CN115910308A - Expense fine control method and device under DRG system, and electronic equipment - Google Patents
Expense fine control method and device under DRG system, and electronic equipment Download PDFInfo
- Publication number
- CN115910308A CN115910308A CN202310011003.4A CN202310011003A CN115910308A CN 115910308 A CN115910308 A CN 115910308A CN 202310011003 A CN202310011003 A CN 202310011003A CN 115910308 A CN115910308 A CN 115910308A
- Authority
- CN
- China
- Prior art keywords
- cost
- stage
- drg
- set stage
- expense
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a cost fine control method, a device and electronic equipment under a DRG system, wherein the method comprises the following steps: performing statistical analysis on historical data of hospital inpatients grouped according to DRG to obtain interval distribution models such as normally distributed hospitalization cost in each set stage in the medical process, and establishing cost prediction models in each set stage; acquiring the current cost actual value of each setting stage, and calculating to obtain a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage; and determining whether the expense early warning and the early warning level are needed according to the size relation of the current expense actual value, the real-time expense predicted value and the total expense predicted value of each set stage. The method and the system realize the staged prediction and control of the cost in the medical treatment process, so that the cost of a doctor in different stages of the medical treatment of a patient is accurately controlled to provide effective guidance suggestions, and the method and the system can be particularly applied to handheld equipment of a hospital and are convenient for the doctor to inquire at any time.
Description
Technical Field
The present application relates to the technical field of intelligent medical information processing, and in particular, to a cost refinement control method and apparatus under a DRG system, and an electronic device.
Background
At present, a DRG (Diagnosis Related Groups) system is tried on nationwide, and the main purpose is to provide guidance for medical insurance reimbursement of patients through data accumulation.
Under the condition of incomplete standard of the treatment process, doctors can only estimate the total amount of the cost of the medical process according to a DRG system, cannot refine the cost to each stage of the medical process, and cannot reasonably distribute the cost. In addition, the existing clinical pathway or clinical guideline design criteria are unclear, and there are many obstacles to the structuring of the clinical pathway to the patient treatment process, so that the goal of embedding the clinical pathway in the HIS (Hospital Information System) to realize the real-time fine management of the whole process of DRGs cost occurrence is currently difficult to realize.
Disclosure of Invention
On one hand, the application provides a cost fine control method under a DRG system, so as to solve the technical problem that in the prior art, a doctor cannot actively and accurately control the cost in the medical process.
The technical scheme adopted by the application is as follows:
a fine control method for the cost under a DRG system comprises the following steps:
performing statistical analysis on historical data of hospital inpatients grouped according to DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model and a proportion consumption interval distribution model which are normally distributed in each set stage in the medical process, and establishing a cost prediction model in each set stage in the medical process, wherein the set stage comprises four stages of a regulation period of preoperative illness state, a waiting operation period, an operation period and a postoperative recovery period which are divided according to actual conditions in the diagnosis and treatment process after the DRG is grouped;
acquiring the current cost actual value of each setting stage, and calculating to obtain a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage;
and determining whether cost early warning is needed according to the size relationship of the current cost actual value, the real-time cost predicted value and the total cost predicted value of each set stage, and starting the cost early warning of the corresponding set stage in a grading manner when the cost early warning is determined to be needed.
Preferably, the statistical analysis is performed on historical data of hospital inpatients grouped according to the DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model and a proportion consumption interval distribution model which are normally distributed at each set stage in the medical process, and the statistical analysis specifically comprises the following steps:
acquiring hospital inpatient historical data from a hospital inpatient historical database, and grouping the hospital inpatient historical data through an in-hospital grouping device to obtain different DRG grouped data;
performing statistical analysis on each DRG grouped data according to the set stage to obtain relevant medical data, wherein the relevant medical data comprises hospitalization cost, hospitalization time, treatment, medical care, consumable material use, medicine use and inspection items;
removing outliers from the statistically analyzed relevant medical data by a stepwise linear regression method;
through data transformation, constructing an hospitalization cost interval distribution model, an hospitalization duration interval distribution model and a consumption ratio interval distribution model of each set stage under corresponding DRG grouped data, and forming a normally distributed hospitalization cost interval distribution model u1 +/-3 sigma 1, a normally distributed hospitalization duration interval distribution model u2 +/-3 sigma 2 and a normally distributed consumption ratio interval distribution model u4 +/-3 sigma 4, wherein u1 is the hospitalization cost of each set stage under the corresponding DRG grouped data, sigma 1 is the hospitalization cost variance of each set stage under the corresponding DRG grouped data, u2 is the hospitalization duration mean of each set stage under the corresponding DRG grouped data, the unit is day, sigma 2 is the hospitalization duration variance of each set stage under the corresponding DRG grouped data, u4 is the consumption ratio mean of each set stage under the corresponding DRG grouped data, and sigma 4 is the variance ratio of each set stage under the corresponding DRG grouped data;
according to the normally distributed average value u1 of the hospitalization cost and the average value u2 of the length of hospitalization, calculating the average daily hospitalization cost of each set stage under the corresponding DRG grouping data:
u3= u1/ u2。
preferably, the establishing of the cost prediction model of each set stage in the medical process specifically includes the steps of:
establishing a multivariate linear model of each set stage in the medical process:
Fcost = a1*x1+a2*x2+a3*x3+a4*x4+a5*x5+a6*x6…+an*xn
in the model construction process, performing variable correlation analysis, variable importance analysis and variable screening, wherein a dependent variable Fcost is a predicted value of the cost in a set stage, independent variables x1, x2, x3, x4, x5 and x6 … xn are typical fields of a cost detail data table, including age, physical conditions of hospital admission, the number of hospitalization days in each set stage, examination items and cost, medicine use conditions and consumable material use conditions, and a1, a2, a3, a4, a5 and a6 … an are weights corresponding to respective variables;
and performing data fitting on the multivariate linear model machine through the historical data of the inpatients in the hospital to obtain the numerical values of the weights corresponding to the respective variables, and obtaining the cost prediction model of each set stage in the medical process.
