A medical performance optimization management method and device

Abstract

The present disclosure provides a medical performance optimization management method and device, belonging to the technical field of management systems, the method comprising: based on a first screening condition, screening sample data of group DRGs from sample data of group DRGs contained in a first sample data set to form a second sample data set; constructing a dual objective function of the CMI value and cost index of the target hospital based on the second sample data set; solving the dual objective function to obtain multiple candidate solution combinations, updating the first sample data set based on the multiple candidate solution combinations, respectively calculating the first CMI value and the first cost index of the target hospital based on the multiple updated first sample data sets, respectively determining the corresponding first CMI value and the first cost index The optimal candidate solution combination is determined as a target variable combination, and resource allocation management of the target hospital is performed based on the target variable combination. The medical performance optimization management method and device provided by the present disclosure can achieve reasonable allocation of medical resources.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of management systems, and more specifically, to a medical performance optimization management method and device. Background Art

[0002] With the implementation and popularization of the diagnosis-related groups (DRGs) payment system, the DRGs payment system has received more and more attention in the fields of payment reform and performance evaluation, and has played a positive role in promoting the formation of a scientific and efficient medical service incentive system. However, if this system cannot be effectively combined with hospital management and performance evaluation, the impact on the refined management of public hospitals will still be very limited. Therefore, it is particularly important to explore and optimize the model of hospital performance appraisal under the new institutional framework. Under this situation, public hospitals have started DRGs payment reform, performance appraisal and other work, established a hospital performance management model suitable for the DRGs payment system, and built a performance evaluation system consistent with the hospital's strategic goals.

[0003] As one of the commonly used indicators of the DRGs evaluation system, the Case Mix Index (CMI) has been widely used in existing studies in recent years. Most of the existing studies pursue high CMI values. However, the higher the CMI, the better. The pursuit of high CMI does not necessarily allow departments and medical institutions to obtain higher profits. For diseases with long hospitalization time and a high proportion of drugs and consumables, although the CMI calculated value is high, the economic value may not be high. Therefore, it is of vital importance to increase the CMI value as much as possible while ensuring that the hospital's income and expenditure are balanced. However, there are few studies on this aspect. Summary of the invention

[0004] The purpose of the present disclosure is to provide a medical performance optimization management method and device, which can improve the CMI value as much as possible and achieve reasonable allocation of medical resources on the basis of ensuring the balance of hospital revenue and expenditure.

[0005] A first aspect of the embodiments of the present disclosure provides a medical performance optimization management method, comprising: Based on the first filtering condition, the first sample data set contains Screening of sample data of DRGs The sample data of each group of DRGs constitutes the second sample data set; the sample data of each group of DRGs includes the number of cases, case costs and CMI values ​​corresponding to multiple hospitals in the target area; A dual objective function of the CMI value and the cost index of the target hospital is constructed based on the second sample data set; the target hospital is any hospital in the target area; the cost index is used to characterize the deviation between the income cost and the expenditure cost; Solving the dual objective function to obtain multiple candidate solution combinations, each of which includes the number of cases and the average cost per case; The first sample data set is updated based on the multiple candidate solution combinations to obtain multiple updated first sample data sets, the first CMI value and the first cost index of the target hospital are calculated based on the multiple updated first sample data sets, the optimal candidate solution combination of the corresponding first CMI value and the first cost index is determined as the target variable combination, and resource allocation management of the target hospital is performed based on the target variable combination.

[0006] A second aspect of the embodiments of the present disclosure provides a medical performance optimization management device, including: A data screening module is used to select the first sample data set from the first sample data set based on the first screening condition. Screening of sample data of DRGs The sample data of each group of DRGs constitutes the second sample data set; the sample data of each group of DRGs includes the number of cases, case costs and CMI values ​​corresponding to multiple hospitals in the target area; The first calculation module is used to construct a dual objective function of the CMI value and the cost index of the target hospital based on the second sample data set; the target hospital is any hospital in the target area; the cost index is used to characterize the deviation between the income cost and the expenditure cost; A second calculation module is used to solve the dual objective function to obtain multiple candidate solution combinations, each of which includes the number of cases and the average cost per case; A resource allocation module is used to update the first sample data set based on the multiple candidate solution combinations to obtain multiple updated first sample data sets, calculate the first CMI value and the first cost index of the target hospital based on the multiple updated first sample data sets, determine the optimal candidate solution combination of the corresponding first CMI value and the first cost index as the target variable combination, and perform resource allocation management of the target hospital based on the target variable combination.

[0007] A third aspect of an embodiment of the present disclosure provides an electronic device, 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 performance optimization management method when executing the computer program.

[0008] According to a fourth aspect of an embodiment 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 performance optimization management method are implemented.

