Clearing method and device suitable for DIP critical and severe cases and medium

Abstract

The invention provides a clearing method and device suitable for DIP critical and severe cases and a medium. The clearing method comprises the steps that a critical and severe feature library is created; based on the critical and critical feature library, screening out a to-be-processed critical and critical case set; on the basis of the critical and critical feature library, grouping a critical and critical case set to be processed; carrying out score calculation on the critical case set; and according to a grouping result, generating a plurality of DIP critical symptom set-up groups, and carrying out medical insurance payment settlement according to the DIP critical symptom set-up groups. Compared with a method for grouping according to main diagnosis of the patient in the prior art, the method has the advantages that the influence of other diagnosis of the patient on resource consumption can be considered, so that screening grouping and score supplementation can be performed on critical and severe cases more accurately, and more scientific and more reasonable medical insurance payment liquidation can be completed.

Description

Technical Field

[0001] The present invention relates to the technical field of medical insurance payment settlement, and in particular to a settlement method, device and medium suitable for DIP critical and severe cases. Background Art

[0002] With the continuous advancement of medical technology and the rapid growth of medical expenses, the medical insurance system faces huge challenges. In order to control the unreasonable growth of medical expenses and improve the quality of medical services, countries have explored new medical insurance payment methods. Disease-based payment (DIP) is a medical insurance payment method based on big data. By classifying diseases and calculating scores, it can achieve refined management and cost control of medical services. However, in the DIP payment method, due to the limitations of the grouping scheme, there is a lack of compensation for critical and severe cases. For hospitals, the settlement of critical and severe cases needs to be carried out through special disease single discussion. The special disease single discussion patients mainly rely on the manual review of experts organized by the Medical Insurance Bureau, which is completely dependent on manpower. Under normal circumstances, an expert can review 20 copies a day. For this, a lot of manpower and material resources are required (and the hospital needs to report the complete medical records of these patients in addition). Since the special disease single discussion review relies on manpower, it is easy to lead to insufficient settlement and payment, and a large number of critical and severe patients have not been effectively allocated. . Summary of the invention

[0003] In order to overcome the above-mentioned technical defects, the present invention provides a liquidation method, device and medium suitable for DIP critical and severe cases, which can take into account the impact of other diagnoses of patients on resource consumption, so as to more accurately screen out critical and severe cases.

[0004] In order to solve the above problems, the present invention is implemented according to the following technical solutions: A liquidation method applicable to DIP critical and severe cases, comprising the steps of: Create a critical illness feature library; Based on the critical and severe disease feature database, screen out the critical and severe disease cases to be processed; Based on the critical and severe disease feature database, the critical and severe disease cases to be processed are grouped; Calculate the scores of critical and severe cases; Based on the grouping results and scores, several DIP critical disease payment groups are generated, and medical insurance payment settlement is carried out according to the DIP critical disease payment groups.

[0005] As a further improvement of the present invention, the critical and severe disease feature library includes: a basic grouping table of critical and severe diseases, a table of critical and severe diseases accompanied by serious complications and comorbidities, a table of critical and severe disease complications accompanied by general complications and comorbidities, and a table of critical and severe disease complications and comorbidities exclusion.

[0006] As a further improvement of the present invention, the step of screening out a set of critical and severe cases to be processed based on the critical and severe disease feature library comprises: Set filtering rules; According to the screening rules, a set of pending critical and severe cases is screened out from the pending DIP payment settlement list.

[0007] As a further improvement of the present invention, the step of setting screening rules includes: Create large clinical diagnosis and treatment data sets; Based on the critical illness feature database, the clinical diagnosis and treatment big data set was analyzed to obtain the relationship model between age and overspending amount; The filtering rules are obtained according to the relational model.

[0008] As a further improvement of the present invention, the step of creating a clinical diagnosis and treatment big data set includes: Obtain medical insurance clinical diagnosis and treatment data; After processing the medical insurance clinical diagnosis and treatment data, a large clinical diagnosis and treatment data set is created.

[0009] As a further improvement of the present invention, the medical insurance clinical diagnosis and treatment data is processed, including: data cleaning processing, expense detail correction processing, partition processing, and expense detail table processing.

[0010] As a further improvement of the present invention, the step of calculating the score of the critical and severe case set includes: The average fee is taken as the basis for scoring, the average cost is calculated, and then divided by the unit price of the local city score to obtain the score corresponding to each critical and severe case grouping.