Preferably, the acquiring of the current cost actual value of each setting stage and the calculating of the real-time cost predicted value and the total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage specifically include the steps of:
obtaining the current cost actual value Y1 of each set stage from the system;
calculating to obtain a real-time expense predicted value T1 corresponding to each set stage according to the expense prediction model of each set stage;
calculating all the cost predicted values corresponding to the setting stages according to the real-time cost predicted value T1, the average hospitalization cost u3 and the remaining days N of hospitalization corresponding to the setting stages:
T2=T1+ u3*N。
preferably, the method for determining whether early warning is needed according to the size relationship among the current cost actual value, the real-time cost predicted value and all the cost predicted values of each setting stage, and starting the cost early warning of the corresponding setting stage in a grading manner when determining that the early warning is needed specifically comprises the following steps:
setting a counter and setting an initial value i of the counter to 0;
when the real-time cost predicted value T1 corresponding to each setting stage is smaller than the current cost actual value Y1 of each setting stage, accumulating the value of i by 1, otherwise, keeping the value of i unchanged;
if all the cost predicted values T2 of all the setting stages are contained in the hospitalization cost interval distribution model normally distributed in all the setting stages, the value of i is unchanged, otherwise, the value of i is accumulated by 1;
if the final value of i is 0, the cost early warning is not started, if the final value of i is 1, the primary cost early warning is started, and if the final value of i is 2, the secondary cost early warning is started.
Preferably, the method further comprises the steps of:
and on the premise of not starting expense early warning, calculating the similarity to obtain the consumption ratio of the nearest neighbor patient in each set stage in the historical data, and recommending according to the consumption of the nearest neighbor patient if the consumption ratio of the nearest neighbor patient in each set stage in the historical data is contained in the consumption ratio interval distribution model.
Another aspect of the present application further provides a cost refinement control apparatus under a DRG system, including:
the model establishing module is used for carrying out statistical analysis on historical data of hospital inpatients grouped according to DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model and a proportion consumption interval distribution model which are normally distributed in each set stage in the medical process, and establishing a cost prediction model in each set stage in the medical process, wherein the set stage comprises four stages of a regulation period of preoperative illness states, a waiting operation period, an operation period and a postoperative recovery period which are divided according to actual conditions in the diagnosis and treatment process grouped according to the DRG;
the cost calculation module is used for acquiring the current cost actual value of each setting stage and calculating a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage;
and the early warning module is used for determining whether the expense early warning is needed according to the size relationship among the current expense actual value, the real-time expense predicted value and all the expense predicted values of each set stage, and starting the expense early warning of the corresponding set stage in a grading manner when the expense early warning is determined to be needed.
Preferably, the method further comprises the following steps:
and the auxiliary decision module is used for obtaining the consumption ratio of the nearest neighbor patient in each set stage in the historical data by calculating the similarity on the premise of not starting expense early warning, and recommending according to the consumption of the nearest neighbor patient if the consumption ratio of the nearest neighbor patient in each set stage in the historical data is contained in the consumption ratio interval distribution model.
The application also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the cost fine control method under the DRG system.
In another aspect, the present application further provides a storage medium, where the storage medium includes a stored program, and when the program runs, the apparatus on which the storage medium is located is controlled to execute the steps of the fee refinement control method under the DRG system.