[0009] The beneficial effects of the medical performance optimization management method and device provided by the embodiments of the present disclosure are: In the disclosed embodiment, the cost index is used to characterize the deviation between the hospital's income costs and expenditure costs. Taking into account the dual needs of the CMI value and the cost index, a second sample data set is screened from the first sample data set, and a dual objective function is constructed based on the second sample data set. By solving the dual objective function, multiple candidate solution combinations of the number of cases and the average cost per case are obtained. The multiple candidate solution combinations are respectively introduced into the first sample data set to obtain the overall CMI value and cost index (that is, the first CMI value and the first cost index) of the target hospital. The optimal candidate solution combination of the corresponding first CMI value and the first cost index is selected, and resource allocation management of the target hospital is performed based on the candidate solution combination, so that the CMI value and cost index of the target hospital can be optimized.

[0010] The method of the disclosed embodiment can promote tiered diagnosis and treatment, ensure the operation of primary medical institutions, and at the same time allow tertiary hospitals to return to their original positions, shift the focus of medical care to the diagnosis and treatment of difficult and complicated diseases, and achieve reasonable allocation of medical resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] 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.

[0012] Figure 1 A flowchart of a medical performance optimization management method provided by an embodiment of the present disclosure; Figure 2 A flowchart of another medical performance optimization management method provided by an embodiment of the present disclosure; Figure 3 An algorithm flow chart of an improved non-dominated sorting genetic algorithm provided by an embodiment of the present disclosure; Figure 4 A schematic diagram of a candidate solution combination of an objective function provided by an embodiment of the present disclosure; Figure 5 A structural block diagram of a medical performance optimization management device provided by an embodiment of the present disclosure; Figure 6 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] 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.

[0014] 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.

[0015] Please refer to Figure 1-Figure 2 , Figure 1 A flowchart of a medical performance optimization management method provided in one embodiment of the present disclosure, the method comprising: S101: based on the first screening condition, select the first sample data set from the Screening of sample data of DRGs The sample data of each group of DRGs constitute the second sample data set; the sample data of each group of DRGs includes the number of cases, case costs and CMI values ​​corresponding to multiple hospitals in the target area.

[0016] In this embodiment, the medical record homepage data of 17 hospitals in the target area in a certain year were counted, with a data volume of about 760,000, and the default DRGs inclusion rate was 100%. It should be noted that this study uses medical DRGs, and high-rate and low-rate cases and the actual payment group by project are not taken into consideration for the time being. The CMI and cost ratio of each hospital are shown in Table 1, where the cost ratio represents the ratio between settlement costs (that is, income costs) and hospital costs (expenditure costs). Based on the cost ratio, the cost index can be obtained.

[0017]

[0018] In Table 1, hospitals with a cost-to-performance ratio greater than 1 are profitable hospitals, and hospitals with a cost-to-performance ratio less than 1 are loss-making hospitals.

[0019] Considering that under normal circumstances, there are about 600 groups of DRGs involved in tertiary hospitals, in order to reduce the amount of calculation, the present invention only screens representative DRGs for optimization, which can play a multiplier effect. S102: Constructing a dual objective function of the CMI value and the cost index of the target hospital based on the second sample data set; the target hospital is any hospital in the target area.

[0020] In this embodiment, for any hospital in the target area, for example, the target hospital The two main factors that affect its optimization results are medical performance Value and Cost Index .

[0021] Among them, the case mix index (CMI value) is an important indicator to measure the technical difficulty of medical services. The higher the CMI value, the higher the technical difficulty of the cases treated by the hospital department. CMI is the average weight of a hospital, which is related to the types of cases admitted by the hospital. If the hospital admits more cases with high weights, the CMI value will be larger. The average weight generally reflects the difference in treatment costs between different types of cases. The more complicated the condition, the higher the treatment cost. Therefore, a high CMI value is usually considered to be a manifestation of the difficulty of evaluating the cases admitted by this hospital.

[0022] Cost Index It is used to characterize the deviation between medical insurance income (i.e. income cost) and medical insurance expenditure (i.e. expenditure cost). Medical insurance income is mainly the fees paid by medical insurance institutions to hospitals according to certain payment standards and settlement methods. Here, the regional average cost provided by the medical insurance department can be used as the specific value of medical insurance income. Medical insurance expenditure is the cost incurred by the hospital in providing medical services to insured patients and paid by the medical insurance fund, including drug costs, medical treatment costs, inspection and testing costs, etc. Here, the average cost of the target hospital can be used as medical insurance expenditure. Each hospital should aim to have a ratio of medical insurance income to medical insurance expenditure close to 1.

[0023] By constructing a dual objective function, a trade-off relationship can be found between the CMI value and the cost index, because the above two objectives often influence and restrict each other in practice. For example, increasing the CMI value may mean receiving more complex cases, which will affect the cost index, so it is necessary to consider both comprehensively to construct a functional relationship.

