows:
[0038] Add one point if the patient's diagnostic cost exceeds the diagnostic cost in the diagnostic configuration table, add one point if the health hazard is high, add one point if the hospital stay is longer than the general hospital stay for the disease, add one point if the patient's surgical cost exceeds the surgical cost in the diagnostic configuration table, add one point if the surgical difficulty is high, add one point if the surgical risk is high.
[0039] Based on the admission records, diagnosis and surgery list on the homepage of the hospital's HIS system, scores are generated to produce a patient diagnosis score sheet and a surgery score sheet;
[0040] The patient diagnosis scoring table stores the patient's name, hospitalization record number, age, diagnosis name, diagnosis code, and diagnosis score.
[0041] The surgical score table stores the patient's name, hospitalization record number, age, surgical name, surgical code, and surgical score.
[0042] As a preferred embodiment of a diagnostic and surgical code alignment processing system based on medical billing statements, the diagnostic-surgical alignment processing module includes:
[0043] The system uses the inpatient registration number to link the patient's diagnostic score table and surgical score table, sorts them in reverse order according to the scores of diagnosis and surgery, and returns each patient's name, inpatient registration number, and the correspondence between diagnosis and surgery.
[0044] This invention has the following advantages: It invokes a full-document data integration module to connect the full-document data integration module and the hospital's HIS system in real time, generating a basic data table and a standard medical record table; it invokes a medical knowledge graph training module to configure a diagnosis dictionary table and a surgical dictionary table according to the set diagnosis selection criteria; it invokes a coding module to use the medical knowledge graph trained from the full medical record data to output the corresponding medical insurance standard name and code based on the input diagnosis name and surgical name; it invokes a diagnosis-surgery score processing module to derive the primary diagnosis score and the primary surgical score according to the ICD code for each patient's diagnosis based on the basic data table and the standard medical record table, and according to the medical knowledge graph training module; and it invokes a diagnosis-surgery alignment processing module to generate and display the corresponding recommendation relationship between the primary diagnosis and the primary surgery based on the primary diagnosis score and the primary surgical score according to the ICD code for each patient's diagnosis. This invention enables the automatic alignment of medical insurance codes for primary diagnoses and major surgeries, which plays a positive role in ensuring the scientific, accurate, and standardized completion of medical settlement lists. It reduces the workload for doctors in aligning primary diagnoses and major surgeries themselves and improves the efficiency of completing medical insurance settlement lists. Attached Figure Description
[0045] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.
[0046] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.
[0047] Figure 1 This is a schematic diagram of the diagnostic and surgical code alignment processing method based on medical settlement lists provided in an embodiment of the present invention;
[0048] Figure 2 This refers to the code for generating the basic data table in the diagnostic and surgical code alignment processing method based on medical settlement lists provided in this embodiment of the invention.
[0049] Figure 3 This refers to the standard medical record form generation code in the diagnosis and surgery code alignment processing method based on medical settlement list provided in this embodiment of the invention;
[0050] Figure 4 This refers to the diagnostic dictionary table generation code in the diagnostic and surgical code alignment processing method based on medical settlement lists provided in this embodiment of the invention.
[0051] Figure 5 This refers to the code for generating the surgical dictionary table in the diagnostic and surgical code alignment processing method based on medical settlement lists provided in this embodiment of the invention.
[0052] Figure 6 This is a schematic diagram of the code matching interface for the diagnosis and surgery code alignment processing method based on medical settlement lists provided in this embodiment of the invention;
[0053] Figure 7 This is a schematic diagram of the system architecture for diagnosis and surgical code alignment processing based on medical billing lists provided in an embodiment of the present invention. Detailed Implementation
[0054] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0055] It should be stated that the medical institution fulfilled its obligation to inform the patient in accordance with the relevant provisions of the Personal Information Protection Law before providing the anonymized data. For cases requiring separate consent, separate authorization from the patient has been obtained. The data processing procedure in this application fully complies with Articles 29 and 30 of the Personal Information Protection Law.
