Medical insurance early warning auditing method and system

Abstract

The invention provides a medical insurance early warning auditing method and system, and belongs to the technical field of data processing, and the method comprises the steps: obtaining a data source of a target database corresponding to a target management system in response to the recognition that the target management system has a data updating request, the target management system being a system associated with the medical insurance early warning auditing system; performing keyword extraction on the data source of the target database to obtain a keyword group; matching the keyword group with an auditing rule base to obtain a target auditing rule matched with a data source of a target database, wherein the auditing rule base is a rule base customized by a hospital; and performing early warning on the data updating request in the target management system based on the target auditing rule. According to the invention, early warning can be carried out before medical insurance auditing and during medical insurance auditing, and normal operation of the system is ensured.

Description

Technical Field

[0001] The present disclosure belongs to the field of data processing technology, and more specifically, to a medical insurance early warning review method and system. Background Art

[0002] At present, the procurement and use of the medical insurance early warning and review system in hospitals is a relatively new management method. The third-party commercial medical information technology companies that cooperate with them generally transform the hospital HIS system, embed the medical insurance early warning and review system in the HIS system, and use the intelligent review engine of the review system to review the hospital's medical and charging behaviors to achieve the purpose of medical insurance fund review. However, there are great application drawbacks in the application of this model. Generally, the medical insurance early warning and review systems purchased in hospitals are semi-finished products, which need to be continuously optimized and adjusted during the operation of the hospital to operate well. There is a problem of "mainly post-audit, and insufficient pre-warning and interception". For example, the long review time of large medical insurance expenses affects clinical medical work, the system is inconvenient and cannot take into account the efficiency of patient visits and medical insurance approval, etc., resulting in the system's inability to strictly implement the medical insurance review policy, and even interferes with and affects normal clinical diagnosis and treatment behaviors, which ultimately causes the problem that the medical insurance early warning and review system cannot be used in the hospital. Summary of the invention

[0003] The purpose of the present invention is to provide a medical insurance early warning review method and system, which can provide early warning before and during medical insurance review to ensure the normal operation of the system.

[0004] A first aspect of the embodiments of the present disclosure provides a medical insurance early warning review method, including: In response to identifying that there is a data update request in the target management system, obtaining a data source of a target database corresponding to the target management system, wherein the target management system is a system associated with the medical insurance early warning and review system; Extracting keywords from the data source of the target database to obtain keyword groups; Matching the keyword group with an audit rule library to obtain a target audit rule that matches the data source of the target database, wherein the audit rule library is a rule library customized by the hospital; Based on the target audit rules, an early warning is issued for the data update request in the target management system.

[0005] A second aspect of the embodiments of the present disclosure provides a medical insurance early warning review system, including: A data acquisition module, for acquiring a data source of a target database corresponding to the target management system in response to identifying that there is a data update request in the target management system, wherein the target management system is a system associated with the medical insurance early warning and review system; A feature extraction module, used to extract keywords from the data source of the target database to obtain keyword groups; A matching module, used for matching the keyword group with an audit rule library to obtain a target audit rule that matches the data source of the target database, wherein the audit rule library is a rule library customized by the hospital; An early warning module is used to issue an early warning to the data update request in the target management system based on the target audit rule.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned medical insurance early warning review method when executing the computer program.

[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned medical insurance early warning review method are implemented.

[0008] The beneficial effects of the medical insurance early warning review method and system provided by the embodiments of the present disclosure are: On the one hand, the present disclosure significantly improves the efficiency and accuracy of medical insurance data review. By automatically extracting keyword groups and matching them with the review rule library, the system can quickly determine the applicable review rules and issue real-time warnings for data update requests. This not only reduces the workload of manual review, but also avoids the adverse effects of reviewing after a problem occurs, thereby ensuring the accuracy and compliance of medical insurance business data.

[0009] On the other hand, this disclosure effectively reduces the risk of loss and violation of medical insurance funds. Through the early warning mechanism, the system can promptly detect potential data risks and violations, and remind relevant personnel to conduct further review and processing, which helps hospitals to promptly correct non-compliant medical insurance business operations and prevent the abuse and loss of medical insurance funds, thereby ensuring the security and sustainability of medical insurance funds. At the same time, this disclosure also provides hospitals with more scientific and standardized medical insurance management methods, which helps to improve the hospital's medical insurance management level and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flowchart of a medical insurance early warning review method provided in one embodiment of the present disclosure; Figure 2 A schematic diagram of the operation flow of a medical insurance early warning and review system provided in one embodiment of the present disclosure; Figure 3 A management flow chart of a hospital's medical insurance early warning and review system provided in an embodiment of the present disclosure; Figure 4 A structural block diagram of a medical insurance early warning and review system provided in an embodiment of the present disclosure; Figure 5 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A flowchart of a medical insurance early warning review method provided in an embodiment of the present disclosure, the method comprising: S101: In response to identifying that a data update request exists in a target management system, a data source of a target database corresponding to the target management system is obtained, where the target management system is a system associated with a medical insurance early warning and review system.

[0015] In this embodiment, the target management system is a specific management system, which can be a medical information management system within the hospital (HIS resident doctor station, HIS resident nurse station, emergency system, etc.), a medical insurance fee settlement system, etc.