[0024] S103: Solving the dual objective function to obtain multiple candidate solution combinations, each candidate solution combination including the number of cases and the average cost per case.

[0025] In this embodiment, existing multi-objective optimization algorithms such as simulated annealing algorithm (SA), particle swarm algorithm (PSO), non-dominated sorting genetic algorithm (NSGA-II) can be used to solve the dual objective function by adjusting the two variables of the number of cases and the average cost per case. Because it is a dual objective optimization problem, there is usually no absolutely optimal single solution, but multiple candidate solution combinations that meet certain conditions will be obtained. Each candidate solution combination contains two key variables, the number of cases and the average cost per case. The number of cases reflects the scale of the hospital's business volume, and the average cost per case reflects the average cost per case. The above candidate solution combination represents the different trade-offs between the two objectives of CMI value and cost index under different configurations of the number of cases and the average cost per case.

[0026] S104: Update the first sample data set based on multiple candidate solution combinations to obtain multiple updated first sample data sets, calculate the first CMI value and the first cost index of the target hospital based on the multiple updated first sample data sets, determine the corresponding optimal candidate solution combination of the first CMI value and the first cost index as the target variable combination, and perform resource allocation management of the target hospital based on the target variable combination.

[0027] In this embodiment, first, the number of cases and average cost per case in each candidate solution combination is substituted into the corresponding DRGs sample data in the first sample data set, and multiple updated first sample data sets can be obtained. Then, based on each updated data set, the corresponding first CMI value and first cost index of the target hospital are recalculated. The above process can simulate the corresponding performance of the target hospital under different configuration modes (determined by the candidate solution combination). Finally, by comparing the first CMI values ​​and first cost indexes calculated under various configuration modes, the optimal candidate solution combination is selected and determined as the target variable combination.

[0028] The target variable combination represents the resource allocation strategy that makes the CMI value and the cost index reach an ideal state. The hospital's resource allocation management is carried out based on the target variable combination. For example, the number of medical staff, medical equipment procurement, ward allocation and other resources can be reasonably arranged to match them with the selected optimal resource allocation strategy, thereby optimizing medical performance.

[0029] It can be concluded from the above that this embodiment comprehensively considers the needs of CMI value and cost index, selects the second sample data set from the first sample data set, constructs a dual objective function based on the second sample data set, obtains multiple candidate solution combinations of the number of cases and the average cost per case by solving the dual objective function, and brings the multiple candidate solution combinations into the first sample data set respectively to obtain the overall CMI value and cost index (that is, the first CMI value and the first cost index) of the target hospital, selects the optimal candidate solution combination of the corresponding first CMI value and the first cost index, and performs resource allocation management of the target hospital based on the candidate solution combination, so as to achieve the optimal CMI value and cost index of the target hospital.

[0030] The method of this embodiment can promote hierarchical diagnosis and treatment, ensure the operation of primary medical institutions, and at the same time allow tertiary hospitals to return to their original positions, shift the focus of medical care to the diagnosis and treatment of difficult and complicated diseases, and achieve reasonable allocation of medical resources.

[0031] In one embodiment of the present disclosure, calculating a first CMI value and a first cost index of a target hospital based on a plurality of updated first sample data sets respectively includes: The weight of any group of DRGs is calculated based on the first formula, which is:

[0032] The first CMI value of the target hospital is calculated based on the second formula, which is:

[0033] in, represents the weight of any group of DRGs, Indicates the total cost of cases in multiple hospitals included in the sample data of any group of DRGs, It represents the total number of cases in multiple hospitals included in the sample data of any group of DRGs; is the number of cases in the target hospital included in the sample data of any group of DRGs; The target area per capita cost for any group of DRGs is calculated based on the third formula, which is:

[0034] The average cost per case of the target hospital included in the sample data of any group of DRGs is calculated based on the fourth formula, which is:

[0035] The first cost index of the target hospital included in the sample data of any group of DRGs is calculated based on the fifth formula. The fifth formula is:

[0036] in, is the average cost per case in the target area of ​​any group of DRGs, is the case cost of the target hospital included in the sample data of any group of DRGs, is the average cost per case of the target hospital included in the sample data of any group of DRGs.

[0037] In this embodiment, the target area The sample data of group DRGs is recorded as , for any group The number of cases included is The total cost is . Cases from Hospitals, denoted as The number of cases they contain are The total costs are . Satisfies the following relationship , .

[0038] DRGs group Weight The expression is: (1) Target Hospital The CMI expression is: (2) in, DRGs group The weight of DRGs group From the target hospital The number of cases, is the number of DRGs groups.