[0056] Example 1
[0057] See Figure 1 Embodiment 1 of the present invention provides a method for aligning diagnostic and surgical codes based on medical billing lists, comprising the following steps:
[0058] S1. Call the full document data docking module to connect the full document data docking module and the hospital HIS system in real time to generate basic data table and standard document medical record table;
[0059] S2. Call the medical knowledge graph training module and configure the diagnostic dictionary table and surgical dictionary table according to the set diagnostic selection criteria;
[0060] S3. Call the code matching module and use the medical knowledge graph trained from the full medical record data to output the corresponding medical insurance standard name and code based on the input diagnosis name and surgery name.
[0061] S4. Call the diagnosis-surgery score processing module, and based on the basic data table and the standard medical record table, and according to the medical knowledge graph training module, obtain the main diagnosis score and the main surgical score of the ICD code for each patient's diagnosis, as well as the main surgical score of the ICD-9-CM-3 standard.
[0062] S5. Call the diagnosis-surgery alignment processing module to generate and display the corresponding recommendation relationship between the primary diagnosis and the primary surgery based on the primary diagnosis score of each patient's ICD code and the primary surgery score of the ICD-9-CM-3 standard.
[0063] See Figure 2 In this embodiment, the fields of the basic data table include auto-incrementing ID, hospital number, patient name, gender, age, name of admitting department, doctor's name, whether the patient is dead, whether surgery was performed, whether the case is a difficult case, whether the case is a blood transfusion case, whether the surgery level is equal to level three or four, stage of the case, name of the admitting ward, discharge diagnosis, whether the patient was transferred to another department, doctor's ID, bed number, number of visits, whether the case is a critical case, and cases marked as key cases.
[0064] See Figure 3 In this embodiment, the fields of the standard medical record form include number, admission number, document number, electronic medical record number, document name, document creation time, and document operation time.
[0065] In this embodiment, the diagnostic dictionary table is configured by a group of medical experts based on data and experience. The fields of the diagnostic dictionary table include ICD-10 disease code, disease name, general hospitalization duration, health hazards, treatment costs, and disease classification. The fields of the surgical dictionary table include surgical ICD-9-CM-3 code, surgical name, surgical risks, surgical difficulty, and surgical costs.
[0066] The diagnostic selection criteria are as follows:
[0067] General principles for selecting primary diagnoses: (1) those posing the greatest threat to the patient's health; (2) those consuming the most medical resources; (3) those affecting the longest hospital stay. General principles for selecting primary surgeries: (1) those with the greatest risk; (2) those with the highest difficulty; (3) those with the highest cost. Diagnostic and surgical dictionary tables are configured based on these principles.
[0068] See Figure 4 The diagnostic dictionary table can be used to find the corresponding ICD-10 code for each diagnosis and the degree of harm to the patient's health. The treatment cost can be used to find out which diagnosis consumes the most medical resources. The length of hospital stay for each disease can be compared with the length of hospital stay for the patient to find out which diagnosis has the longest impact on hospitalization time.
[0069] See Figure 5 The surgical dictionary table can be used to find out the corresponding ICD-9-cm3 code for each type of surgery, as well as its impact on patients, difficulty, and cost.
[0070] In this embodiment, the hospital obtains the name of the surgery, the surgery code, the diagnosis name, and the diagnosis code from the patient's medical record; the medical insurance bureau obtains the name of the surgery and the code, the diagnosis name, and the diagnosis code from the medical insurance bureau; a surgery comparison table and a diagnosis comparison table are established, and recommendations are given based on the confidence score.
[0071] See Figure 6 Based on the hospital's complete medical record data, a disease and surgery knowledge graph is trained. It can output the corresponding medical insurance version name and code according to the input diagnosis name and surgery name, and give recommendations based on the confidence score. The higher the score, the higher the accuracy.
[0072] Specifically, the first step is to obtain the surgical name and surgical code from the hospital's medical record and the surgical name and code from the medical insurance system, as well as the diagnosis name and diagnosis code from the hospital's medical record and the diagnosis name and code from the medical insurance system.