Compared with the prior art, the method has the following beneficial effects:
the application provides a cost fine control method, a device and electronic equipment under a DRG system, wherein the method comprises the following steps: performing statistical analysis on historical data of hospital inpatients grouped according to DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model and a proportion consumption interval distribution model which are normally distributed at each set stage in the medical process, and establishing a cost prediction model at each set stage in the medical process; acquiring the current cost actual value of each setting stage, and calculating to obtain a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage; and determining whether the cost early warning is needed according to the size relation of the current cost actual value, the real-time cost predicted value and the total cost predicted value of each setting stage, and starting the cost early warning of the corresponding setting stage in a grading manner when the cost early warning is determined to be needed. The method is based on the DRG pre-grouping technology, extends to each set stage in the diagnosis and treatment process of doctors, and is higher in real-time performance by building a real-time early warning model of the medical process cost of patients, and doctors can predict the hospitalization cost of each stage in real time according to the built interval distribution model and the cost prediction model, so that hospitals are better adapted to the DRG medical insurance payment mode of relevant grouping according to disease diagnosis.
In addition to the objects, features and advantages described above, other objects, features and advantages will be apparent from the present application. The present application will now be described in further detail with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a schematic flow chart of a cost refinement control method under the DRG system in the preferred embodiment of the present application.
Fig. 2 is a flow chart illustrating the sub-steps of step S1 according to the preferred embodiment of the present application.
Fig. 3 is a flow chart illustrating the sub-steps of step S1 according to another preferred embodiment of the present application.
Fig. 4 is a flow chart illustrating the sub-steps of step S2 according to the preferred embodiment of the present application.
Fig. 5 is a flow chart illustrating the sub-steps of step S3 according to the preferred embodiment of the present application.
Fig. 6 is a schematic flow chart of a cost refinement control method under a DRG system according to another preferred embodiment of the present application.
Fig. 7 is a schematic diagram of a module of a cost refinement control device under the DRG system in the preferred embodiment of the present application.
FIG. 8 is a schematic diagram of a module of a cost refinement control device under DRG system according to another preferred embodiment of the present application.
Fig. 9 is a schematic block diagram of an electronic device entity of the preferred embodiment of the present application.
Fig. 10 is an internal structural view of a computer device of the preferred embodiment of the present application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1, a preferred embodiment of the present application provides a cost refinement control method under a DRG system, including the steps of:
s1, performing statistical analysis on historical data of hospital inpatients grouped according to DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model and a proportion consumption interval distribution model which are normally distributed in each set stage in a medical process, and establishing a cost prediction model in each set stage in the medical process, wherein the set stage comprises four stages of a regulation period (registration in admission to surgical application submission), a waiting period (surgical application to surgical start), a surgical period (surgical start to surgical end) and a post-operative recovery period (surgical end to patient discharge) of pre-operative conditions, which are divided according to actual conditions in a diagnosis and treatment process after the DRG is grouped according to the actual conditions;
s2, obtaining the current cost actual value of each setting stage, and calculating to obtain a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage;
and S3, determining whether cost early warning is needed according to the size relation among the current cost actual value, the real-time cost predicted value and all the cost predicted values of each set stage, and starting the cost early warning of the corresponding set stage in a grading manner when determining that the cost early warning is needed.
The embodiment provides a cost fine control method under a DRG system, which comprises the following steps: s1, performing statistical analysis on historical data of hospital inpatients grouped according to DRG to obtain an inpatient expense interval distribution model, an inpatient time interval distribution model and a proportion consumption interval distribution model which are normally distributed at each set stage in the medical process, and establishing a expense prediction model at each set stage in the medical process; s2, obtaining the current cost actual value of each setting stage, and calculating to obtain a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage; and S3, determining whether cost early warning is needed according to the size relation of the current cost actual value, the real-time cost predicted value and the total cost predicted value of each set stage, and starting the cost early warning of the corresponding set stage in a grading manner when the cost early warning is determined to be needed. The embodiment is based on a DRG pre-grouping technology, extends to each set stage in the diagnosis and treatment process of a doctor, realizes cost prediction of specific patients at different time nodes by building a patient medical process cost real-time early warning model, realizes real-time early warning of cost by combining a cost staged interval estimation model, has higher real-time performance, and can predict hospitalization cost of each stage in real time by the doctor according to the built interval distribution model and the cost prediction model, so that a hospital can better adapt to a DRG medical insurance payment mode grouped according to disease diagnosis.