[0016] The target management system can establish a connection with the medical insurance early warning review system through a data interface. The main function of the target management system is to manage various business data, and changes in these data may have an impact on the medical insurance early warning review. For example, when a doctor prescribes a new examination item or adjusts the treatment plan for a patient, the target management system needs to record these changes and pass the relevant information to the subsequent processing flow when a data update request is made to ensure that the medical insurance review can be judged based on the latest information.

[0017] A data update request is a signal or instruction that indicates that the data in the target management system needs to be updated. It can be triggered by the business logic within the system or by external users (such as medical staff, medical insurance management personnel, etc.). For example, when a medical staff modifies the patient's diagnosis in the HIS resident doctor station system, the system will generate a data update request. Common triggering scenarios include but are not limited to medical staff prescribing drugs at the resident doctor station, emergency medical staff registering patient transfers in the emergency system, and medical insurance fee review timeouts affecting subsequent process advancement.

[0018] The target database is where the target management system stores data. It contains various business data required for the operation of the system. These data are organized and stored in a certain logical structure (such as the table structure of a relational database). For example, in a hospital's medical management system, the target database can contain multiple data tables such as patient basic information table, medical service record table, and medical insurance reimbursement expense table.

[0019] The medical insurance early warning and review system is used to provide early warning and review of medical insurance-related businesses. It analyzes medical insurance data (such as medical expenses, whether treatment items comply with medical insurance policies, etc.) to identify possible medical insurance violation risks or unreasonable medical insurance reimbursement in advance and conduct review and processing. For example, it can check whether the treatment items provided by the hospital to patients are within the scope of medical insurance reimbursement, and whether the medical insurance reimbursement amount meets the prescribed ratio.

[0020] In this embodiment, the medical insurance early warning and review system will continuously monitor the target management system. Since the target management system and the medical insurance early warning and review system are associated through the data interface, when the target management system is identified to have a data update request, the medical insurance early warning and review system can obtain the data source of the target database corresponding to the target management system. The data source includes various types of medical insurance-related business data stored in the target management system, the processing time nodes of each business, etc. By obtaining the data source, the medical insurance early warning and review system can issue early warnings and reviews of medical insurance business situations according to preset rules and standards, so as to determine whether there is a risk of medical insurance violations or unreasonable reimbursement, thereby ensuring the compliance of medical insurance business and the security of medical insurance funds.

[0021] S102: extracting keywords from the data source of the target database to obtain keyword groups.

[0022] In this embodiment, keyword extraction refers to automatically extracting words or phrases that can represent the main content of the text from text data. Common keyword extraction methods include statistical methods (such as word frequency-inverse document frequency TF-IDF algorithm), machine learning methods (such as using a neural network model for keyword prediction), clustering algorithm-based methods (such as using K-Means clustering algorithm) and rule-based methods (such as extracting keywords according to specific part-of-speech tags and grammatical rules).

[0023] Keyword extraction helps improve data processing efficiency and information retrieval capabilities, and helps the system quickly locate and obtain key information from large amounts of data.

[0024] Keyword groups are a set of keywords extracted from the data source of the target database through keyword extraction technology. These keywords can reflect the main content and characteristics of the data source to a certain extent. For example, keyword groups extracted from data sources related to medical insurance reimbursement may include "medical insurance restrictions", "medical insurance reimbursement amount", "reimbursement process", "medical insurance catalogue", etc.

[0025] Keyword phrases can be used as a concise representation of data sources to facilitate further analysis and processing of data. In practical applications, keyword phrases can be used to build indexes to quickly retrieve relevant data; they can also be used in data mining and machine learning tasks to help models better understand the characteristics and patterns of data.

[0026] S103: Match the keyword group with the audit rule library to obtain the target audit rule that matches the data source of the target database, and the audit rule library is a rule library customized by the hospital.

[0027] In this embodiment, the audit rule base is a collection of a series of audit rules customized by the hospital based on its own business needs, medical insurance policy requirements, and management specifications. These rules are stored in a specific form and are used to determine whether medical insurance-related data is compliant. Each rule in the rule base clearly specifies the applicable conditions and corresponding processing methods. For example, when the audit time for a certain medical scenario is greater than 120s, an error message will be directly prompted, and the clinic will be informed that there are medical insurance violations. Click Return to modify and contact the hospital medical insurance office staff for manual review.

[0028] The content of the audit rule library is rich and diverse, covering rules in multiple aspects such as medical insurance reimbursement process, reimbursement scope, drug use specifications, rationality of medical service items, etc. These rules can be set based on numerical ranges, such as the upper limit of reimbursement amount and drug dosage limit; they can also be set based on logical relationships, such as the treatment items corresponding to a certain disease must meet a specific combination, etc.

[0029] Exemplarily, the audit rules of the audit rule library are arranged as follows: Serial number-Rule instance-Audit content-Remarks 1- Restricted to children-Children and age-Violations For example: Intravenous infusion (children 6 years old and under) The age limit is 7 years old; Intravenous injection (children 6 years old and below) Age limit 7 years old; Doppler blood pressure monitoring in children is limited to age 14 years.