[0073] The second step involves creating surgical reference tables and diagnostic reference tables. The core implementation code is as follows:
[0074] "CREATE TABLE `chs_hos_operation` (
[0075] `id` bigint(64) NOT NULL AUTO_INCREMENT,
[0076] `admission_id` varchar(64) NOT NULL DEFAULT '' COMMENT 'Hospital admission record number',
[0077] `chs_operation_code` varchar(80) DEFAULT NULL COMMENT 'Medical Insurance Surgical Operation Code',
[0078] `chs_operation_name` varchar(100) DEFAULT NULL COMMENT 'Medical Insurance Surgical Operation Name',
[0079] `hos_operation_code` varchar(80) DEFAULT NULL COMMENT 'Hospital surgical operation code',
[0080] `hos_operation_name` varchar(100) DEFAULT NULL COMMENT 'Hospital surgical procedure name',
[0081] `create_time` datetime DEFAULT NULL COMMENT 'Creation Time',
[0082] `update_time` datetime DEFAULT NULL ON UPDATE CURRENT_TIMESTAMPCOMMENT 'update time',
[0083] PRIMARY KEY (`id`) USING BTREE,
[0084] KEY `idx_admission_id` (`admission_id`) USING BTREE
[0085] ) ENGINE=InnoDB DEFAULT CHARSET=utf8 ROW_FORMAT=COMPACT COMMENT='Surgical Comparison Table';
[0086] CREATE TABLE `chs_hos_diagnose` (
[0087] `id` bigint(64) NOT NULL AUTO_INCREMENT,
[0088] `admission_id` varchar(64) NOT NULL DEFAULT '' COMMENT 'Hospital admission record number',
[0089] `chs_diag_code` varchar(80) DEFAULT NULL COMMENT 'Medical Insurance Diagnosis Code',
[0090] `chs_diag_name` varchar(100) DEFAULT NULL COMMENT 'Medical Insurance Diagnosis Name',
[0091] `hos_diag_code` varchar(80) DEFAULT NULL COMMENT 'Hospital Diagnosis Code',
[0092] `hos_diag_name` varchar(100) DEFAULT NULL COMMENT 'Hospital Diagnosis Name',
[0093] `create_time` datetime DEFAULT NULL COMMENT 'Creation Time',
[0094] `update_time` datetime DEFAULT NULL ON UPDATE CURRENT_TIMESTAMPCOMMENT 'update time',
[0095] PRIMARY KEY (`id`) USING BTREE,
[0096] KEY `idx_admission_id` (`admission_id`) USING BTREE
[0097] ) ENGINE=InnoDB DEFAULT CHARSET=utf8 ROW_FORMAT=COMPACT COMMENT='Diagnosis Comparison Table'.
[0098] The third step is to obtain the confidence score. The core implementation code is as follows:
[0099] SELECT
[0100] c.chs_operation_code AS medicaid_operation_code,
[0101] c.chs_operation_name AS medicaid_operation_name,
[0102] COUNT(*) AS count,
[0103] ROUND((COUNT(*) / (SELECT COUNT(*) FROM chs_hos_operation WHEREhos_operation_code LIKE '%YOUR_PARTIAL_HOSPITAL_OPERATION_CODE%' OR hos_operation_name LIKE '%YOUR_PARTIAL_HOSPITAL_OPERATION_NAME%')) * 100, 4) ASpercentage
[0104] FROM chs_hos_operation h
[0105] INNER JOIN chs_hos_operation c
[0106] ON h.hos_operation_code = c.hos_operation_code OR h.hos_operation_name = c.hos_operation_name
[0107] WHERE h.hos_operation_code LIKE '%YOUR_PARTIAL_HOSPITAL_OPERATION_CODE%'
[0108] OR h.hos_operation_name LIKE '%YOUR_PARTIAL_HOSPITAL_OPERATION_CODE%'
[0109] GROUP BY c.chs_operation_code, c.chs_operation_name;
[0110] YOUR_PARTIAL_HOSPITAL_OPERATION_CODE”。
[0111] This replaces the hospital-side surgical code or name portion with the fuzzy query the user wants to find. This query will return the medical insurance surgical code and name for each matching group, as well as the number and percentage of that group (to four decimal places). The ROUND function is used to retain percentage values to four decimal places.