[0039] DRGs group Average cost per region The expression is: (3) DRGs group Target Hospital Average cost The expression is: (4) Target Hospital The cost index is based on the ratio of the average cost per case in the region to the average cost per case in the target hospital, and is expressed as: (5) in, DRGs group The average regional cost is DRGs group Target Hospital The average cost per case is DRGs group From the target hospital The number of cases, is the number of DRGs groups. It is the ratio of the average medical insurance settlement cost per case in the sample data of any group of DRGs to the average cost per case in the target hospital, that is, the cost ratio.

[0040] From the above, it can be concluded that in this embodiment, the multiple candidate solution combinations are respectively put back (replacing the original data) into the overall hospital data (that is, the first sample data set) to obtain multiple updated first sample data sets, and based on each updated data set, the corresponding first CMI value and first cost index of the target hospital are recalculated, and the optimal candidate solution combination is selected from the multiple candidate solution combinations based on the recalculated results of the first CMI value and the first cost index.

[0041] In one embodiment of the present disclosure, the medical performance optimization management method further includes: Based on the first formula, we calculate The weights and weights of group DRGs; Will The weights of the group DRGs are arranged in ascending order to obtain the sequence ; Determine the value interval of the number of cases based on the sixth formula; Determine the range of average cost per case based on the seventh formula; Solve the dual objective function based on the value interval of the number of cases and the value interval of the average cost per case; The sixth formula is:

[0042] in, for The number of cases in the target hospital included in the sample data of any group of DRGs in the group DRGs, for The weight of any group of DRGs in the group DRGs, for The minimum number of cases of the target hospital included in the sample data of the first ranked DRGs in the group DRGs, for The maximum number of cases of the target hospital included in the sample data of the first ranked DRGs in the group DRGs, for The minimum number of cases of the target hospital included in the sample data of the last DRGs in the group DRGs, for The maximum number of cases of the target hospital included in the sample data of the last DRG in the group DRGs; The seventh formula is:

[0043] in, , express The average cost per case in the target area of ​​any group of DRGs, express The average cost per case of the target hospitals included in the sample data of the group DRGs.

[0044] In this example, filter out After grouping DRGs, in order to distinguish the subscript representation from the original data, '~' is added to the symbols of the filtered data to distinguish them. The optimization process involves a series of constraints to constrain the variables. and , which is crucial in the decision-making process. , : (1) Constraints , DRGs group From the hospital The number of cases should be greater than 100. DRGs with less than 100 cases are relatively weak in discipline construction and have little research significance. (2) Original The weight set of DRGs groups is recorded as , the elements in the set are arranged in ascending order as , Corresponding The number of cases in a hospital is recorded as , from this rule we can think that the weight The corresponding Number of cases in hospitals There is the following corresponding relationship, that is, when the weight is in When the hospital is in a certain interval, the corresponding number of hospital cases should be The weight interval is divided as follows: The interval where , and at the same time , ,in and Respectively Corresponding The maximum and minimum values ​​of the number of cases in the hospitals. Group DRGs, The weight is , including from hospitals The number of cases is , with the following constraints: (6) (3) Constraints , ,in , indicating DRGs group Average cost per region And its hospital Average cost The difference between them is between 0 and the mean of their differences, ensuring that the same DRGs group The average cost per case in any hospital is not much different from the average cost per case in the region.

[0045] Determining the range of values ​​for the number of cases and the average cost per case based on the above constraints can ensure that the optimization results are consistent with the actual needs of the hospital.

[0046] In one embodiment of the present disclosure, the first screening condition includes: is within the set value range, and The number of cases in the target hospital included in the sample data of each group of DRGs is greater than the first threshold, and The difference between the second CMI value and the third CMI value is less than a second threshold value, and The difference between the second fee index and the third fee index is less than a third threshold; The second CMI value is based on The CMI value of the target hospital is calculated based on the sample data of the group DRGs. The third CMI value is based on The CMI value of the target hospital is calculated based on the sample data of the DRGs group; the second cost index is based on The cost index of the target hospital is calculated based on the sample data of group DRGs. The third cost index is based on The cost index of the target hospital is calculated based on the sample data of group DRGs.

[0047] In this embodiment, in view of the computational complexity and analysis difficulties that may be caused by the huge amount of original data, in the initial stage of the experiment, some representative data are selected through the first screening condition for optimization research to achieve a reasonable reduction in the amount of data.

[0048] exist DRGs were selected from the group The DRGs of the group were used as the sample data for screening. The group data should meet the following requirements: (1) small amount of data; (2) as close to the original as possible. DRGs data of the group; (3) due to the number of cases DRGs below 100 are relatively weak in discipline construction and have little research significance, so the number of cases should be selected. DRGs greater than 100.