Preferably, as shown in fig. 2, the statistical analysis is performed on the historical data of the hospital inpatients grouped according to the DRG to obtain an hospitalization cost interval distribution model, an hospitalization time interval distribution model and a proportion consumption interval distribution model which are normally distributed at each set stage in the medical process, and the statistical analysis specifically includes the following steps:
s101, acquiring hospital inpatient historical data from a hospital inpatient historical database, and grouping the hospital inpatient historical data through an in-hospital grouping device to obtain different DRG grouping data;
s102, performing statistical analysis on the DRG grouped data according to the set stage to obtain relevant medical data, wherein the relevant medical data comprises hospitalization cost, hospitalization time, treatment, medical care, consumable use, medicine use and inspection items;
s103, removing outliers from the relevant medical data subjected to statistical analysis through a stepwise linear regression method to achieve the purpose of denoising;
s104, constructing an hospitalization cost interval distribution model, an hospitalization duration interval distribution model and a occupation ratio interval distribution model of each set stage under corresponding DRG grouped data through data transformation to form a normally distributed hospitalization cost interval distribution model u1 +/-3 sigma 1, a normally distributed hospitalization duration interval distribution model u2 +/-3 sigma 2 and a normally distributed occupation ratio interval distribution model u4 +/-3 sigma 4, wherein u1 is an average value of hospitalization cost of each set stage under corresponding DRG grouped data, sigma 1 is an occupation cost variance of each set stage under corresponding DRG grouped data, u2 is an average value of hospitalization duration of each set stage under corresponding DRG grouped data, a unit is day, sigma 2 is an occupation duration variance of each set stage under corresponding DRG grouped data, u4 is an occupation ratio average value of each set stage under corresponding DRG grouped data, and sigma 4 is an occupation ratio variance of each set stage under corresponding DRG grouped data;
s105, calculating the average hospitalization cost u3 of each set stage under the corresponding DRG grouping data according to the normally distributed average hospitalization cost u1 and the average hospitalization duration u 2:
u3= u1/ u2。
preferably, as shown in fig. 3, the establishing of the cost prediction model at each setting stage in the medical procedure specifically includes the steps of:
s110, establishing a multivariate linear model of each set stage in the medical process:
Fcost = a1*x1+a2*x2+a3*x3+a4*x4+a5*x5+a6*x6…+an*xn
in the model construction process, performing variable correlation analysis, variable importance analysis and variable screening, wherein a dependent variable Fcost is a predicted value of the cost in a set stage, independent variables x1, x2, x3, x4, x5 and x6 … xn are typical fields of a cost detail data table, including age, physical conditions of hospital admission, the number of hospitalization days in each set stage, examination items and cost, medicine use conditions and consumable material use conditions, and a1, a2, a3, a4, a5 and a6 … an are weights corresponding to respective variables;
and S111, performing data fitting on the multi-element linear model machine through hospital inpatient historical data to obtain the numerical values of the weights corresponding to the respective variables, and obtaining the cost prediction model of each set stage in the medical process.
Preferably, as shown in fig. 4, the acquiring of the current cost actual value of each setting stage and the calculating of the real-time cost predicted value and the total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage specifically include the steps of:
s21, obtaining the current cost actual value Y1 of each set stage from the system;
s22, calculating to obtain a real-time expense predicted value T1 corresponding to each setting stage according to the expense prediction model of each setting stage;
s23, calculating all the cost predicted values corresponding to the setting stages according to the real-time cost predicted value T1, the average hospitalization cost u3 and the remaining days N of hospitalization corresponding to the setting stages:
T2=T1+ u3*N。
preferably, as shown in fig. 5, the determining whether to need early warning according to the magnitude relationship between the current actual cost value, the real-time predicted cost value and all the predicted cost values of each setting stage, and starting the early warning of the cost of the corresponding setting stage at a time division level when determining that the early warning is needed specifically includes the steps of:
s31, setting a counter and setting an initial value i of the counter to be 0;
s32, when the real-time cost predicted value T1 corresponding to each setting stage is smaller than the current cost actual value Y1 of each setting stage, accumulating the value of i by 1, otherwise, keeping the value of i unchanged;
s33, if all the cost predicted values T2 of all the setting stages are contained in the hospitalization cost interval distribution model in normal distribution of all the setting stages, the value of i is unchanged, otherwise, the value of i is accumulated by 1;
and S34, if the final value of i is 0, not starting the expense early warning, if the final value of i is 1, starting the primary expense early warning, and if the final value of i is 2, starting the secondary expense early warning.
Preferably, as shown in fig. 6, the cost refinement control method under the DRG system further includes the steps of:
and S4, on the premise of not starting expense early warning, obtaining the consumption ratio of the nearest neighbor patient in each set stage in the historical data by calculating the similarity, and if the consumption ratio of the nearest neighbor patient in each set stage in the historical data is contained in the consumption ratio interval distribution model, recommending according to the consumption of the nearest neighbor patient. In the embodiment, the consumption ratio data of patients in different stages are used as indexes, and the use of consumables of the patients is recommended according to the consumable use condition of the nearest neighbor patient setting stage in historical data, so that the cost is controlled to a certain extent, and meanwhile, the method plays a role in assisting decision-making on a patient treatment method.