[0112] Example as follows:
[0113] Search: "Cardiac bypass surgery"
[0114] result:
[0115] The medical insurance website refers to it as: "Coronary artery bypass grafting"
[0116] Code: "3016001"
[0117] Confidence score: 0.9222 (high confidence)
[0118] Search: "diabetes"
[0119] result:
[0120] The medical insurance forum users are calling it "diabetes".
[0121] Code: "250.00"
[0122] Confidence score: 0.8555 (high confidence level)
[0123] This is the logic for obtaining information during surgery; the logic for obtaining information during diagnosis is the same.
[0124] The core code for the diagnostic SQL is as follows:
[0125] SELECT
[0126] c.chs_diag_code AS medicaid_diag_code,
[0127] c.chs_diag_name AS medicaid_diag_name,
[0128] COUNT(*) AS count,
[0129] ROUND((COUNT(*) / (SELECT COUNT(*) FROM chs_hos_diagnose WHERE hos_diag_code LIKE '%YOUR_PARTIAL_HOSPITAL_DIAG_CODE%' OR hos_diag_name LIKE '%YOUR_PARTIAL_HOSPITAL_DIAG_CODE%')) * 100, 4) AS percentage
[0130] FROM chs_hos_diagnose h
[0131] INNER JOIN chs_hos_diagnose c
[0132] ON h.hos_diag_code = c.hos_diag_code OR h.hos_diag_name = c.hos_diag_name
[0133] WHERE h.hos_diag_code LIKE '%YOUR_PARTIAL_HOSPITAL_DIAG_CODE%'
[0134] OR h.hos_diag_name LIKE '%YOUR_PARTIAL_HOSPITAL_DIAG_CODE%'
[0135] GROUP BY c.chs_diag_code, c.chs_diag_name;
[0136] Please replace 'YOUR_PARTIAL_HOSPITAL_DIAG_CODE' with the hospital-side diagnostic code or name part of the query you want to perform a fuzzy search for.
[0137] This query will return the medical insurance diagnosis code and name for each matching group, as well as the number and percentage of that group (to four decimal places). The ROUND function is used to retain percentage values to four decimal places.
[0138] In this embodiment, the calculation method for the primary diagnostic score of the diagnostic ICD code and the primary surgical score of the ICD-9-CM-3 standard is as follows:
[0139] Add one point if the patient's diagnostic cost exceeds the diagnostic cost in the diagnostic configuration table, add one point if the health hazard is high, add one point if the hospital stay is longer than the general hospital stay for the disease, add one point if the patient's surgical cost exceeds the surgical cost in the diagnostic configuration table, add one point if the surgical difficulty is high, add one point if the surgical risk is high.
[0140] Based on the admission records, diagnoses, and surgery lists on the homepage of the hospital's HIS system, a patient diagnosis score table and a surgery score table are generated. The patient diagnosis score table stores the patient's name, hospital admission record number, age, diagnosis name, diagnosis code, and diagnosis score. The surgery score table stores the patient's name, hospital admission record number, age, surgery name, surgery code, and surgery score.
[0141] Specifically, the diagnosis-surgery alignment processing module, based on the medical record data table and basic information, and then using the medical knowledge graph training module, derives the primary diagnosis score and the primary surgical score according to the ICD-9-CM-3 standard for each patient's diagnosis. The calculation rules are as follows:
[0142] One point is added for each patient whose diagnostic cost exceeds the diagnostic cost in the diagnostic configuration table; one point is added for a high level of health hazard; one point is added for a longer hospital stay than the general hospital stay for the disease; one point is added for each surgical cost exceeding the surgical cost in the diagnostic configuration table; one point is added for a high level of surgical difficulty; one point is added for a high level of surgical risk. Then, a patient diagnostic score sheet is generated based on the admission records of the connected HIS system and the diagnosis and surgical list on the homepage.