[0011] As a further improvement of the present invention, when calculating the scores of the critical and severe case set, a method of removing the lowest cost and the highest cost is adopted to perform outlier filtering processing.

[0012] The present invention also provides a computer device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is used to implement the above-mentioned clearing method when executing the program stored in the memory.

[0013] The present invention also provides one or more computer-readable media having instructions stored thereon, which, when executed by one or more processors, enable the processors to perform the above-mentioned liquidation method.

[0014] Compared with the prior art, the beneficial effects of the liquidation method provided by the present invention are as follows: Based on the critical and severe disease feature library, the present invention can more accurately identify different types of critical and severe patients and perform effective grouping and score calculation, and give full payment. Compared with the method of grouping only according to the patient's main diagnosis in the prior art, the present invention can take into account the impact of the patient's other diagnoses on resource consumption, thereby more accurately screening out critical and severe cases, bringing positive empowerment to the fairness and justice of medical insurance payment and encouraging tertiary hospitals to actively treat serious patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of the liquidation method of the present invention; Figure 2 This is the middle age / overspending amount graph of the present invention. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0017] Considering the shortcomings of the existing technology: 1. The grouping scheme is inherently insufficient. Cases with the same main diagnosis and treatment methods are grouped together, which cannot solve the resource consumption differences caused by other diagnostic differences, and easily induce the problem of decomposition of hospitalization; 2. The DIP payment method cannot fully consider the high resource consumption and high cost requirements of critical and severe cases, resulting in low enthusiasm of medical institutions to admit critical and severe patients, and the situation of shirking patients; 3. Abnormal disease group cases are highly correlated with medical record quality. Complex or critical and severe cases with abnormal grouping due to problems in medical record quality will not be settled in accordance with the complex or critical disease supplement method. In some cities and prefectures, the medical insurance bureaus will settle such abnormal groupings or non-grouping medical records at the original price, which will cause medical institutions to deliberately ignore the quality of medical records in order to obtain higher settlement results.

[0018] The present invention provides a liquidation method suitable for DIP critical and severe cases, such as Figure 1 As shown, the steps include: S1. Create a critical and severe disease feature library. The critical and severe disease feature library is based on the critical and severe disease feature classification experience summarized by DIP / DRG. The critical and severe disease feature library is the basis for subsequent grouping.

[0019] The critical and severe disease feature library includes: a basic grouping table for critical and severe diseases, a table for critical and severe diseases accompanied by serious complications and comorbidities, a table for critical and severe disease complications accompanied by general complications and comorbidities, and a table for exclusion of critical and severe disease complications and comorbidities.

[0020] Example: Critical and severe basic grouping table - heart failure

[0021] Critical illness with severe complications and comorbidities - heart failure

[0022] Critical complications with general complications and comorbidities - tachycardia

[0023] Critical illness complications and comorbidities exclusion list - heart failure

[0024] S2. Based on the critical and severe disease feature database, screen out the critical and severe disease case set to be processed: In this process, you first need to set up screening rules, and then, based on the screening rules, filter out the set of critical and severe cases to be processed from the pending DIP payment settlement list.

[0025] In one embodiment, S21, setting screening rules: including the following steps: S211. Create a large clinical diagnosis and treatment data set. Here, you can obtain medical insurance clinical diagnosis and treatment data by importing csv files or dmp files. Medical insurance clinical diagnosis and treatment data includes medical insurance expense details (diagnosis and treatment item code, diagnosis and treatment item name, medical insurance item code, medical insurance item name, expense amount, pooling amount, quantity, etc.), medical insurance settlement information (such as patient ID, name, age, gender, etc.), medical insurance settlement list diagnosis information (such as diagnosis code, diagnosis name, etc.), medical insurance liquidation settlement information (such as patient ID, settlement amount, overspending amount, etc.), etc.

[0026] In order to ensure that the final classification results are more accurate, after obtaining the medical insurance clinical diagnosis and treatment data, it is necessary to process the medical insurance clinical diagnosis and treatment data, including: data cleaning processing, cost detail correction processing, partition processing, and cost detail table processing.

[0027] Among them, data cleaning is used to check and correct errors or inconsistencies in the data, and data cleaning tools are used for automated processing, such as deleting duplicate records, filling missing values, converting data types, etc. The medical insurance clinical diagnosis and treatment data is then processed at a deeper level: cost detail correction processing, partition processing, and cost detail table processing, and the processed medical insurance clinical diagnosis and treatment data is used to create a clinical diagnosis and treatment big data set.