[0049] To do this, set the first filter condition to: (1) Setup ; (2) Command use The second CMI value calculated by group DRGs was compared with that calculated by using The ratio of the second CMI values ​​calculated for the group DRGs is closer to 1 (i.e., the difference between the second CMI value and the third CMI value is less than the second threshold); (3) Order use The second cost index calculated by group DRGs is the same as that calculated by using The ratio of the second cost index calculated for the group DRGs is closer to 1 (i.e., the difference between the second cost index and the third cost index is less than the third threshold); (4) Consider the number of cases constraints.

[0050] The specific implementation steps are as follows: (1) Calculate according to the second formula in the above embodiment Target hospitals in group DRGs The third CMI value is recorded as ; Calculated according to the fifth formula Target hospitals in group DRGs The third cost index is recorded as ; (2) Considering the number of cases under constraints , first filter out the number of cases DRGs group, a total of Group; (3) Order exist DRGs in the group are randomly selected Group, where , according to a certain order of arrangement and combination, there are possible combinations, and calculate these possible combinations separately Target hospitals in group DRGs The second CMI value is , the second cost index is ,when Iterating over a collection When possible combinations of these possible combinations Group DRGs Chinese Medicine Hospital The second CMI value is , the second cost index is ; (4) Calculated , ,in , select and Closest to 1 and ; exist In the group of DRGs, select the permutation combination with the sequence number of DRGs are the selected Sample data of group DRGs.

[0051] It can be concluded from the above that this embodiment sets the first screening condition for Screening the sample data of group DRGs can screen out more representative DRGs, which can reduce the amount of calculation while ensuring the accuracy of the calculation.

[0052] In one embodiment of the present disclosure, the dual objective function is:

[0053] in, Indicates the minimum value, represents the second CMI value, represents the second cost index, express The number of cases in the target hospital included in the sample data of the first group of DRGs in the group DRGs, Indicates The number of cases in the target hospital included in the sample data of the group DRGs, express The average cost per case of the target hospital included in the sample data of the first group of DRGs in the group DRGs, Indicates The average cost per case of the target hospitals included in the sample data of the group DRGs.

[0054] In this embodiment, for the target hospital The two main factors that affect its optimization results are medical performance Value and Cost Index , this paper seeks the larger the CMI value, the better, that is The smaller the value, the better. At the same time, public hospitals should try to achieve a break-even point, that is, The smaller the value, the better.

[0055] Then the dual objective function can be expressed as: (8) Through DRGs group From the hospital Number of cases And the average cost common Set reasonable values ​​for each variable and get a set of solutions Make and To reach the minimum, that is: (9).

[0056] It can be concluded from the above that this embodiment determines the corresponding objective function based on the different characteristics of the CMI value and the cost index, and the obtained optimization result is more in line with the actual situation of the hospital.

[0057] Please refer to Figure 3 In one embodiment of the present disclosure, the medical performance optimization management method further includes: The dual objective function is solved based on the non-dominated sorting genetic algorithm. After the initial parent population is merged with the offspring, a fast non-dominated sort is performed and the crowding degree of the individuals in each non-dominated layer is calculated. The elite individuals are selected to enter the next generation population based on the crowding degree calculation results. For the selected elite individuals, the taboo search algorithm is used to perform a local search operation again. If an operation is in a taboo state but meets the amnesty criteria, this operation can still be executed, and the equilibrium plan corresponding to the elite individuals is continuously updated.

[0058] In this embodiment, a non-dominated sorting genetic algorithm (NSGA-II) is used to solve the dual objective function. NSGA-II is a multi-objective optimization method based on a genetic algorithm. By introducing non-dominated sorting, crowding comparison, elite retention strategy and other mechanisms, it can find multiple Pareto optimal solutions in one run, so it is suitable for solving such multi-objective optimization problems as the balance between CMI value and cost index. However, when facing complex practical applications, the NSGA-II algorithm may encounter some challenges, such as the slow convergence of the algorithm to the global optimal frontier.

[0059] Based on this, this embodiment proposes an improved NSGA-II algorithm, which merges the initial parent population with the offspring, performs fast non-dominated sorting, and calculates the crowding degree of individuals in each non-dominated layer to select elite individuals to enter the next generation population. On this basis, the elite individuals are further screened and optimized. For the elite individuals that have been determined, the taboo search algorithm is selected to perform a local search operation again. The taboo search can be used to define a suitable neighborhood structure and operation, and the neighborhood solution is generated by changing the equilibrium relationship between the CMI value and the cost index. These operations are recorded in the taboo table. If an operation is in a taboo state but meets the amnesty criterion, this operation can still be executed. The equilibrium solution corresponding to the elite individual is continuously updated to optimize it, and it is put into the next generation population after it is better. This can accelerate the speed of the algorithm converging to the global optimal frontier.

[0060] In one embodiment of the present disclosure, the medical performance optimization management method further includes: Selecting a sample hospital from multiple hospitals in the target area based on the second screening condition, where the target hospital is any one of the sample hospitals; The second screening condition is: A hospital whose corresponding CMI value is less than the first set threshold and whose cost index is greater than the second set threshold, or a hospital whose corresponding CMI value is greater than the first set threshold and whose cost index is less than the third set threshold.