[0143] Specifically, the core code of the patient diagnostic scoring scale is as follows:
[0144] "CREATE TABLE patient data(
[0145] id INT AUTO_INCREMENT PRIMARY KEY,name VARCHAR(255),
[0146] serial_number VARCHAR(255),age INT,
[0147] diagnosis VARCHAR(255),
[0148] diagnosis_code VARCHAR(255),score DECIMAL(10,2)
[0149] )".
[0150] The table contains the following fields: "name" stores the patient's name, "serial_number" stores the patient's hospitalization serial number, "age" stores the patient's age, "diagnosis" stores the patient's diagnosis, "diagnosis_code" stores the patient's diagnosis code, and "score" stores the diagnosis score. The "id" field is an auto-incrementing primary key.
[0151] Specifically, the core code of the surgical scoring table is as follows:
[0152] "CREATE TABLE patient_surgery (
[0153] id INT AUTO_INCREMENT PRIMARY KEY,name VARCHAR(255),
[0154] serial_number VARCHAR(255),age INT,
[0155] surgery VARCHAR(255),
[0156] surgery_code VARCHAR(255),score DECIMAL(10,2)
[0157] )".
[0158] The above SQL statement will create a table named "patient_surgery" containing the following fields: "name" to store the patient's name, "serial_number" to store the patient's hospitalization record number, "age" to store the patient's age, "surgery" to store the patient's surgery, "surgery_code" to store the patient's surgery code, and "score" to store the surgery score. The "id" field in the table is an auto-incrementing primary key.
[0159] In this embodiment, the inpatient serial number is used to associate the patient's diagnostic score table and the surgical score table, and the data is sorted in reverse order according to the scores of diagnosis and surgery to return each patient's name, inpatient serial number, and the correspondence between diagnosis and surgery.
[0160] Specifically, the SQL code for retrieving the correspondence between diagnosis and surgery for each patient based on their score is as follows:
[0161] "SELECT pd.name, pd.serial_number, pd.diagnosis, ps.surgery FROM patient_data pd JOIN patient_surgery ps ON pd.serial_number = ps.serial_number ORDER BY pd.score DESC, ps.score DESC".
[0162] The above query associates the patient's diagnosis score table and surgical score table with the inpatient serial number, and sorts them in descending order according to the diagnosis and surgical scores (provided by the "score" field in the table). The result returns the correspondence between each patient's name, inpatient serial number, diagnosis, and surgery.
[0163] In summary, this invention utilizes a full-document data integration module to connect the full-document medical record system with the hospital's HIS system in real time, generating a basic data table and a standard medical record table. It also utilizes a medical knowledge graph training module to configure a diagnosis dictionary table and a surgical dictionary table based on set diagnostic selection criteria. Furthermore, it utilizes a coding module trained on the full medical record data to output the corresponding medical insurance standard name and code based on the input diagnosis and surgical name. Finally, it utilizes a diagnosis-surgery score processing module to derive the primary diagnosis score and the primary surgical score for each patient's ICD code, based on the basic data table and the standard medical record table, and according to the medical knowledge graph training module. Finally, it utilizes a diagnosis-surgery alignment processing module to generate and display the corresponding recommendation relationship between the primary diagnosis and the primary surgery, based on the primary diagnosis score and the primary surgical score for each patient's ICD code. This invention enables the automatic alignment of medical insurance codes for primary diagnoses and major surgeries, which plays a positive role in ensuring the scientific, accurate, and standardized completion of medical settlement lists. It reduces the workload for doctors in aligning primary diagnoses and major surgeries themselves and improves the efficiency of completing medical insurance settlement lists.
[0164] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.