[0028] S212. Based on the critical illness feature database, the clinical diagnosis and treatment big data set was analyzed to obtain the age-overspending amount relationship model.

[0029] Specifically, based on the critical and severe disease feature database, the data of the clinical diagnosis and treatment big data set are analyzed in turn according to different "hospital levels", "patient age" and "overspending amount".

[0030] When describing the relationship between age and overspending amount, a simple linear regression model can be used to form a data formula to obtain the relationship model of age-overspending amount: Y=aX+b Among them, Y represents the overspending amount (horizontal axis), X represents age (vertical axis), a is the slope, which represents the rate of change of the overspending amount for every increase in age by one year, and b is the intercept, which represents the overspending amount when the age is zero.

[0031] By performing regression analysis on the data of the large clinical diagnosis and treatment data set, the values ​​of the slope a and the intercept b are determined.

[0032] S213. The filtering rules are obtained according to the relational model. In actual operation, some data preprocessing is required, such as rounding down. The age and the overspending amount are rounded up to obtain a piecewise function instead of a continuous linear function. For example, the age rounding interval and the corresponding overspending amount lower limit can be set to form a piecewise filtering rule. For example, if the following data is obtained through aggregation analysis: For people aged between 0 and 20, the lower limit of overspending is RMB 10,000.

[0033] For people aged between 20 and 99, the lower limit for overspending is RMB 20,000.

[0034] These data points can be represented as: Y1=10000for0≤X<20Y1=10000for0≤X<20 Y2=2000for20≤X<99Y2=1500for20≤X<99 Among them, Y1Y1 and Y2Y2 correspond to the lower limits of overspending amounts for different age groups respectively.

[0035] Take the definition of the screening rule for "heart failure" as an example: "I50.000x006 / Acute right heart failure" is the main diagnosis, and patients in a tertiary public hospital are analyzed by cluster analysis (based on the K-means algorithm implemented in Python) based on these two dimensions to obtain the following two types of aggregation ranges: from Figure 2It can be seen that the overspending amount of "heart failure" is distributed as follows: the overspending amount in the 0-14 age group is generally more than 10,000 yuan, while the overspending amount in the 20-year-old group is almost all more than 20,000 yuan. The system forms a screening rule by rounding the lower limits of these two types of aggregations. The specific screening rule table is as follows:

[0036] Note: ... represents values ​​in other ranges.

[0037] S22. According to the screening rules, a set of critical and severe cases to be processed is screened out from the DIP payment settlement list to be processed.

[0038] An example of the screening process is as follows: The following is a list of DIP payment settlements in a certain city (excerpt)

[0039] According to the above filtering rules, the main diagnosis is "I50.000x006 / Acute right heart failure", and there are only two values ​​in the "age" and "overspending amount" that are within the range, that is, the records with a gray background in the list.

[0040] S3. Based on the critical and severe disease feature library, the critical and severe disease cases to be processed are grouped: First, obtain the main diagnosis and other diagnoses of each screened medical record in the critical and severe case set, and compare them with the relevant tables of the critical and severe feature library. If the patient's other diagnoses are in the critical and severe disease with serious complications and comorbidities table or the critical and severe disease complications with general complications and comorbidities table, and are not in the critical and severe disease complications and comorbidities exclusion table, then divide the patient into the critical and severe disease group; if the patient's other diagnoses are in the critical and severe disease with serious complications and comorbidities table or the critical and severe disease complications with general complications and comorbidities table, but in the critical and severe disease complications and comorbidities exclusion table, then divide the patient into the common disease group (without comorbidities and complications); if the patient's other diagnoses are not in the critical and severe disease with serious complications and comorbidities table and the critical and severe disease complications with general complications and comorbidities table, then divide the patient into the common disease group (without comorbidities and complications).

[0041] S4. Calculate the scores of the critical and severe cases. Specifically, take the average fee as the basis for the score, calculate the average of the fees, and then divide it by the score unit price of the local city (the score unit price needs to distinguish between employees and residents) to obtain the score corresponding to each critical and severe case group. In this process, remove the lowest and highest fees and filter outliers to ensure the accuracy of the results.

[0042] Take "critical illness - heart failure" as an example:

[0043] S5. Based on the grouping results and scores, generate several DIP critical illness payment groups, a list of critical illness medical insurance payments to be liquidated, and perform medical insurance payment liquidation according to the DIP critical illness payment groups. For cases in the common disease group (without comorbidities and complications), which are hospital management issues, they will be grouped according to the original DIP disease types to complete liquidation.