[0061] In this embodiment, by analyzing the data in Table 1, benchmark hospitals and sample hospitals can be selected from multiple hospitals, wherein the basis for selecting the benchmark hospital (optimization target) is that the CMI value is relatively high and the cost ratio is close to 1, such as the H12 hospital in Table 1, the CMI value is 1.1453, and the cost ratio is 1.17; the selection criteria for the sample hospital are a low CMI value but a high cost surplus (greater than the second set threshold), or a high CMI value but a serious loss (less than the third set threshold), such as the H01 hospital in Table 1, which has the largest surplus and the CMI value still has room for improvement (one is too large and the other is too small and needs to be balanced).

[0062] Taking H01 hospital as the target hospital in this embodiment, there are 14 groups of Pareto optimal solutions after optimization and solution using the method of this embodiment, see Figure 4 (The CMI value here is only calculated for 10 groups of DRGs, not the CMI value of the entire hospital). Substitute the number of cases and average cost per case corresponding to the Pareto optimal solution into the original data set (that is, the first sample data set) to obtain the overall CMI value and cost ratio of the target hospital. The best solution is shown in Table 2.

[0063]

[0064] from Figure 4 As can be seen from Table 2, the best solution is Group 3. It can be seen that after optimizing the number of cases and average cost per case of some DRGs, the overall CMI of the hospital increased from the original 0.9615 to about 1.2569, the cost ratio decreased from 1.26 to 1.07, and the total number of cases increased by about 4.44% of the original.

[0065] It can be concluded from the above that, through the scientific dual-objective optimization of this embodiment, it is proved that the dual (or multi-) objective optimization design method of the medical performance CMI value and the cost index of this embodiment is effective and feasible.

[0066] Corresponding to a medical performance optimization management method in the above embodiment, Figure 5 This is a structural block diagram of a medical performance optimization management device provided by an embodiment of the present disclosure. For ease of description, only the parts related to the embodiment of the present disclosure are shown. Figure 5 The medical performance optimization management device 20 includes: a data screening module 21, a first calculation module 22, a second calculation module 23 and a resource allocation module 24. The data screening module 21 is used to select the first sample data set from the first sample data set based on the first screening condition. Screening of sample data of DRGs The sample data of each group of DRGs constitutes the second sample data set; the sample data of each group of DRGs includes the number of cases, case costs and CMI values ​​corresponding to multiple hospitals in the target area; A first calculation module 22 is used to construct a dual objective function of the CMI value and the cost index of the target hospital based on the second sample data set; the target hospital is any hospital in the target area; The second calculation module 23 is used to solve the dual objective function to obtain multiple candidate solution combinations, each candidate solution combination includes the number of cases and the average cost per case; the cost index is used to characterize the deviation between the income cost and the expenditure cost; The resource allocation module 24 is used to update the first sample data set based on multiple candidate solution combinations to obtain multiple updated first sample data sets, calculate the first CMI value and the first cost index of the target hospital based on the multiple updated first sample data sets, determine the corresponding optimal candidate solution combination of the first CMI value and the first cost index as the target variable combination, and perform resource allocation management of the target hospital based on the target variable combination.

[0067] In one embodiment of the present disclosure, the resource allocation module 24 is specifically configured to: The weight of any group of DRGs is calculated based on the first formula, which is:

[0068] The first CMI value of the target hospital is calculated based on the second formula, which is:

[0069] in, represents the weight of any group of DRGs, Indicates the total cost of cases in multiple hospitals included in the sample data of any group of DRGs, It represents the total number of cases in multiple hospitals included in the sample data of any group of DRGs; is the number of cases in the target hospital included in the sample data of any group of DRGs; The target area per capita cost for any group of DRGs is calculated based on the third formula, which is:

[0070] The average cost per case of the target hospital included in the sample data of any group of DRGs is calculated based on the fourth formula, which is:

[0071] The first cost index of the target hospital included in the sample data of any group of DRGs is calculated based on the fifth formula. The fifth formula is:

[0072] in, is the average cost per case in the target area of ​​any group of DRGs, is the case cost of the target hospital included in the sample data of any group of DRGs, is the average cost per case of the target hospital included in the sample data of any group of DRGs.