[0030] 2-Gender-Restricted Items-Gender-Violation For example: Tamsulosin hydrochloride extended-release capsules are limited to men Gynecological Qianjin Capsules are only for women Clotrimazole vaginal expansion suppository is limited to women 3-Limited outpatient / inpatient use items-Medical treatment methods-Violations For example: General outpatient consultation fees are limited to outpatient The consultation fee of well-known experts is limited to outpatient clinics Hospitalization examination fee is limited to hospitalization 4- Daily Charge Limit for Projects - Daily Charge Quantity - Violations For example: Coronary angiography is limited to 1 time Anterior chamber paracentesis is limited to 1 time Uterine tamponade limited to 1 time 5- Daily Charge Limit for Projects - Daily Charge Amount - Violations For example: Coronary angiography is limited to 1 time Anterior chamber paracentesis is limited to 1 time Uterine tamponade limited to 1 time 6- The consistency between medical materials and surgical items - Are there any associated costs - Violations For example: functional dressings rely on general medical services, general examination and treatment, community health services and preventive health care programs, other medical service programs, or burn dressing changes; Oral and maxillofacial general surgery materials rely on oral orthognathic surgery, oral plastic surgery, oral and maxillofacial surgical treatment, oral trauma surgery, oral and maxillofacial general surgery, oral tumor surgery or oral implant surgery; Vascular sheath-dependent transvascular intervention, off-pump coronary artery bypass grafting, coronary artery bypass grafting + valve replacement, atrial septal defect repair, or transcatheter aortic valve implantation.

[0031] 7- Relationship between main and secondary projects-Are there any related expenses-Violations Example: Level I Care - Child (Additional Charge) Dependent on Level I Care Clinical blood storage fees depend on ABO blood typing (cardiac method) Monitoring during anesthesia General anesthesia 8- Relationship between hospitalization days and nursing level- Charge quantity and days- Violation 9- Relationship between hospitalization days and bed fees- Number of charges and days- Violations 10- Relationship between hospitalization days and hospitalization examination fees - Number of charges and days - Violations 11- Mutually Exclusive Fees- Daily Mutually Exclusive Relationship Items- Violations Example: Duplication of charges for intensive care and advanced care Duplication of charges for local infiltration anesthesia and local infiltration anesthesia (topical anesthesia) Superficial tumor resection and neuraxial anesthesia duplication charges The target audit rule is a specific audit rule that matches the data source of the target database after matching the keyword group with the audit rule library. These rules are selected based on the characteristics and business scenarios of a specific data source and will be used to audit the data in the data source. For example, if the data source is data about medical insurance hospitalization expense reimbursement, the matched target audit rule may be "The reimbursement standard for nursing expenses in hospitalization expenses shall not exceed [X] yuan per day."

[0032] In this embodiment, first, keywords are extracted from the data source of the target database to obtain keyword groups that can highly summarize the core content of the data source. Secondly, the extracted keyword groups are matched with the rules in the audit rule library. The matching process uses specific algorithms and logic. This algorithm can be a simple string matching, that is, checking whether the keywords appear in the text description of the rules; or it can be a more complex semantic matching algorithm, considering the meaning of the keywords, context, and semantic relevance to the rules. Finally, after the matching process, the system will filter out rules with a high correlation with the keyword groups from the audit rule library. These rules are the target audit rules that match the data source of the target database.

[0033] By determining the target audit rules through keyword groups, we can quickly and accurately find applicable audit rules for the data source of the target database, improve the efficiency and accuracy of medical insurance data audits, and confirm the compliance of the hospital's medical insurance business. If there are any non-compliance situations, early warnings can be issued in a timely manner.

[0034] S104: issuing an early warning for data update requests in the target management system based on the target audit rules.

[0035] In this embodiment, early warning refers to the process of sending a prompt message to relevant personnel or the system when it is found that the data update may not comply with the rules after checking and evaluating the data update request in the target management system according to the target audit rules. Early warning can be presented in a variety of ways, such as system pop-up prompt window, sending email notification, generating early warning report, etc. For example, when the medical insurance reimbursement amount involved in the data update request exceeds the limit set by the target audit rules, the system will pop up a prompt window to inform the operator that the update may be risky.

[0036] The purpose of the early warning is to promptly detect potential data risks and violations, and remind relevant personnel to conduct further verification and processing, so as to ensure the accuracy and compliance of medical insurance business data and avoid possible medical insurance fund losses and violation risks.

[0037] Exemplary, reference Figure 2 , Figure 2 A schematic diagram of the operation flow of the medical insurance early warning and review system provided for an embodiment of the present disclosure. After the patient is admitted to the hospital, the doctor at the resident doctor station issues a medical order. After the intelligent review system monitors the data update request of the resident doctor station, it obtains the patient's corresponding personal information, medical diagnosis information, and medical orders for prior review. If the review of the medical order or the review of the medical expenses is unreasonable, an early warning message will be sent to the doctor at the resident doctor station, pointing out the unreasonableness and re-issuing the medical order. If the medical order and medical expenses are both reasonable, the system will be transferred to in-process monitoring. If the system's in-process monitoring is reasonable, it will be transferred to post-event supervision. If the in-process supervision is unreasonable, an early warning message will be sent to the department to remind the department to handle it and transfer it to post-event supervision. If the post-event supervision is reasonable, the patient can be arranged to transfer to another department or be discharged. If the system's post-event supervision is unreasonable, a violation interception will be carried out and the relevant departments will be reminded. The relevant departments will handle the violations, issue a transfer application, and add the patient to the severe whitelist.

[0038] It can be concluded from the above that, on the one hand, the present disclosure significantly improves the efficiency and accuracy of medical insurance data review. By automatically extracting keyword groups and matching them with the review rule library, the system can quickly determine the applicable review rules and issue real-time warnings for data update requests. This not only reduces the workload of manual review, but also avoids the adverse effects caused by reviewing after a problem occurs, thereby ensuring the accuracy and compliance of medical insurance business data.