[0165] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0166] Example 2
[0167] See Figure 7 Embodiment 2 of the present invention also provides a diagnostic and surgical code alignment processing system based on medical billing lists, comprising:
[0168] Full document data docking module 1 is used to connect with the hospital's HIS system in real time to generate basic data tables and standard document medical record tables;
[0169] Medical knowledge graph training module 2 is used to configure the diagnostic dictionary table and surgical dictionary table according to the set diagnostic selection criteria;
[0170] The coding module 3 is used to output the corresponding medical insurance standard name and code based on the medical knowledge graph trained from the full medical record data and the input diagnosis name and surgery name.
[0171] Diagnosis-Surgery Score Processing Module 4 is used to derive the primary diagnosis score and the primary surgical score of each patient's ICD code based on the basic data table and the standard medical record table, and according to the medical knowledge graph training module.
[0172] The diagnosis-surgery alignment processing module 5 generates and displays the corresponding recommendation relationship between the primary diagnosis and the primary surgery based on the primary diagnosis score of each patient's ICD code and the primary surgery score of the ICD-9-CM-3 standard.
[0173] In this embodiment, the full-document data docking module 1 includes:
[0174] The fields in the basic data table include auto-incrementing ID, hospital number, patient name, gender, age, name of admitting department, doctor's name, whether the patient is deceased, whether surgery was performed, whether the case is a difficult case, whether the case is a blood transfusion case, whether the surgical level is equal to level three or four, stage of the case, name of the admitting ward, discharge diagnosis, whether the patient was transferred to another department, doctor's ID, bed number, number of visits, whether the case is a critical case, and cases marked as key cases.
[0175] The fields of the standard medical record form include number, admission number, document number, electronic medical record number, document name, document creation time, and document operation time.
[0176] In this embodiment, the medical knowledge graph training module 2 includes:
[0177] The diagnostic dictionary table was configured by a group of medical experts based on data and experience. The fields of the diagnostic dictionary table include ICD-10 disease code, disease name, general hospitalization duration, health hazards, treatment costs, and disease classification.
[0178] The fields of the surgical dictionary table include the surgical ICD-9-CM-3 code, surgical name, surgical risk, surgical difficulty, and surgical cost.
[0179] In this embodiment, in the code matching module 3:
[0180] Obtain the hospital's medical records containing the name of the surgery, surgery code, diagnosis name, and diagnosis code; obtain the medical insurance records from the medical insurance bureau containing the name of the surgery, surgery code, diagnosis name, and diagnosis code; establish a surgery comparison table and a diagnosis comparison table, and provide recommendations based on confidence scores.
[0181] In this embodiment, the diagnosis-surgery score processing module 4 includes:
[0182] The calculation methods for the primary diagnostic score of the ICD code and the primary surgical score of the ICD-9-CM-3 standard are as follows:
[0183] Add one point if the patient's diagnostic cost exceeds the diagnostic cost in the diagnostic configuration table, add one point if the health hazard is high, add one point if the hospital stay is longer than the general hospital stay for the disease, add one point if the patient's surgical cost exceeds the surgical cost in the diagnostic configuration table, add one point if the surgical difficulty is high, add one point if the surgical risk is high.
[0184] Based on the admission records, diagnosis and surgery list on the homepage of the hospital's HIS system, scores are generated to produce a patient diagnosis score sheet and a surgery score sheet;
[0185] The patient diagnosis scoring table stores the patient's name, hospitalization record number, age, diagnosis name, diagnosis code, and diagnosis score.
[0186] The surgical score table stores the patient's name, hospitalization record number, age, surgical name, surgical code, and surgical score.
[0187] In this embodiment, the diagnosis-surgery alignment processing module 5 includes:
[0188] The system uses the inpatient registration number to link the patient's diagnostic score table and surgical score table, sorts them in reverse order according to the scores of diagnosis and surgery, and returns each patient's name, inpatient registration number, and the correspondence between diagnosis and surgery.