[0073] In one embodiment of the present disclosure, the resource allocation module 24 is further configured to: Based on the first formula, we calculate The weights and weights of group DRGs; Will The weights of the group DRGs are arranged in ascending order to obtain the sequence ; Determine the value interval of the number of cases based on the sixth formula; Determine the range of average cost per case based on the seventh formula; Solve the dual objective function based on the value interval of the number of cases and the value interval of the average cost per case; The sixth formula is:

[0074] in, for The number of cases in the target hospital included in the sample data of any group of DRGs in the group DRGs, for The weight of any group of DRGs in the group DRGs, for The minimum number of cases of the target hospital included in the sample data of the first ranked DRGs in the group DRGs, for The maximum number of cases of the target hospital included in the sample data of the first ranked DRGs in the group DRGs, for The minimum number of cases of the target hospital included in the sample data of the last DRGs in the group DRGs, for The maximum number of cases of the target hospital included in the sample data of the last DRG in the group DRGs; The seventh formula is:

[0075] in, , express The average cost per case in the target area of ​​any group of DRGs, express The average cost per case of the target hospitals included in the sample data of the group DRGs.

[0076] In one embodiment of the present disclosure, the first screening condition includes: is within the set value range, and The number of cases in the target hospital included in the sample data of each group of DRGs is greater than the first threshold, and The difference between the second CMI value and the third CMI value is less than a second threshold value, and The difference between the second fee index and the third fee index is less than a third threshold; The second CMI value is based on The CMI value of the target hospital is calculated based on the sample data of the group DRGs. The third CMI value is based on The CMI value of the target hospital is calculated based on the sample data of the DRGs group; the second cost index is based on The cost index of the target hospital is calculated based on the sample data of group DRGs. The third cost index is based on The cost index of the target hospital is calculated based on the sample data of group DRGs.

[0077] In one embodiment of the present disclosure, the dual objective function is:

[0078] in, Indicates the minimum value, represents the second CMI value, represents the second cost index, express The number of cases in the target hospital included in the sample data of the first group of DRGs in the group DRGs, Indicates The number of cases in the target hospital included in the sample data of the group DRGs, express The average cost per case of the target hospital included in the sample data of the first group of DRGs in the group DRGs, Indicates The average cost per case of the target hospitals included in the sample data of the group DRGs.

[0079] In one embodiment of the present disclosure, the second calculation module 23 is specifically used to: The dual objective function is solved based on the non-dominated sorting genetic algorithm. After the initial parent population is merged with the offspring, a fast non-dominated sort is performed and the crowding degree of the individuals in each non-dominated layer is calculated. The elite individuals are selected to enter the next generation population based on the crowding degree calculation results. For the selected elite individuals, the taboo search algorithm is used to perform a local search operation again. If an operation is in a taboo state but meets the amnesty criteria, this operation can still be executed, and the equilibrium plan corresponding to the elite individuals is continuously updated.

[0080] In one embodiment of the present disclosure, the data screening module 21 is specifically used to: Selecting a sample hospital from multiple hospitals in the target area based on the second screening condition, where the target hospital is any one of the sample hospitals; The second screening condition is: Hospitals whose corresponding CMI value is less than the first set threshold and whose cost index is greater than the second set threshold, or hospitals whose corresponding CMI value is greater than the first set threshold and whose cost index is less than the third set threshold. Figure 6 , Figure 6 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 6The 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 each module / unit in the above-mentioned device embodiments, such as Figure 5 The functions of modules 21 to 24 are shown.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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 a medical performance optimization management 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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 performance optimization management method, characterized in that: include: Based on the first filtering condition, the first sample data set contains Screening of sample data of DRGs The sample data of each group of DRGs constitutes the second sample data set; the sample data of each group of DRGs includes the number of cases, case costs and CMI values ​​corresponding to multiple hospitals in the target area; A dual objective function of the CMI value and the cost index of the target hospital is constructed based on the second sample data set; the target hospital is any hospital in the target area; the cost index is used to characterize the deviation between the income cost and the expenditure cost; Solving the dual objective function to obtain multiple candidate solution combinations, each of which includes the number of cases and the average cost per case; The first sample data set is updated based on the multiple candidate solution combinations to obtain multiple updated first sample data sets, the first CMI value and the first cost index of the target hospital are calculated based on the multiple updated first sample data sets, the optimal candidate solution combination of the corresponding first CMI value and the first cost index is determined as the target variable combination, and resource allocation management of the target hospital is performed based on the target variable combination.

2. A medical performance optimization management method as claimed in claim 1, characterized in that: The calculating the first CMI value and the first cost index of the target hospital based on the multiple updated first sample data sets respectively includes: The weight of any group of DRGs is calculated based on the first formula, which is: The first CMI value of the target hospital is calculated based on the second formula, where the second formula is: in, represents the weight of any group of DRGs, Indicates the total cost of cases in multiple hospitals included in the sample data of any group of DRGs, It represents the total number of cases in multiple hospitals included in the sample data of any group of DRGs; is the number of cases in the target hospital included in the sample data of any group of DRGs; The target area average cost for any group of DRGs is calculated based on the third formula, which is: The average cost per case of the target hospital included in the sample data of any group of DRGs is calculated based on the fourth formula, and the fourth formula is: The first cost index of the target hospital included in the sample data of any group of DRGs is calculated based on the fifth formula, and the fifth formula is: in, is the average cost per case in the target area of ​​any group of DRGs, is the case cost of the target hospital included in the sample data of any group of DRGs, is the average cost per case of the target hospital included in the sample data of any group of DRGs.