[0039] On the other hand, this disclosure effectively reduces the risk of loss and violation of medical insurance funds. Through the early warning mechanism, the system can promptly detect potential data risks and violations, and remind relevant personnel to conduct further review and processing, which helps hospitals to promptly correct non-compliant medical insurance business operations and prevent the abuse and loss of medical insurance funds, thereby ensuring the security and sustainability of medical insurance funds. At the same time, this disclosure also provides hospitals with more scientific and standardized medical insurance management methods, which helps to improve the hospital's medical insurance management level and service quality.

[0040] In one embodiment of the present disclosure, the data source of the target database includes department information and diagnosis information.

[0041] Keyword extraction is performed on the data source of the target database to obtain keyword groups, including: Based on the pre-constructed department classification keyword library, the department information is matched and extracted to obtain the first keyword group, and based on the clustering algorithm model, the diagnosis information is keyword extracted to obtain the second keyword group.

[0042] A keyword group is obtained based on the first keyword group and the second keyword group.

[0043] In this embodiment, the pre-built department classification keyword library includes the standard names, abbreviations, aliases and professional terms of various departments such as clinical departments, medical technology departments, auxiliary departments, etc. For example, for "cardiovascular department", its keywords include "cardiology department", "cardiovascular department", "cardiology department" and related disease diagnosis and treatment keywords such as "coronary heart disease" and "arrhythmia"; department information includes department name, special identification of department, etc.

[0044] Based on the pre-built department classification keyword library, the department information is matched and extracted to obtain the first keyword group, including: Based on the pre-built department classification keyword library, keywords are extracted for each department in the department information, and a department keyword association matrix is ​​established. The matrix elements represent the degree of association between keywords of different departments, and the degree of association is obtained by analyzing the information between different departments in the historical medical insurance data.

[0045] The first keyword group is obtained according to the keywords corresponding to each department and the department keyword association matrix.

[0046] The information between different departments in the historical medical insurance data includes the frequency of business collaboration, disease referral relationships, and the flow of medical insurance expenses. In the process of medical insurance early warning review, the department keyword association matrix is ​​used to conduct a comprehensive analysis of complex diagnosis and treatment data involving multiple departments. If it is found that the association between departments deviates significantly from the historical rules, an early warning can also be triggered to effectively monitor the rationality and standardization of medical insurance use between departments.

[0047] From the above, it can be concluded that this embodiment realizes the precise extraction and correlation analysis of department information by constructing a department classification keyword library and a department keyword association matrix, improves the accuracy and efficiency of keyword extraction, facilitates the comprehensive analysis of complex diagnosis and treatment data in the medical insurance early warning review process, and effectively monitors the rationality and standardization of medical insurance use among departments.

[0048] In one embodiment of the present disclosure, keywords are extracted from the diagnostic information based on a clustering algorithm model to obtain a second keyword group, including: Determines the amount of data for diagnostic information.

[0049] When the data volume of the diagnostic information is less than the first preset threshold, the K value of the clustering algorithm model is determined by using the elbow method, and the initial point of the clustering algorithm model is randomly generated; Keywords are extracted from the diagnostic information based on the clustering algorithm model to obtain a second keyword group.

[0050] When the data volume of the diagnostic information is greater than or equal to a first preset threshold, a density-based spatial clustering algorithm is used to determine the number of clusters of the clustering algorithm model; the local density of each data point in the diagnostic information is calculated, and an initial point of the clustering algorithm model is determined based on the local density; Keywords are extracted from the diagnostic information based on the clustering algorithm model to obtain a second keyword group.

[0051] In this embodiment, the clustering algorithm model is an unsupervised learning algorithm model that can divide the data points in the data set into different groups or clusters according to similarity, so that the data points in the same cluster have high similarity, while the data points between different clusters have large differences. The clustering algorithm model can mine the inherent structure and rules in the data by clustering the diagnostic information, and help extract the keywords that reflect the core content of the diagnostic information, so as to better understand and process the information.

[0052] Diagnostic information includes detailed information related to the diagnosis of the patient's condition, such as disease name, symptom description, diagnostic basis, test results and other text data. The second keyword group is a group of representative words or phrases obtained by extracting keywords from the diagnostic information using a clustering algorithm model. The second keyword group can summarize the main content of the diagnostic information and reflect the key features and key points of the diagnosis of the condition.

[0053] Data volume refers to the number of data points or the size of the text contained in the diagnostic information. In the present embodiment, data volume is an important basis for determining the clustering algorithm model parameters and initial points in which manner. Different data volumes require different processing methods to ensure the accuracy and efficiency of the clustering algorithm. Therefore, by determining the data volume of the diagnostic information, a more appropriate clustering strategy can be selected to obtain a better keyword extraction effect.

[0054] The first preset threshold is a pre-set data volume standard value, which is used to distinguish the size of the diagnostic information data volume, so as to decide to use different methods to process the clustering algorithm model. This threshold is set according to actual business needs and experience, and different types of hospitals may have different thresholds.

[0055] The elbow method is a method for determining the optimal number of clusters (K value) in a clustering algorithm. This method calculates the error (such as the sum of squared errors) of the clustering model under different K values ​​and plots the K value and the error into a curve. The curve usually presents an elbow-like shape, and the K value corresponding to the inflection point (elbow point) of the curve is considered to be the optimal number of clusters. When the amount of diagnostic information data is less than the first preset threshold, the initial point of the clustering algorithm can be randomly determined as the initial center of each cluster.