The cost fine control process of the application is described as follows by taking the orthopedic cost early warning flow under a certain hospital DRG system as an example:
s1, historical data of hospital inpatients after entering a group according to DRG comprises the following steps:
patient history data includes medical insurance card data, hospitalization details, etc., including:
1.1, population data, gender, age, medical insurance status and the like;
1.2, examination item data including blood routine, urinalysis data and the like;
1.3, consumable, nursing and medication;
1.4, surgical consumables and treatment;
s2, selecting IG19 groups (muscle and tendon operations), and mainly diagnosing and selecting 'S59.700 forearm multiple injuries' and industrial benchmarking total cost 13445.83 yuan;
s3, the DRG group aggregated in 2016-2022 is IG19 grouped data, the total is 600 cases, and the data are naturally divided into 4 stages according to each case: the method comprises the following steps of adjusting the condition before operation, waiting for the operation, performing the operation and recovering after the operation to obtain 600 x4 matrix data, wherein for example, the total cost of a certain patient is 14677, and the four-stage cost is 4313.4, 2556.3, 5388.4 and 2477.1 respectively;
s4, removing outliers by a stepwise linear regression method to obtain 553 historical data and 553 x4 matrix data, and then obtaining 4 stages of 553 historical data, wherein the average values u1 of hospitalization costs of the 553 historical data are 4223.3, 2867.5, 5501.7 and 1552.6 respectively through data statistical analysis, and the variance sigma of the hospitalization costs are 516.3, 223.4, 341.7 and 311.2 respectively;
s5, constructing a multivariate linear model in stages, for example, in the regulation period of the condition of the disease before the operation, constructing a multivariate linear model with independent variables of cost, dependent variable Fcost, hospital stay number, examination items, consumables, medical care, medication, complications and the like, and obtaining a cost prediction model by fitting 553 cases of data:
fcost =3.61 days of hospitalization +54.90 inspection item +2.54 consumables
S6, for each patient, as long as the patient is in the adjusting period of the pre-operation illness state, obtaining a real-time cost predicted value T1 of the current stage according to the cost prediction model, obtaining a current cost actual value Y1 of the stage from the system, and finally, calculating all cost predicted values T2 corresponding to the stage according to the real-time cost predicted value T1, the average hospitalization cost u3 and the remaining number of hospitalization days N;
s7, starting an early warning process according to the diagram shown in FIG. 5, thereby realizing fine control of the cost of each stage in the medical process;
and S8, on the premise of not starting expense early warning, obtaining the consumption ratio of the nearest neighbor patient in each set stage in the historical data by calculating the similarity, and recommending according to the consumption ratio of the nearest neighbor patient in each set stage in the historical data if the consumption ratio of the nearest neighbor patient in each set stage in the historical data is contained in the consumption ratio interval distribution model, so that expense is controlled, and an auxiliary decision-making effect is also played for a patient treatment method.
As shown in fig. 7, in another aspect, the present application further provides a cost refinement control device under a DRG system, including:
the model establishing module is used for carrying out statistical analysis on historical data of hospital inpatients grouped according to DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model and a proportion consumption interval distribution model which are normally distributed in each set stage in the medical process, and establishing a cost prediction model in each set stage in the medical process, wherein the set stage comprises four stages of a regulation period of preoperative illness states, a waiting operation period, an operation period and a postoperative recovery period which are divided according to actual conditions in the diagnosis and treatment process grouped according to the DRG;
the cost calculation module is used for acquiring the current cost actual value of each setting stage and calculating a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage;
and the early warning module is used for determining whether the expense early warning is needed according to the size relationship among the current expense actual value, the real-time expense predicted value and all the expense predicted values of each set stage, and starting the expense early warning of the corresponding set stage in a grading manner when the expense early warning is determined to be needed.
Preferably, as shown in fig. 8, the charge refinement control device under the DRG system further includes:
and the auxiliary decision module is used for obtaining the consumption ratio of the nearest neighbor patient in each set stage in the historical data by calculating the similarity on the premise of not starting expense early warning, and recommending according to the consumption of the nearest neighbor patient if the consumption ratio of the nearest neighbor patient in each set stage in the historical data is contained in the consumption ratio interval distribution model.
As shown in fig. 9, a preferred embodiment of the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the steps of the fee refinement control method under the DRG regime in the foregoing embodiments when executing the program.