[0189] It should be noted that the information interaction and execution process between the modules of the above system are based on the same concept as the method embodiment in Embodiment 1 of this application, and the resulting technical effects are the same as those in the method embodiment of this application. For details, please refer to the description in the method embodiment shown above in this application, and it will not be repeated here.
[0190] Example 3
[0191] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium storing program code for a diagnostic and surgical code alignment processing method based on a medical billing list. The program code includes instructions for executing the diagnostic and surgical code alignment processing method based on a medical billing list as described in Embodiment 1 or any possible implementation thereof.
[0192] Computer-readable storage media can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).
[0193] Example 4
[0194] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;
[0195] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor can call the program instructions to execute the diagnostic and surgical code alignment processing method based on the medical billing list in Embodiment 1 or any possible implementation thereof.
[0196] Specifically, a processor can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.
[0197] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.
[0198] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.
[0199] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.
Claims
1. A method for processing alignment of diagnosis and operation codes based on medical billing statements, characterized by, include: The full-document data docking module is invoked to connect the full-document medical record with the hospital HIS system in real time, generating a basic data table and a standard document medical record table; The medical knowledge graph training module is invoked to configure the diagnostic dictionary and surgical dictionary tables according to the set diagnostic selection criteria. The code matching module is invoked, and the medical knowledge graph trained from the full medical record data is used to output the corresponding medical insurance standard name and code based on the input diagnosis name and surgery name. The diagnosis-surgery score processing module is invoked to obtain the primary diagnosis score and the primary surgical score of each patient's ICD code based on the basic data table and the standard medical record table, and according to the medical knowledge graph training module. The diagnosis-surgery alignment processing module is invoked to generate and display the corresponding recommendation relationship between the primary diagnosis and the primary surgery based on the primary diagnosis score of each patient's ICD code and the primary surgery score according to the ICD-9-CM-3 standard. The fields in the basic data table include auto-incrementing ID, hospital number, patient name, gender, age, name of admitting department, name of doctor, whether deceased, whether surgery was performed, whether it is a difficult case, whether it is a blood transfusion case, whether the surgery level is equal to level three or four, stage of the medical record, name of the admitting ward, discharge diagnosis, whether it was transferred to another department, doctor ID, bed number, number of visits, whether it is a critical case, and marked as a key case. The fields of the standard medical record form include: number, admission number, document number, electronic medical record number, document name, document creation time, and document operation time. Obtain the hospital's medical records containing the name of the surgery, surgery code, diagnosis name, and diagnosis code; obtain the medical insurance records from the medical insurance bureau containing the name of the surgery, surgery code, diagnosis name, and diagnosis code; establish a surgery comparison table and a diagnosis comparison table, and provide recommendations based on confidence scores. The calculation methods for the primary diagnostic score of the ICD code and the primary surgical score of the ICD-9-CM-3 standard are as follows: Add one point if the patient's diagnostic cost exceeds the diagnostic cost in the diagnostic configuration table, add one point if the health hazard is high, add one point if the hospital stay is longer than the general hospital stay for the disease, add one point if the patient's surgical cost exceeds the surgical cost in the diagnostic configuration table, add one point if the surgical difficulty is high, add one point if the surgical risk is high. Based on the admission records, diagnosis and surgery list on the homepage of the hospital's HIS system, a score is generated to produce a patient diagnosis score sheet and a surgery score sheet.
2. The medical billing invoice-based diagnosis and procedure code alignment processing method of claim 1, wherein, The diagnostic dictionary table was configured by a group of medical experts based on data and experience. The fields of the diagnostic dictionary table include ICD-10 disease code, disease name, general hospitalization duration, health hazards, treatment costs, and disease classification. The fields of the surgical dictionary table include the surgical ICD-9-CM-3 code, surgical name, surgical risk, surgical difficulty, and surgical cost. 3.The medical billing invoice-based diagnosis and procedure code alignment processing method of claim 1, wherein, The patient diagnosis scoring table stores the patient's name, hospitalization record number, age, diagnosis name, diagnosis code, and diagnosis score.