[0056] The density-based spatial clustering algorithm is a clustering algorithm based on the density of data points. It determines the clustering structure by examining the density around the data points. In this embodiment, when processing large-scale data, the density-based spatial clustering algorithm can more accurately reflect the distribution of data, overcome the limitations of some traditional clustering algorithms (such as K-Means algorithm) on data shape and distribution, and thus obtain more reasonable clustering results, providing a more reliable basis for keyword extraction.

[0057] In this embodiment, in the density-based spatial clustering algorithm, local density is used to determine the relationship between the core points of the cluster and the data points. Data points with higher local density are often regarded as the core of the cluster. By determining the initial point of the clustering algorithm model based on local density, the distribution characteristics of the data can be better reflected, and the clustering effect and the accuracy of keyword extraction can be improved.

[0058] From the above, it can be concluded that the present invention can flexibly select the clustering method according to the data volume of the diagnostic information. For small data volumes, the elbow method is used to determine the K value, and for large data volumes, a density-based spatial clustering algorithm is used, thereby improving the accuracy and efficiency of keyword extraction and optimizing the processing flow of diagnostic information.

[0059] In one embodiment of the present disclosure, the review rule base includes a drug review rule base and a process review rule base; The keyword group is matched with the audit rule library to obtain the target audit rules that match the data source of the target database, including: Matching the keyword group with the drug review rule library to obtain a first target review rule that matches the data source of the target database; Matching the keyword group with the process audit rule library to obtain a second target audit rule that matches the data source of the target database; The first target audit rule and the second target audit rule constitute the target audit rule.

[0060] In this embodiment, the rules in the drug review rule library are customized based on multiple factors such as medical insurance policies, drug use specifications, clinical treatment guidelines, etc., and are used to provide advance warning for medical insurance business involving drugs. For example, the rules may include the target of the drug, the scope of drug reimbursement (such as which drugs belong to Class A and Class B of medical insurance, and which are self-funded drugs), drug dosage restrictions (reasonable drug dosages for patients with different diseases and different age groups), drug combination rules (which drugs can be used in combination and which are prohibited from being used in combination), etc.

[0061] For example, taking coenzyme Q10 as an example, this drug is limited to emergency and rescue use; after the patient is admitted to the hospital, the system detects that the doctor at the resident doctor station has issued a new medical order. The medical order contains a judgment on the patient's condition. When the patient meets the conditions (the system sets the definition of emergency and rescue diagnosis: unconsciousness, coma, etc.; the system sets the definition of emergency and rescue costs: major rescue, medium rescue, minor rescue costs, etc.), the drug can be prescribed if the conditions are met; if it does not meet the drug review rules set by the system, the system will directly intercept it in advance.

[0062] For example, taking ulinastatin as an example, this drug is limited to acute pancreatitis and chronic recurrent pancreatitis. After the patient is admitted to the hospital, the system monitors that the doctor at the resident doctor station has issued a new medical order. The medical order contains a judgment on the patient's condition and the prescribed drugs. When the patient meets the conditions (the system sets the diagnosis definition of acute pancreatitis and chronic recurrent pancreatitis: diagnostic keywords pancreatitis, pancreatic enlargement, pancreatic effusion; diagnostic codes K85, K86), the drug can be prescribed if the conditions are met; if it does not meet the drug review rules set by the system, the system will directly intercept it in advance.

[0063] For example, taking the structured fat emulsion (20%) / amino acid (16) / glucose (13%) injection as an example, this drug needs to undergo nutritional risk screening, and it will only be paid for hospitalized patients who are clearly at nutritional risk and cannot supplement adequate nutrition through diet or "enteral nutrition". After the patient was admitted to the hospital, the system monitored that the doctor at the resident doctor's station had issued a new medical order. The medical order contains a judgment on the patient's condition and the prescribed drugs. When the patient meets the conditions (the system stipulates that the patient must first open a nutritional risk screening and nutritional assessment medical order, and the drug can be prescribed after reviewing the medical order for this item), the drug can be prescribed if the conditions are met; if it does not meet the drug review rules set by the system, the system will directly intercept it in advance.

[0064] The process review rule base is a collection of medical insurance business process review rules. These rules cover the time nodes of each link of the entire medical insurance business process, from patient registration, medical consultation, examination, treatment to settlement. When patients perform hospitalization orders, hospitalization charges, exit / transfer to other departments at the resident doctor workstation and resident nurse workstation, due to the high medical insurance costs and many charging items, there is an overtime review, and the system's continuous review affects clinical medical work. By matching the keyword group with the process review rule base, a second target review rule that matches the data source of the target database is obtained; then, based on the second target review rule, an early warning is issued for the data update request in the target management system.

[0065] For example, when the system receives a data update request (status update), the system determines whether to issue an early warning by comparing the time it takes to review a certain medical scenario with the preset value. When the review takes more than 120 seconds, the system directly prompts an error and informs the clinic that there are medical insurance violations. Click Return to modify and contact the hospital medical insurance office staff for manual review. When the review takes less than or equal to 120 seconds, the system is set not to give up the review and automatically skip due to a review timeout.

[0066] From the above, it can be concluded that this embodiment achieves accurate advance warning of medical insurance business by constructing two major audit rule bases for drugs and processes, effectively avoiding illegal medical insurance operations, while improving audit efficiency, ensuring the smooth progress of medical processes, and reducing medical insurance risks and costs for hospitals and patients.