As shown in fig. 10, the preferred embodiment of the present application also provides a computer device, which may be a terminal or a biopsy server, and the internal structure thereof may be as shown in fig. 10. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with other external computer devices through network connection. The computer program is executed by a processor to realize the steps of the cost fine control method under the DRG system.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The preferred embodiment of the present application further provides a storage medium, where the storage medium includes a stored program, and when the program runs, the apparatus where the storage medium is located is controlled to execute the steps of the fee refinement control method under the DRG system in the foregoing embodiment.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
If the functions of the method of the present embodiment are implemented in the form of software functional units and sold or used as independent products, the functions may be stored in one or more storage media readable by a computing device. Based on such understanding, part of the contribution to the prior art of the embodiments of the present application or part of the technical solution may be embodied in the form of a software product stored in a storage medium and including several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein. The scheme in the embodiment of the application can be implemented by adopting various computer languages, such as object-oriented programming language Java and transliterated scripting language JavaScript.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. A fine control method for the cost under a DRG system is characterized by comprising the following steps:
performing statistical analysis on historical data of hospital inpatients grouped according to DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model and a proportion consumption interval distribution model which are normally distributed in each set stage in the medical process, and establishing a cost prediction model in each set stage in the medical process, wherein the set stage comprises four stages of a regulation period of preoperative illness state, a waiting operation period, an operation period and a postoperative recovery period which are divided according to actual conditions in the diagnosis and treatment process after the DRG is grouped;
acquiring the current cost actual value of each setting stage, and calculating to obtain a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage;
and determining whether cost early warning is needed according to the size relationship of the current cost actual value, the real-time cost predicted value and the total cost predicted value of each set stage, and starting the cost early warning of the corresponding set stage in a grading manner when the cost early warning is determined to be needed.
2. The method of claim 1, wherein statistical analysis is performed on historical data of hospital inpatients grouped according to DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model, and a consumption-to-occupation ratio interval distribution model that are normally distributed at each setting stage in the medical procedure, and the method specifically comprises the following steps:
acquiring hospital inpatient historical data from a hospital inpatient historical database, and grouping the hospital inpatient historical data by using an in-hospital grouping device to obtain different DRG grouped data;
performing statistical analysis on each DRG grouped data according to the set stage to obtain relevant medical data, wherein the relevant medical data comprises hospitalization cost, hospitalization time, treatment, medical care, consumable material use, medicine use and inspection items;
removing outliers from the statistically analyzed relevant medical data by a stepwise linear regression method;
constructing an hospitalization expense interval distribution model, an hospitalization duration interval distribution model and a occupation ratio interval distribution model of each set stage under corresponding DRG grouped data through data transformation to form a normally distributed hospitalization expense interval distribution model u1 +/-3 sigma 1, a normally distributed hospitalization duration interval distribution model u2 +/-3 sigma 2 and a normally distributed occupation ratio interval distribution model u4 +/-3 sigma 4, wherein u1 is an average value of hospitalization expenses of each set stage under corresponding DRG grouped data, sigma 1 is an occupation expense variance of each set stage under corresponding DRG grouped data, u2 is an average value of the hospitalization durations of each set stage under corresponding DRG grouped data, a unit is day, sigma 2 is an occupation ratio variance of each set stage under corresponding DRG grouped data, u4 is an occupation ratio average value of each set stage under corresponding DRG grouped data, and sigma 4 is an occupation ratio variance of each set stage under corresponding DRG grouped data;
according to the normally distributed average value u1 of the hospitalization cost and the average value u2 of the length of hospitalization, calculating the average daily hospitalization cost of each set stage under the corresponding DRG grouping data:
u3= u1/ u2。
3. the method for fine control of expenses under the DRG system according to claim 1, wherein the step of establishing an expense prediction model at each set stage in the medical procedure specifically comprises the steps of:
establishing a multivariate linear model of each set stage in the medical process:
Fcost = a1*x1+a2*x2+a3*x3+a4*x4+a5*x5+a6*x6…+an*xn
in the model construction process, performing variable correlation analysis, variable importance analysis and variable screening, wherein a dependent variable Fcost is a predicted value of the cost in a set stage, independent variables x1, x2, x3, x4, x5 and x6 … xn are typical fields of a cost detail data table, including age, physical conditions of hospital admission, the number of hospitalization days in each set stage, examination items and cost, medicine use conditions and consumable material use conditions, and a1, a2, a3, a4, a5 and a6 … an are weights corresponding to respective variables;
and performing data fitting on the multivariate linear model machine through the historical data of the inpatients in the hospital to obtain the numerical values of the weights corresponding to the respective variables, and obtaining the cost prediction model of each set stage in the medical process.