3. A medical performance optimization management method as claimed in claim 2, characterized in that: Also includes: Based on the first formula, we calculate The weights and weights of group DRGs; Will The weights of the group DRGs are arranged in ascending order to obtain the sequence ; Determine the value interval of the number of cases based on the sixth formula; Determine the range of average cost per case based on the seventh formula; Solving the dual objective function based on the value interval of the number of cases and the value interval of the average cost per case; The sixth formula is: in, for The number of cases in the target hospital included in the sample data of any group of DRGs in the group DRGs, for The weight of any group of DRGs in the group DRGs, for The minimum number of cases of the target hospital included in the sample data of the first ranked DRGs in the group DRGs, for The maximum number of cases of the target hospital included in the sample data of the first ranked DRGs in the group DRGs, for The minimum number of cases of the target hospital included in the sample data of the last DRGs in the group DRGs, for The maximum number of cases of the target hospital included in the sample data of the last DRG in the group DRGs; The seventh formula is: in, , express The average cost per case in the target area of ​​any group of DRGs, express The average cost per case of the target hospitals included in the sample data of the group DRGs.

4. A medical performance optimization management method as claimed in claim 1, characterized in that: The first screening condition includes: is within the set value range, and The number of cases in the target hospital included in the sample data of each group of DRGs is greater than the first threshold, and The difference between the second CMI value and the third CMI value is less than a second threshold value, and The difference between the second fee index and the third fee index is less than a third threshold; The second CMI value is based on The CMI value of the target hospital calculated based on the sample data of the group DRGs, the third CMI value is based on The CMI value of the target hospital is calculated based on the sample data of the group DRGs; the second cost index is based on The cost index of the target hospital calculated based on the sample data of group DRGs, the third cost index is based on The cost index of the target hospital is calculated based on the sample data of group DRGs.

5. A medical performance optimization management method as claimed in claim 1, characterized in that: The dual objective function is: in, Indicates the minimum value, represents the second CMI value, represents the second cost index, express The number of cases in the target hospital included in the sample data of the first group of DRGs in the group DRGs, Indicates The number of cases in the target hospital included in the sample data of the group DRGs, express The average cost per case of the target hospital included in the sample data of the first group of DRGs in the group DRGs, Indicates The average cost per case of the target hospitals included in the sample data of the group DRGs.

6. A medical performance optimization management method as claimed in claim 1, characterized in that: Also includes: The dual objective function is solved based on a non-dominated sorting genetic algorithm. After the initial parent population is merged with the offspring, a fast non-dominated sort is performed and the crowding degree of the individuals in each non-dominated layer is calculated. Elite individuals are selected to enter the next generation population based on the crowding degree calculation results. For the selected elite individuals, a taboo search algorithm is used to perform a local search operation again. If an operation is in a taboo state but meets the amnesty criterion, this operation is still executed, and the equilibrium solution corresponding to the elite individuals is continuously updated.

7. A medical performance optimization management method as claimed in claim 1, characterized in that: Also includes: Selecting a sample hospital from multiple hospitals in the target area based on the second screening condition, wherein the target hospital is any one of the sample hospitals; The second screening condition is: A hospital whose corresponding CMI value is less than the first set threshold and whose cost index is greater than the second set threshold, or a hospital whose corresponding CMI value is greater than the first set threshold and whose cost index is less than the third set threshold.

8. A medical performance optimization management device, characterized in that: include: A data screening module is used to select the first sample data set from the first sample data set based on the first screening condition. Screening of sample data of DRGs The sample data of each group of DRGs constitutes the second sample data set; the sample data of each group of DRGs includes the number of cases, case costs and CMI values ​​corresponding to multiple hospitals in the target area; A first calculation module is used to construct a dual objective function of the CMI value and the cost index of the target hospital based on the second sample data set; The target hospital is any hospital in the target area; the cost index is used to characterize the deviation between income costs and expenditure costs; A second calculation module is used to solve the dual objective function to obtain multiple candidate solution combinations, each of which includes the number of cases and the average cost per case; A resource allocation module is used to update the first sample data set based on the multiple candidate solution combinations to obtain multiple updated first sample data sets, calculate the first CMI value and the first cost index of the target hospital based on the multiple updated first sample data sets, determine the optimal candidate solution combination of the corresponding first CMI value and the first cost index as the target variable combination, and perform resource allocation management of the target hospital based on the target variable combination.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images