[0044] For example, a critically ill patient with heart failure in a tertiary hospital, whose main diagnosis is "I50.000x006 / Acute right heart failure", is 46 years old and covered by employee medical insurance. According to the "Critical Illness-Heart Failure" example table above, the DIP critical illness payment group to which the patient belongs is the second row of records. Based on this, the score of the critically ill patient is 4639.9, and the Medical Insurance Bureau pays the hospital an equivalent amount according to the score.

[0045] In summary, the liquidation method of the present invention has the following beneficial effects: 1. More accurate identification of critical and severe cases: Based on the results of medical insurance overspending, the present invention compares the complication table and the comorbidity table to more accurately identify critical and severe cases. Compared with the prior art method of grouping patients only according to their main diagnosis, the present invention can take into account the impact of other diagnoses of patients on resource consumption, thereby more accurately screening out critical and severe cases.

[0046] 2. A more reasonable settlement method: The present invention uses a cluster analysis algorithm for the critical and severe group to generate several DIP critical and severe groups for payment. This settlement method can be refined according to the specific circumstances of the case and fully mobilize the enthusiasm of medical institutions to treat critical and severe patients. Compared with the unified settlement method used in the prior art, the present invention can better guarantee the reasonable income of medical institutions and promote the improvement of medical service quality.

[0047] Based on the same inventive concept, another embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to load the liquidation method as described in any one of the embodiments of the present invention.

[0048] Specifically, the computer device includes: a memory and a processor. The memory and the processor are connected via a bus communication. A computer program is stored in the memory. The computer program can be run on the processor to load the liquidation method of the present invention.

[0049] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0050] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0051] Based on the same inventive concept, another embodiment of the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon, which loads the liquidation method of the present invention when executed by a processor.

[0052] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0053] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, devices, electronic devices, storage media or computer program products. Therefore, embodiments of the present invention may take the form of complete hardware embodiments, complete software embodiments, or embodiments combining software and hardware. Moreover, embodiments of the present invention may take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CDROM, optical storage, etc.) containing computer-usable program codes.

[0054] The above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A liquidation method suitable for DIP critical and severe cases, characterized in that: Includes steps: Create a critical illness feature library; Based on the critical and severe disease feature database, screen out the critical and severe disease cases to be processed; Based on the critical and severe disease feature database, the critical and severe disease cases to be processed are grouped; Calculate the scores of critical and severe cases; Based on the grouping results and scores, several DIP critical disease payment groups are generated, and medical insurance payment settlement is carried out according to the DIP critical disease payment groups.

2. The liquidation method according to claim 1, characterized in that: The critical and severe disease feature library includes: a basic grouping table for critical and severe diseases, a table for critical and severe diseases accompanied by serious complications and comorbidities, a table for critical and severe disease complications accompanied by general complications and comorbidities, and a table for exclusion of critical and severe disease complications and comorbidities.

3. The liquidation method according to claim 1, characterized in that: The step of screening out a set of critical and severe cases to be processed based on the critical and severe disease feature library comprises: Set filtering rules; According to the screening rules, a set of pending critical and severe cases is screened out from the pending DIP payment settlement list.

4. The liquidation method according to claim 3, characterized in that: The step of setting the screening rules includes: Create large clinical diagnosis and treatment data sets; Based on the critical illness feature database, the clinical diagnosis and treatment big data set was analyzed to obtain the relationship model between age and overspending amount; The filtering rules are obtained according to the relational model.

5. The liquidation method according to claim 4, characterized in that: The step of creating a clinical diagnosis and treatment big data set includes: Obtain medical insurance clinical diagnosis and treatment data; After processing the medical insurance clinical diagnosis and treatment data, a large clinical diagnosis and treatment data set is created.

6. The liquidation method according to claim 5, characterized in that: Processing of medical insurance clinical diagnosis and treatment data, including: data cleaning, cost detail correction, zoning, and cost detail table processing.

7. The liquidation method according to claim 1, characterized in that: The step of calculating the score of the critical and severe case set includes: The average fee is taken as the basis for scoring, the average cost is calculated, and then divided by the unit price of the local city score to obtain the score corresponding to each critical and severe case grouping.

8. The liquidation method according to claim 7, characterized in that: When calculating the scores for the critical and severe case set, the method of removing the lowest and highest costs was used to filter out outliers.

9. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to implement the liquidation method according to any one of claims 1 to 8 when executing the program stored in the memory.

10. One or more computer-readable media having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the liquidation method according to any one of claims 1 to 8.

Images