[0067] In one embodiment of the present disclosure, the keyword group is matched with the drug review rule library to obtain a first target review rule that matches the data source of the target database, including: Construct a multi-dimensional rule index system based on the pharmacological effects, therapeutic uses, medical insurance reimbursement restrictions, and drug interaction information of drugs; The first target review rule is obtained by matching the keyword group based on the multi-dimensional rule indexing system.

[0068] Among them, the keyword groups are matched based on a multi-dimensional rule indexing system, including: The keyword group is matched based on the first formula, which is:

[0069] in, Indicates the matching result; n is the number of dimensions in the rule index system; is the weight coefficient of the i-th dimension, indicating the importance of this dimension in the overall matching process; is the matching function of the i-th dimension, returning a matching value; P represents a keyword group, Represents the data of the i-th dimension.

[0070] In this embodiment, a multi-dimensional rule index system is constructed based on the pharmacological effects, therapeutic uses, medical insurance reimbursement restrictions, and drug interaction information of the drug. When matching key phrases, semantic analysis and ontology matching technology are used to not only match direct information such as drug names and dosage forms, but also to deeply analyze the association between the drug's mechanism of action and applicable diseases and key phrases.

[0071] For example, when a keyword group contains the name and symptom information of a certain disease, the rule index system can quickly locate the relevant rules for the treatment of the disease, and combine the drug interaction rules to determine whether there are contraindications for multiple drugs used at the same time. If so, the corresponding strong warning signal will be triggered, and detailed drug substitution suggestions and medical basis will be provided.

[0072] In this embodiment, a first target audit rule is obtained by matching the keyword group based on the first formula. In the first formula, R1 represents the matching result of the first target audit rule, and its value or specific value range can indicate the degree of matching or whether the corresponding rule is triggered. For example, when R1 is greater than the first threshold, it indicates that the match is successful and the relevant audit rules are triggered. n is the number of dimensions in the rule index system, such as the drug name dimension, pharmacological action dimension, treatment disease dimension, etc. The weight coefficient can be determined based on historical data, medical insurance policy priorities, and medical expert experience. For example, for the dimensions corresponding to the drug categories or key treatment diseases that are monitored by medical insurance, the weights are Will be relatively high.

[0073] is the matching function of the i-th dimension, which accepts the keyword group K and the data of the i-th dimension As input, it returns a matching value. This matching value can be a value between 0 and 1, indicating the degree of matching between the keyword group and the dimension data, where 0 indicates no match at all and 1 indicates a perfect match. For example, in the drug name dimension, if the keyword group contains words that are exactly the same as the drug name in the rule, then Returns 1. If there is a partial match or a certain correlation, a value between 0 and 1 is returned. In the pharmacological effect dimension, semantic analysis and knowledge graph technology can be used to determine the degree of match between the pharmacological effect-related words in the keyword group and the pharmacological effect defined in the rule, and the corresponding matching value is returned.

[0074] From the above, it can be concluded that this embodiment achieves efficient and accurate docking of keyword groups with the drug review rule library by constructing a multi-dimensional rule index system and using the first formula for precise matching, effectively improving the intelligence level of medical insurance business review and ensuring drug safety and compliance.

[0075] In one embodiment of the present disclosure, the keyword group is matched with the process audit rule library to obtain a second target audit rule that matches the data source of the target database, including: Adopt the rule representation method based on the business process model to determine the process audit rule base; The keyword group is input into the business process model for rule matching to obtain the second target audit rule.

[0076] In this embodiment, the system models the medical insurance reimbursement process, medical service provision process, etc., and converts the key links, participating roles, time nodes, data flow and other elements in the process into rule conditions. When matching the keyword group, the operation sequence of the department involved, the cost settlement stage, etc. are accurately matched with the process audit rule library to obtain the second target audit rule. If abnormal conditions such as missing process links, reversed order or time overdue are found, different levels of warnings are generated according to the severity of the abnormality, and traced back to the specific responsible links and personnel, providing strong support for process optimization and responsibility identification.

[0077] In this embodiment, in the rule representation of the business process model, a finite state machine (FSM) is used to model the medical insurance business process, and the medical insurance business process is divided into multiple state nodes, including but not limited to expense declaration, under review, approved, unapproved, expense settlement and other states. The transition between different states is triggered by preset conditions, which constitute part of the process review rule library. When the keyword group is input into the business process model for rule matching, the current state of the business process is determined based on the process-related information in the keyword group (such as the current process stage, operation time, operator information, etc.), and whether the state transition conditions are met based on the current state and other information in the keyword group. If not, the corresponding second target review rule is triggered. The second target review rule includes a detailed description of the illegal process state, the possible risk assessment, and the handling suggestions for the illegal state.

[0078] From the above, it can be concluded that this embodiment realizes intelligent monitoring of medical insurance business processes by constructing a business process model and a finite state machine, accurately matching keyword groups with process review rules, effectively warning of process anomalies, tracing responsibilities, providing strong support for process optimization and responsibility identification, and improving the efficiency and accuracy of medical insurance management.

[0079] In one embodiment of the present disclosure, an early warning is issued for a data update request in a target management system based on a target audit rule, including: Rating the warning information according to the severity and risk level of the target audit rules; Issue warnings based on the rated warning information.