4. The medical billing invoice-based diagnosis and procedure code alignment processing method of claim 3, wherein, The surgical score table stores the patient's name, hospitalization record number, age, surgical name, surgical code, and surgical score. 5.The medical billing invoice-based diagnosis and procedure code alignment processing method of claim 4, wherein, The system uses the inpatient registration number to link the patient's diagnostic score table and surgical score table, sorts them in reverse order according to the scores of diagnosis and surgery, and returns each patient's name, inpatient registration number, and the correspondence between diagnosis and surgery.
6. A diagnosis and surgery code alignment processing system based on a medical billing statement, characterized by, include: The full-document data integration module is used to connect with the hospital's HIS system in real time to generate basic data tables and standard document medical record tables. The medical knowledge graph training module is used to configure diagnostic and surgical dictionary tables based on the set diagnostic selection criteria. The coding module is used to generate a medical knowledge graph based on the full medical record data, and output the corresponding medical insurance standard name and code according to the input diagnosis name and surgery name. The diagnosis-surgery score processing module is used to derive the primary diagnosis score and the primary surgical score of each patient's ICD code based on the basic data table and the standard medical record form, and according to the medical knowledge graph training module. The diagnosis-surgery alignment processing module generates and displays the corresponding recommendation relationship between the primary diagnosis and the primary surgery based on the primary diagnosis score of each patient's ICD code and the primary surgery score according to the ICD-9-CM-3 standard. In the full-document data integration module: The fields in the basic data table include auto-incrementing ID, hospital number, patient name, gender, age, name of admitting department, name of doctor, whether deceased, whether surgery was performed, whether it is a difficult case, whether it is a blood transfusion case, whether the surgery level is equal to level three or four, stage of the medical record, name of the admitting ward, discharge diagnosis, whether it was transferred to another department, doctor ID, bed number, number of visits, whether it is a critical case, and marked as a key case. The fields of the standard medical record form include: number, admission number, document number, electronic medical record number, document name, document creation time, and document operation time. In the code matching module: Obtain the hospital's medical records containing the name of the surgery, surgery code, diagnosis name, and diagnosis code; obtain the medical insurance records from the medical insurance bureau containing the name of the surgery, surgery code, diagnosis name, and diagnosis code; establish a surgery comparison table and a diagnosis comparison table, and provide recommendations based on confidence scores. In the diagnosis-surgery score processing module: The calculation methods for the primary diagnostic score of the ICD code and the primary surgical score of the ICD-9-CM-3 standard are as follows: Add one point if the patient's diagnostic cost exceeds the diagnostic cost in the diagnostic configuration table, add one point if the health hazard is high, add one point if the hospital stay is longer than the general hospital stay for the disease, add one point if the patient's surgical cost exceeds the surgical cost in the diagnostic configuration table, add one point if the surgical difficulty is high, add one point if the surgical risk is high. Based on the admission records, diagnosis and surgery list on the homepage of the hospital's HIS system, a score is generated to produce a patient diagnosis score sheet and a surgery score sheet.
7. The medical billing claim based diagnosis, procedure coding alignment processing system of claim 6, wherein, In the medical knowledge graph training module: The diagnostic dictionary table was configured by a group of medical experts based on data and experience. The fields of the diagnostic dictionary table include ICD-10 disease code, disease name, general hospitalization duration, health hazards, treatment costs, and disease classification. The fields of the surgical dictionary table include the surgical ICD-9-CM-3 code, surgical name, surgical risk, surgical difficulty, and surgical cost; The patient diagnosis scoring table stores the patient's name, hospitalization record number, age, diagnosis name, diagnosis code, and diagnosis score. The surgical score table stores the patient's name, hospital admission number, age, surgical name, surgical code, and surgical score. In the diagnostic-surgical alignment processing module: The system uses the inpatient registration number to link the patient's diagnostic score table and surgical score table, sorts them in reverse order according to the scores of diagnosis and surgery, and returns each patient's name, inpatient registration number, and the correspondence between diagnosis and surgery.