4. The method according to claim 2, wherein the step of obtaining the current cost actual value of each setting stage and calculating the real-time cost predicted value and the total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage comprises the steps of:
obtaining the current cost actual value Y1 of each set stage from the system;
calculating to obtain a real-time expense predicted value T1 corresponding to each set stage according to the expense prediction model of each set stage;
calculating all the cost predicted values corresponding to the setting stages according to the real-time cost predicted value T1, the average hospitalization cost u3 and the remaining days N of hospitalization corresponding to the setting stages:
T2=T1+ u3*N。
5. the method for fine control of expenses under the DRG system according to claim 4, wherein the method for determining whether an early warning is needed according to a magnitude relationship between the current actual value of expenses, the real-time predicted value of expenses, and the predicted value of all expenses in each setting stage, and starting the expense early warning in the corresponding setting stage at a time-division level when the early warning is determined to be needed, comprises the steps of:
setting a counter and setting an initial value i of the counter to 0;
when the real-time expense predicted value T1 corresponding to each setting stage is less than the current expense actual value Y1 of each setting stage, accumulating the value of i by 1, otherwise, keeping the value of i unchanged;
if all the cost predicted values T2 of all the setting stages are contained in the hospitalization cost interval distribution model normally distributed in all the setting stages, the value of i is unchanged, otherwise, the value of i is accumulated by 1;
if the final value of i is 0, the cost early warning is not started, if the final value of i is 1, the primary cost early warning is started, and if the final value of i is 2, the secondary cost early warning is started.
6. The fine control method of the cost under the DRG system according to claim 1, further comprising the steps of:
and on the premise of not starting expense early warning, calculating the similarity to obtain the consumption ratio of the nearest neighbor patient in each set stage in the historical data, and recommending according to the consumption of the nearest neighbor patient if the consumption ratio of the nearest neighbor patient in each set stage in the historical data is contained in the consumption ratio interval distribution model.
7. A fine control device for the cost under the DRG system is characterized by comprising:
the model establishing module is used for carrying out statistical analysis on historical data of hospital inpatients grouped according to the DRG to obtain an inpatient cost interval distribution model, an inpatient time interval distribution model and a consumption-occupation ratio interval distribution model which are normally distributed in each set stage in the medical process, and establishing a cost prediction model in each set stage in the medical process, wherein the set stage comprises four stages of a regulation period of preoperative illness state, a waiting operation period, an operation period and a postoperative recovery period which are divided according to actual conditions in the diagnosis and treatment process grouped according to the DRG;
the cost calculation module is used for acquiring the current cost actual value of each setting stage and calculating a real-time cost predicted value and a total cost predicted value corresponding to each setting stage according to the cost prediction model of each setting stage;
and the early warning module is used for determining whether the expense early warning is needed according to the size relationship among the current expense actual value, the real-time expense predicted value and all the expense predicted values of each set stage, and starting the expense early warning of the corresponding set stage in a grading manner when the expense early warning is determined to be needed.
8. The apparatus of claim 7, further comprising:
and the auxiliary decision module is used for obtaining the consumption ratio of the nearest neighbor patient in each set stage in the historical data by calculating the similarity on the premise of not starting expense early warning, and recommending according to the consumption of the nearest neighbor patient if the consumption ratio of the nearest neighbor patient in each set stage in the historical data is contained in the consumption ratio interval distribution model.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor,
the processor, when executing the program, implements the steps of the fee refinement control method under the DRG regime of any one of claims 1 to 6.
10. A storage medium including a stored program, characterized in that,
the steps of controlling a device in which the storage medium is located to execute a fee-refining control method under the DRG regime as set forth in any one of claims 1 to 6 when the program is run.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310011003.4A CN115910308B (en) | 2023-01-05 | 2023-01-05 | Method and device for finely controlling cost under DRG system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310011003.4A CN115910308B (en) | 2023-01-05 | 2023-01-05 | Method and device for finely controlling cost under DRG system and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115910308A true CN115910308A (en) | 2023-04-04 |
| CN115910308B CN115910308B (en) | 2023-06-13 |
Family
ID=86497028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310011003.4A Active CN115910308B (en) | 2023-01-05 | 2023-01-05 | Method and device for finely controlling cost under DRG system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115910308B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160253687A1 (en) * | 2015-02-26 | 2016-09-01 | Aetna Inc. | System and method for predicting healthcare costs |