[0080] Generate a unique identification code for each warning information, and store the warning information using the unique identification code as an index; Update the audit rule base based on the warning information within the preset time period.

[0081] In this embodiment, the rating of the warning information is determined based on a second formula, and the second formula is:

[0082] Among them, S represents the severity level , The larger the value, the more serious the consequences of violating the target audit rules. R represents the risk level. , , the larger the value, the greater the possibility of violation. For example, r1 indicates a low risk situation where violation will only occur under special circumstances; r l Indicates a high risk of violations that could easily occur during routine operations. Indicates the rating of the warning information. , The larger the value, the more important the warning information is and the more priority it needs to be handled. The rating of the warning information is determined based on the specific combination of severity level and risk level, which more intuitively reflects the difference in importance of different situations.

[0083] In this embodiment, in order to facilitate the management and tracking of warning information, the system will generate a unique identification code for each warning information. This identification code is like the "identity card" of the warning information, which can uniquely identify the warning information in the entire system to avoid confusion between different warning information. Using the unique identification code as an index to store the warning information means that in a database or other storage system, this identification code can be used as a key basis for searching and locating. This storage method can improve the efficiency of data storage and retrieval. When it is necessary to query the details of a certain warning information, the corresponding warning information record can be quickly found by simply using the unique identification code, which is convenient for subsequent system optimization and analysis.

[0084] From the above, it can be concluded that this embodiment can quickly identify the importance of warnings by classifying and grading warning information according to severity and risk levels; generating unique identification codes to store warning information facilitates information management and tracing. Based on the preset time warning information, the review rule library can be updated to continuously optimize the rules, improve the accuracy and efficiency of medical insurance review, and ensure the compliance of medical insurance business.

[0085] In this embodiment, reference Figure 3 The hospital's management process for the medical insurance early warning review system is as follows: For problems reported by the audit system, if they are information system problems, such as network freezes, slow audit process, etc., the problem needs to be sent to the HIS engineer / intelligent audit system engineer for investigation. After the problem is solved, it will be reported to the clinic and the processing is completed. If it is a medical insurance policy issue, it is necessary to check the policy document and log in to the intelligent audit system with the account and password to make a judgment. For clinical charging issues, contact the department for processing and the processing is completed. For problems with incomplete intelligent audit system rules, the medical insurance office maintains the rules and reports them to the clinic and the processing is completed.

[0086] Corresponding to the medical insurance early warning review method in the above embodiment, Figure 4 This is a structural block diagram of a medical insurance early warning review system provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 4 The medical insurance early warning and review system 20 includes: a data acquisition module 21, a feature extraction module 22, a matching module 23 and an early warning module 24.

[0087] The data acquisition module 21 is used to obtain the data source of the target database corresponding to the target management system in response to identifying that there is a data update request in the target management system, and the target management system is a system associated with the medical insurance early warning and review system; A feature extraction module 22 is used to extract keywords from the data source of the target database to obtain keyword groups; A matching module 23 is used to match the keyword group with the audit rule library to obtain a target audit rule that matches the data source of the target database, and the audit rule library is a rule library customized by the hospital; The early warning module 24 is used to issue an early warning to the data update request in the target management system based on the target audit rules.

[0088] In one embodiment of the present disclosure, the data source of the target database includes department information and diagnosis information; the feature extraction module 22 is specifically used for: Based on the pre-built department classification keyword library, the department information is matched and extracted to obtain the first keyword group, and based on the clustering algorithm model, the diagnosis information is keyword extracted to obtain the second keyword group; A keyword group is obtained based on the first keyword group and the second keyword group.

[0089] In one embodiment of the present disclosure, the feature extraction module 22 is specifically used to: Determine the amount of data for diagnostic information; When the data volume of the diagnostic information is less than the first preset threshold, the K value of the clustering algorithm model is determined by using the elbow method, and the initial point of the clustering algorithm model is randomly generated; Extracting keywords from the diagnostic information based on the clustering algorithm model to obtain a second keyword group; When the data volume of the diagnostic information is greater than or equal to a first preset threshold, a density-based spatial clustering algorithm is used to determine the number of clusters of the clustering algorithm model; the local density of each data point in the diagnostic information is calculated, and an initial point of the clustering algorithm model is determined based on the local density; Keywords are extracted from the diagnostic information based on the clustering algorithm model to obtain a second keyword group.

[0090] In one embodiment of the present disclosure, the audit rule base includes a drug audit rule base and a process audit rule base. The matching module 23 is specifically used for: Matching the keyword group with the drug review rule library to obtain a first target review rule that matches the data source of the target database; Matching the keyword group with the process audit rule library to obtain a second target audit rule that matches the data source of the target database; The first target audit rule and the second target audit rule constitute the target audit rule.

[0091] In one embodiment of the present disclosure, the matching module 23 is specifically used for: Construct a multi-dimensional rule index system based on the pharmacological effects, therapeutic uses, medical insurance reimbursement restrictions, and drug interaction information of drugs; The first target review rule is obtained by matching the keyword group based on the multi-dimensional rule indexing system.

[0092] In one embodiment of the present disclosure, the matching module 23 is specifically used for: The keyword group is matched based on the first formula, which is:

[0093] in, Indicates the matching result; n is the number of dimensions in the rule index system; is the weight coefficient of the i-th dimension, indicating the importance of this dimension in the overall matching process; is the matching function of the i-th dimension, returning a matching value; P represents a keyword group, Represents the data of the i-th dimension.

[0094] In one embodiment of the present disclosure, the matching module 23 is specifically used for: Adopt the rule representation method based on the business process model to determine the process audit rule base; The keyword group is input into the business process model for rule matching to obtain the second target audit rule.

[0095] In one embodiment of the present disclosure, the early warning module 24 is specifically used to: Rating the warning information according to the severity and risk level of the target audit rules; Issue warnings based on the rated warning information.

[0096] In one embodiment of the present disclosure, the early warning module 24 is further configured to: Generate a unique identification code for each warning information, and store the warning information using the unique identification code as an index; Update the audit rule base based on the warning information within the preset time period.

[0097] See also Figure 5 , Figure 5 Schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 5 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 4 The functions of modules 21 to 24 are shown.

[0098] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0099] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0100] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0101] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the medical insurance early warning review method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0102] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0103] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0104] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0105] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0106] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0108] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0109] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A medical insurance early warning review method, characterized in that: include: In response to identifying that there is a data update request in the target management system, obtaining a data source of a target database corresponding to the target management system, wherein the target management system is a system associated with the medical insurance early warning and review system; Extracting keywords from the data source of the target database to obtain keyword groups; Matching the keyword group with an audit rule library to obtain a target audit rule that matches the data source of the target database, wherein the audit rule library is a rule library customized by the hospital; Based on the target audit rules, an early warning is issued for the data update request in the target management system.

2. The medical insurance early warning review method according to claim 1, characterized in that: The data sources of the target database include department information and diagnosis information; The step of extracting keywords from the data source of the target database to obtain keyword groups includes: Based on the pre-built department classification keyword library, the department information is matched and extracted to obtain the first keyword group, and based on the clustering algorithm model, the diagnosis information is keyword extracted to obtain the second keyword group; The keyword group is obtained based on the first keyword group and the second keyword group.

3. The medical insurance early warning review method according to claim 2, characterized in that: The method of extracting keywords from the diagnostic information based on the clustering algorithm model to obtain a second keyword group includes: Determine the amount of data for diagnostic information; When the data volume of the diagnostic information is less than the first preset threshold, the K value of the clustering algorithm model is determined by using the elbow method, and the initial point of the clustering algorithm model is randomly generated; Extracting keywords from the diagnostic information based on the clustering algorithm model to obtain a second keyword group; When the data volume of the diagnostic information is greater than or equal to a first preset threshold, a density-based spatial clustering algorithm is used to determine the number of clusters of the clustering algorithm model; the local density of each data point in the diagnostic information is calculated, and an initial point of the clustering algorithm model is determined based on the local density; Keywords are extracted from the diagnostic information based on the clustering algorithm model to obtain a second keyword group.

4. The medical insurance early warning review method according to claim 1, characterized in that: The review rule base includes a drug review rule base and a process review rule base; The step of matching the keyword group with the audit rule library to obtain a target audit rule that matches the data source of the target database includes: Matching the keyword group with a drug review rule library to obtain a first target review rule that matches a data source of the target database; Matching the keyword group with a process audit rule library to obtain a second target audit rule that matches the data source of the target database; The first target audit rule and the second target audit rule constitute a target audit rule.

5. The medical insurance early warning review method according to claim 4, characterized in that: The step of matching the keyword group with a drug review rule library to obtain a first target review rule that matches a data source of the target database includes: Construct a multi-dimensional rule index system based on the pharmacological effects, therapeutic uses, medical insurance reimbursement restrictions, and drug interaction information of drugs; The keyword group is matched based on the multi-dimensional rule indexing system to obtain the first target review rule.

6. The medical insurance early warning review method according to claim 5, characterized in that: The matching of the keyword group based on the multi-dimensional rule indexing system includes: The keyword group is matched based on a first formula, where the first formula is: in, Indicates the matching result; n is the number of dimensions in the rule index system; is the weight coefficient of the i-th dimension, indicating the importance of this dimension in the overall matching process; is the matching function of the i-th dimension, returning a matching value; P represents a keyword group, Represents the data of the i-th dimension.

7. The medical insurance early warning review method according to claim 4, characterized in that: The step of matching the keyword group with the process audit rule library to obtain a second target audit rule that matches the data source of the target database includes: Adopt the rule representation method based on the business process model to determine the process audit rule base; The keyword group is input into the business process model for rule matching to obtain a second target audit rule.

8. The medical insurance early warning review method according to claim 1, characterized in that: The step of providing an early warning for a data update request in the target management system based on the target audit rule includes: Rating the warning information according to the severity and risk level of the target audit rules; Issue warnings based on the rated warning information.

9. The medical insurance early warning review method according to claim 8, characterized in that: Also includes: Generate a unique identification code for each warning information, and store the warning information using the unique identification code as an index; Update the audit rule base based on the warning information within the preset time period.

10. A medical insurance early warning review system, characterized in that: include: A data acquisition module, for acquiring a data source of a target database corresponding to the target management system in response to identifying that there is a data update request in the target management system, wherein the target management system is a system associated with the medical insurance early warning and review system; A feature extraction module, used to extract keywords from the data source of the target database to obtain keyword groups; A matching module, used for matching the keyword group with an audit rule library to obtain a target audit rule that matches the data source of the target database, wherein the audit rule library is a rule library customized by the hospital; The early warning module is used to issue an early warning to the data update request in the target management system based on the target audit rule.

Images