| CN111898797A (en) * | 2020-06-22 | 2020-11-06 | 青岛国新健康产业科技有限公司 | Medical expense prediction method and device, electronic equipment and storage medium |
| US20210049241A1 (en) * | 2019-08-13 | 2021-02-18 | International Business Machines Corporation | Predictive Multi-Stage Modelling for Complex Process Control |
| CN112652389A (en) * | 2021-01-19 | 2021-04-13 | 浙江建达科技股份有限公司 | Fee control method based on DRGs pre-grouping |
| CN113112372A (en) * | 2021-02-26 | 2021-07-13 | 太平洋医疗健康管理有限公司 | Medical insurance payment early warning system and processing method thereof |
| US20210295987A1 (en) * | 2019-03-27 | 2021-09-23 | General Electric Company | Monitoring, predicting and alerting for census periods in medical inpatient units |
| CN113570162A (en) * | 2021-08-30 | 2021-10-29 | 平安医疗健康管理股份有限公司 | Hospitalization cost prediction method and device based on artificial intelligence and computer equipment |
| CN113722507A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Hospital cost prediction method and device based on knowledge graph and computer equipment |
| CN115482921A (en) * | 2022-08-01 | 2022-12-16 | 杭州吉音医疗科技有限公司 | Modeled DRGs clinical path planning management information system and method |
-
2023
- 2023-01-05 CN CN202310011003.4A patent/CN115910308B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160253687A1 (en) * | 2015-02-26 | 2016-09-01 | Aetna Inc. | System and method for predicting healthcare costs |
| US20210295987A1 (en) * | 2019-03-27 | 2021-09-23 | General Electric Company | Monitoring, predicting and alerting for census periods in medical inpatient units |
| US20210049241A1 (en) * | 2019-08-13 | 2021-02-18 | International Business Machines Corporation | Predictive Multi-Stage Modelling for Complex Process Control |
| CN111898797A (en) * | 2020-06-22 | 2020-11-06 | 青岛国新健康产业科技有限公司 | Medical expense prediction method and device, electronic equipment and storage medium |
| CN112652389A (en) * | 2021-01-19 | 2021-04-13 | 浙江建达科技股份有限公司 | Fee control method based on DRGs pre-grouping |
| CN113112372A (en) * | 2021-02-26 | 2021-07-13 | 太平洋医疗健康管理有限公司 | Medical insurance payment early warning system and processing method thereof |
| CN113570162A (en) * | 2021-08-30 | 2021-10-29 | 平安医疗健康管理股份有限公司 | Hospitalization cost prediction method and device based on artificial intelligence and computer equipment |
| CN113722507A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Hospital cost prediction method and device based on knowledge graph and computer equipment |
| CN115482921A (en) * | 2022-08-01 | 2022-12-16 | 杭州吉音医疗科技有限公司 | Modeled DRGs clinical path planning management information system and method |
Non-Patent Citations (4)
| Title |
|---|
| CHE-WEI CHANG: "Constructing a Novel Early Warning Algorithm for Global Budget Payments", MATHEMATICAL ANALYSIS IN ECONOMICS AND MANAGEMENT, vol. 8, no. 11 * |
| JINGHUI LIU, ETC: "Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes", NPJ DIGITAL MEDICINE, vol. 4, pages 1 - 8 * |
| 张慧: "基于DRGs分组的费用预测模型研究与实现", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》, no. 5, pages 1 - 63 * |
| 高峰;郑二维;张清芝;腾慧杰;: "基于决策树模型脑卒中患者住院费用DRG分组实证研究", 中国卫生经济, no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115910308B (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang | ATTAIN: Attention-based time-aware LSTM networks for disease progression modeling. | |
| Peine et al. | Development and validation of a reinforcement learning algorithm to dynamically optimize mechanical ventilation in critical care | |
| US20140279754A1 (en) | Self-evolving predictive model | |
| US7716147B2 (en) | Real-time predictive computer program, model, and method | |
| JP2016197330A (en) | Analysis system, and rehabilitation support system, method, and program | |
| CN112562836A (en) | Doctor recommendation method and device, electronic equipment and storage medium | |
| JP6148255B2 (en) | Method and system for reducing early readmission | |
| Krikunov et al. | Complex data-driven predictive modeling in personalized clinical decision support for Acute Coronary Syndrome episodes | |
| WO2019045637A2 (en) | A predictive analytics solution for personalized clinical decision support | |
| US20210375464A1 (en) | Assistance system, assistance method, and assistance program | |
| CN116453706B (en) | Hemodialysis scheme making method and system based on reinforcement learning | |
| Ala et al. | Alternative mathematical formulation and hybrid meta-heuristics for patient scheduling problem in health care clinics | |
| US7707130B2 (en) | Real-time predictive computer program, model, and method | |
| KR20190099901A (en) | Patient information based medication management device and method | |
| Adams et al. | Surgical procedure prediction using medical ontological information | |
| EP3929939A1 (en) | System and method for peri-anaesthetic risk evaluation | |
| CN115910308A (en) | Expense fine control method and device under DRG system, and electronic equipment | |
| Adams et al. | Physician rostering for workload balance | |
| Hu et al. | A first step towards behavioral coaching for managing stress: a case study on optimal policy estimation with multi-stage threshold Q-learning | |
| Iantovics | The CMDS medical diagnosis system | |
| US7877341B2 (en) | Self-adaptive data pre-fetch by artificial neuron network | |
| CN113940640A (en) | Cardiovascular disease risk control method, system and storage medium | |
| KR20220138327A (en) | Apparatus, method and program for providing disease symptom and treatment informetion predicting service | |
| LeBoulluec et al. | Outcome and state transition modeling for adaptive interdisciplinary pain management | |
| Moghimi et al. | Intelligent home risk-based monitoring solutions enable post acute care surveillance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |