Big data medical risk assessment system

Abstract

The invention relates to the technical field of medical risk insurance, and particularly discloses a big data medical risk assessment system which is provided with a data acquisition module, a value index selection module, a data analysis module, a risk assessment module and a risk early warning module. Integrated medical service information data acquisition and medical service risk data and medical service premium data screening are realized through a data acquisition module and a value index selection module; cost-effect analysis and judgment are carried out through a data analysis module in combination with the operation risk index and the economic value index, risk assessment is carried out, and low-value medical service early warning notification is carried out; inputting the historical medical service risk data and the historical medical service premium data into a preset risk assessment model for training through a risk assessment module, outputting risk assessment parameters and judging risk situation information; according to the invention, the medical service insurance demand of the patient is met through medical risk analysis, the medical economic risk is reduced, and the medical risk assessment accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical risk insurance technology, and in particular to a big data medical risk assessment system. Background Art

[0002] With the development of health and medical big data in the information age, information sharing has been achieved through the extraction of medical data and data risk analysis in the information systems of various medical insurance institutions. By utilizing various big data analysis technologies to process more and more medical data, the sensitivity of various medical service security incidents to digitized medical risks has been revealed.

[0003] In particular, some low-value medical insurance services that provide little or no health benefits to patients, and whose medical risks and input costs exceed the potential benefits, account for a large proportion of medical expenditures. There is also a lack of an accurate assessment system for the health hazards to patients and the risk of large economic investment losses caused by the use of low-value medical services, resulting in low clinical contribution values ​​of major medical service insurance systems, which affects the establishment of a high-value medical system for society as a whole. Summary of the invention

[0004] The purpose of the present invention is to provide a big data medical risk assessment system to solve the following technical problems:

[0005] How to meet patients' medical service insurance needs through medical risk analysis, reduce medical economic risks, and improve the accuracy of medical risk assessment.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] Big data medical risk assessment system, including:

[0008] A data acquisition module is used to obtain integrated medical service information data in the historical database;

[0009] A value indicator selection module is used to screen medical service risk data and medical service premium data according to the integrated medical service information data, and obtain the surgical risk index and economic value index respectively according to the value indicator selection strategy;

[0010] The medical service risk data include: preoperative accident risk parameters, intraoperative accident risk parameters, and postoperative accident risk parameters for the same type of diseases;

[0011] The medical service premium data include: pre-operative accident risk premium, intra-operative accident risk premium, and post-operative accident risk premium for the same disease;

[0012] Data analysis module, used to combine surgical risk index and economic value index to conduct cost-effectiveness analysis and determine whether it meets the requirements:

[0013] If the requirements are met, a risk assessment is conducted;

[0014] If the requirements are not met, a warning of low-value medical services will be issued;

[0015] The risk assessment module is used to input historical medical service risk data and historical medical service premium data into a preset risk assessment model for training, output risk assessment parameters and determine risk situation information;

[0016] The risk warning module is used to warn of risk situation information and issue warning signals.

[0017] Preferably, the value indicator selection strategy includes:

[0018] By calculating the medical service risk data:

[0019] By formula Calculate the surgical risk index H v ; Among them, α1, α2, α3 are all preset weight coefficients, and α1, α2, α3 are all greater than 0; f1 is a preset function; D P is the preoperative accident risk parameter, I s is the risk parameter for intraoperative accidents, R p is the risk parameter for postoperative accidents; D P0 is the standard preoperative accident risk parameter, I s0 is the standard intraoperative accident risk parameter, R p0 It is the standard postoperative accident risk parameter;

[0020] By calculating the medical service premium data:

[0021] By formula Calculate the economic value index E v ; Among them, μ1, μ2, μ3 are all preset weight coefficients, and μ1, μ2, μ3 are all greater than 0; f2 is a preset function; Cd P is the preoperative accident risk premium parameter, Ci s is the risk premium parameter for intraoperative accidents; Cr p is the postoperative accident risk premium parameter; Cd P0 is the standard preoperative accident risk premium parameter, Ci s0 is the standard intraoperative accident risk premium parameter; Cr p0 It is the standard postoperative accident risk premium parameter.

[0022] Preferably, the data analysis module:

[0023] Obtain the periodic change curve Q of the surgical risk index within consecutive surgical cycles for the same disease Hj The periodic change curve Q of the economic value index in the same continuous surgery cycle corresponding to the same disease Ej ;

[0024] Among them, the completion of preoperative, intraoperative, and postoperative treatment of the current similar disease is considered a whole surgical cycle, and j is the number of surgical cycles;

[0025] Establish the periodic change curve Q of surgical risk index in the same coordinate system Hj and the preset standard surgical risk index periodic change curve Q Hith ;

[0026] And establish the periodic change curve Q of the economic value index in the same coordinate system Ej and the preset standard economic value index cyclical change curve Q Eith ;

[0027] Determine the Q Hj and Q Hith The first area difference ΔS1;

[0028] Determine the Q Ej and Q Eith The second area difference ΔS2.

[0029] Preferably, a cost-effectiveness analysis is performed based on the first area difference ΔS1 and the second area difference ΔS2:

[0030] By formula Calculate the additional coefficient Coe in the i-th continuous operation cycle i ;

[0031] Where n is the total number of consecutive surgical cycles for the same disease, and i∈[1,n]; w1, w2 are the preset deviation coefficients; ΔS 1i is the first area difference of the i-th consecutive surgical cycle; ΔS 2i is the second area difference of the i-th consecutive surgical cycle; ΔS 1i0 ΔS is the standard value of the first area difference of the same number of consecutive surgical cycles; 2i0 is the standard value of the first area difference of the same number of consecutive surgical cycles; ρ i is the preset weight coefficient of the area difference obtained in the i-th consecutive surgical cycle.

[0032] Preferably, the additional coefficient Coe in the i-th consecutive operation cycle is i Corresponding to the preset standard threshold interval [Coe A , Coe B] for comparison:

[0033] If Coe i ∈[Coe A , Coe B ], then it is judged to be in line with the cost-effectiveness change and a risk assessment is conducted;

[0034] like If the cost-effectiveness is not met, a warning signal will be generated.

[0035] Preferably, the risk assessment model is constructed as follows:

[0036] Collect historical medical service risk data and historical medical service premium data within consecutive surgical cycles of the same disease, and select the additional coefficient Coe corresponding to the cost-effectiveness of each cycle i and the medical service risk data and medical service premium data associated with the corresponding period to generate training samples;

[0037] A model was built using a convolutional neural network, and the model was trained using training samples to obtain a risk assessment model for the cost-effectiveness analysis parameters of each cycle.

[0038] Preferably, the risk assessment module:

[0039] Obtain a risk assessment parameter set A output by the risk assessment model of the cost-effectiveness analysis parameters of each cycle;

[0040] Analyze the number x of elements in set A that fall into the standard risk assessment parameter threshold interval; compare x with the preset standard number X that falls into the standard risk assessment parameter threshold interval to determine whether x is greater than X:

[0041] If yes, the risk situation is judged to be low;

[0042] If not, the risk situation is judged to be high and a warning signal is issued.

[0043] Preferably, the risk assessment module further includes performing a sensitivity analysis on the low-cost-effectiveness analysis results:

[0044] Acquire low-cost-effective incremental cost of medical input along with the acceptable value of patient treatment cycle Ac1;

[0045] Get the historical low cost-effectiveness of the incremental cost of medical input along with the standard acceptable value Ac2 of the patient treatment cycle;

[0046] If 90%Ac2≤Ac1≤110%Ac2, it is judged that economic risk occurs and the value sensitivity is high;

[0047] If Ac2 is less than 90% of Ac1, it is judged that the economic risk is high and the value sensitivity is extremely high;

[0048] If Ac2>110%Ac2, it is judged that the economic risk is low and the value sensitivity is average.

[0049] Beneficial effects of the present invention:

[0050] (1) The present invention obtains the surgical risk index and economic value index of the medical service as the analysis of the value of the medical service, and further performs cost-effectiveness analysis by setting a data analysis module to combine the surgical risk index and the economic value index to determine whether the cost-effectiveness judgment result is reasonable. This rationality mainly involves judging whether the change state of the cost and effect of the diagnostic medical service is stable within the data range of the entire continuous surgical cycle and the selected diagnosis; if it is judged to meet the requirements, a risk assessment is performed; if it is not met, a low-value medical service warning is issued, and the data analysis module is used to ensure that the data that meets the current medical service value requirements are screened, and low-value medical services are warned and excluded in advance.

[0051] (2) The present invention sets up a risk assessment module for inputting historical medical service risk data and historical medical service premium data into a preset risk assessment model for training, outputs risk assessment parameters and determines risk situation information, and uses a risk warning module to ensure that risk situation information is warned and a warning signal is issued; through medical risk supervision, the patient's medical service insurance needs are met and the probability of medical economic risk accidents is reduced.

[0052] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0054] Figure 1 This is a schematic diagram of a big data medical risk assessment system module of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] The existing low-value medical insurance services provide little or no health benefits to patients, and the medical risks and input costs exceed the potential benefits. They account for a large proportion of medical expenditures. There is also a lack of an accurate assessment system for the health hazards of low-value medical services to patients and the risk of large economic investment losses. This has led to low clinical contribution values ​​of major medical service insurance systems, affecting the establishment of a high-value medical system for society as a whole.

[0057] To solve the above technical problems, please refer to Figure 1 As shown, the present invention is a big data medical risk assessment system, comprising:

[0058] A data acquisition module is used to obtain integrated medical service information data in the historical database;

[0059] A value indicator selection module is used to screen medical service risk data and medical service premium data according to the integrated medical service information data, and obtain the surgical risk index and economic value index respectively according to the value indicator selection strategy;

[0060] Medical service risk data include: preoperative accident risk parameters, intraoperative accident risk parameters, and postoperative accident risk parameters for the same disease;

[0061] Medical service premium data include: pre-operative accident risk premium, intra-operative accident risk premium, and post-operative accident risk premium for the same disease;

[0062] Data analysis module, used to combine surgical risk index and economic value index to conduct cost-effectiveness analysis and determine whether it meets the requirements:

[0063] If the requirements are met, a risk assessment is conducted;

[0064] If the requirements are not met, a warning of low-value medical services will be issued;

[0065] The risk assessment module is used to input historical medical service risk data and historical medical service premium data into a preset risk assessment model for training, output risk assessment parameters and determine risk situation information;

[0066] The risk warning module is used to warn of risk situation information and issue warning signals.

[0067] Through the above technical scheme, the data medical risk assessment system designed in this embodiment specifically realizes meeting the patient's medical service insurance needs through medical risk supervision and reducing the probability of medical economic risk accidents by setting up four modules: data acquisition module, data analysis module, risk assessment module and risk warning module; specifically, by setting up the data acquisition module, it is ensured that the integrated medical service information data is acquired by providing a large database, and the integrated medical service information data is further pre-processed to complete the unified and standardized data acquisition; by setting up the value indicator selection module, it is ensured that the medical service risk data and medical service premium data in the integrated medical service information data are screened, and the surgical risk index and economic value index of the medical service are respectively obtained according to the value indicator selection strategy; the medical data risk is evaluated by obtaining the surgical risk index and the economic value index.

[0068] Since there are many factors affecting the degree of risk, but most of them do not consider the relative relationship between the treatment effect and economic cost of patients brought by medical treatment under mature technology, this design obtains the surgical risk index and economic value index of medical services as a specific manifestation of the value of medical services for further analysis; the coverage of medical service risk data includes: preoperative accident risk parameters, intraoperative accident risk parameters, and postoperative accident risk parameters of similar diseases, and the basic data of preoperative accident risk parameters, intraoperative accident risk parameters, and postoperative accident risk parameters can all be obtained through big data system training, and the corresponding risk data of the medical system can be easily calculated through big data analysis software; the coverage of medical service premium data includes: preoperative accident risk premium, intraoperative accident risk premium, and postoperative accident risk premium of similar diseases, and the preoperative accident risk premium, intraoperative accident risk premium, and postoperative accident risk premium can all be obtained through the relevant expense financial statements and statistical tables of the disease treatment insurance policy recorded by the medical big data system, and can be obtained by classification through big data statistical calculations.

[0069] This embodiment also provides a data analysis module, which combines the surgical risk index and the economic value index to conduct further cost-effectiveness analysis, and judges whether the cost-effectiveness evaluation result is reasonable. This reasonable content mainly involves the data range of the entire continuous surgical cycle and the selected diagnosis to judge whether the change state of the cost and effect of the diagnostic medical service is within a stable range; if it is further judged that it meets the requirements, a risk assessment is carried out; if it does not meet the requirements, a low-value medical service warning is issued.

[0070] A risk assessment module is set up to input historical medical service risk data and historical medical service premium data into a preset risk assessment model for training, output risk assessment parameters and judge risk situation information; this risk assessment is the result of an overall judgment based on the changes in big data, and analyzes and predicts the rationality trend of this result. Furthermore, a risk warning module is also set up to ensure that it is used to warn of risk situation information and issue warning signals. This embodiment sets up a data analysis module to ensure the screening of data that meets the current medical service value requirements, and to warn and exclude low-value medical services in advance.

[0071] As an implementation mode of the present invention, the value indicator selection strategy includes:

[0072] This embodiment calculates the medical service risk data:

[0073] By formula Calculate the surgical risk index H for obtaining medical services v ; Among them, α1, α2, α3 are all preset weight coefficients, and α1, α2, α3 are all greater than 0; f1 is a preset function; D P is the preoperative accident risk parameter, I s is the risk parameter for intraoperative accidents, R p is the risk parameter for postoperative accidents; D P0 is the standard preoperative accident risk parameter, I s0 is the standard intraoperative accident risk parameter, R p0 It is the standard postoperative accident risk parameter;

[0074] This embodiment also calculates the medical service premium data:

[0075] By formula Calculate the economic value index E v ; Among them, μ1, μ2, μ3 are all preset weight coefficients, and μ1, μ2, μ3 are all greater than 0; f2 is a preset function; Cd P is the preoperative accident risk premium parameter, Ci s is the risk premium parameter for intraoperative accidents; Cr p is the postoperative accident risk premium parameter; Cd P0 is the standard preoperative accident risk premium parameter, Ci s0 is the standard intraoperative accident risk premium parameter; Cr p0 It is the standard postoperative accident risk premium parameter.

[0076] In the above technical solution, in this embodiment, the corresponding surgical risk index H is obtained by calculating the medical service risk data and the medical service premium data respectively. v and economic value index E v; and set the corresponding parameters according to the size of the corresponding index and its influencing factors. Specifically, the preoperative accident risk parameter D P , Intraoperative Accident Risk Parameter I s and postoperative accident risk parameter R p The proportion of each data in the health value of medical services is used to calculate the surgical risk index for obtaining medical services; the preoperative accident risk premium parameter Cd P 、Intraoperative accident risk premium parameter Ci s and postoperative accident risk premium parameter Cr p The economic value index E is calculated by calculating the proportion of each in the economic value of medical services. v ; Then ensure the surgical risk index H v and economic value index E v The results are more accurate.

[0077] It should be noted that the preset weight coefficient α1 refers to the weight set for the impact of the preoperative accident risk parameter on the success of the patient's operation in the entire treatment process; the preset weight coefficient α2 refers to the weight set for the intraoperative accident risk parameter on the success of the patient's operation in the entire treatment process; the preset weight coefficient α3 refers to the weight set for the impact of the postoperative accident risk parameter on the success of the patient's operation in the entire treatment process; and the preset weight coefficient μ1 refers to the weight set for the impact of the preoperative accident risk premium parameter on the economic cost of treatment in the entire treatment process; the preset weight coefficient μ2 refers to the weight set for the impact of the intraoperative accident risk premium parameter on the economic cost of treatment in the entire treatment process; the preset weight coefficient μ3 refers to the weight set for the impact of the postoperative accident risk premium parameter on the economic cost of treatment in the entire treatment process.

[0078] The above preset weight coefficients are obtained by calculating the weight ratio based on historical experience data and are pre-set; P0 ,I s0 , R p0 and Cd P0 、Ci s0 Cr p0 Both are standard data values ​​obtained based on historical experience; the preset functions f1 and f2 are control functions set according to historical data conditions, which are used to ensure that the index results obtained by the corresponding preset functions are within a specific reasonable range.

[0079] As an implementation mode of the present invention, the data analysis module:

[0080] Obtain the periodic change curve Q of the surgical risk index within consecutive surgical cycles for the same disease HjThe periodic change curve Q of the economic value index in the same continuous surgery cycle corresponding to the same disease Ej ;

[0081] Among them, the completion of preoperative, intraoperative, and postoperative treatment of the current similar disease is considered a whole surgical cycle, and j is the number of surgical cycles;

[0082] Establish the periodic change curve Q of surgical risk index in the same coordinate system Hj and the preset standard surgical risk index periodic change curve Q Hith ;

[0083] And establish the periodic change curve Q of the economic value index in the same coordinate system Ej and the preset standard economic value index cyclical change curve Q Eith ;

[0084] Determine the Q Hj and Q Hith The first area difference ΔS1;

[0085] Determine the Q Ej and Q Eith The second area difference ΔS2.

[0086] In the above technical solution, the data analysis module in this embodiment performs processing in the following manner:

[0087] First, obtain the periodic change curve Q of the surgical risk index in the continuous surgical cycle of the same disease Hj The periodic change curve Q of the economic value index in the same continuous surgery cycle corresponding to the same disease Ej ; Then, establish the surgical risk index periodic change curve Q in the same coordinate system Hj and the preset standard surgical risk index periodic change curve Q Hith ; and establish the periodic change curve Q of the economic value index in the same coordinate system Ej and the preset standard economic value index cyclical change curve Q Eith ; Finally, by comparing: determine the Q Hj and Q Hith The first area difference ΔS1; Determine the Q Ej and Q Eith The second area difference ΔS2.

[0088] Since the changes in the curve are relatively dynamic, the index sizes corresponding to different cycles are different. By comparing the changes in the surgical risk index and the economic value index in consecutive cycles and comparing whether the changes are reasonable, we can judge whether the current disease medical service cost-effectiveness is reasonable, and realize intelligent risk assessment from the two aspects of surgical accident risks and premiums to reduce the probability of low-value medical services.

[0089] It should be noted that the completion of preoperative, intraoperative and postoperative treatments for the current similar diseases is regarded as a whole surgical cycle, and j is the number of surgical cycles. The number of surgical cycles for different diseases varies with the prevalence and expansion of the disease, and needs to be determined and set according to the specific situation.

[0090] As an implementation of the present invention, a cost-effectiveness analysis is performed based on the first area difference ΔS1 and the second area difference ΔS2:

[0091] By formula Calculate the additional coefficient Coe in the i-th continuous operation cycle i ;

[0092] Where n is the total number of consecutive surgical cycles for the same disease, and i∈[1,n]; w1, w2 are the preset deviation coefficients; ΔS 1i is the first area difference of the i-th consecutive surgical cycle; ΔS 2i is the second area difference of the i-th consecutive surgical cycle; ΔS 1i0 ΔS is the standard value of the first area difference of the same number of consecutive surgical cycles; 2i0 is the standard value of the first area difference of the same number of consecutive surgical cycles; ρ i is the preset weight coefficient of the area difference obtained in the i-th consecutive surgical cycle.

[0093] In the above technical solution, this embodiment sets an additional coefficient Coe in the continuous operation cycle i The dynamic changes of cost-effectiveness are measured, and the additional coefficient Coe i The larger the range of variation, the less "stable" the cost-effectiveness variation is. Of course, this "stability" is based on the ideal state of treatment cost investment and treatment effectiveness. Change analysis is carried out through the construction of big data analysis models.

[0094] As an embodiment of the present invention, the additional coefficient Coe in the i-th continuous operation cycle is i Corresponding to the preset standard threshold interval [Coe A , Coe B To compare:

[0095] If Coe i∈[Coe A , Coe B ], then it is judged to be in line with the cost-effectiveness change and a risk assessment is conducted;

[0096] like If the cost-effectiveness is not met, a warning signal will be generated.

[0097] In the above technical solution, in order to reflect whether the range of cost-effectiveness change is reasonable, a preset standard threshold interval [Coe A , Coe B ], and this threshold interval is obtained by machine fitting based on the relevant data of the corresponding cases in the historical database; compare the area difference between the curve of the periodic change of the economic value index in the detection and analysis period and the periodic change curve of the preset standard economic value index; by judging whether the area difference is within the preset standard area difference threshold interval, specifically by calculating the additional coefficient Coe in the i-th continuous surgery cycle i Corresponding to the preset standard threshold interval [Coe A , Coe B ] to compare: If Coe i ∈[Coe A , Coe B ], it is judged to be in line with the cost-effectiveness change and a risk assessment is conducted; if If the cost-effectiveness is not met, a warning signal will be generated.

[0098] As an implementation mode of the present invention, the process of constructing the risk assessment model is as follows:

[0099] Collect historical medical service risk data and historical medical service premium data within consecutive surgical cycles of the same disease, and select the additional coefficient Coe corresponding to the cost-effectiveness of each cycle i and the medical service risk data and medical service premium data associated with the corresponding period to generate training samples;

[0100] A model was built using a convolutional neural network, and the model was trained using training samples to obtain a risk assessment model for the cost-effectiveness analysis parameters of each cycle.

[0101] In the above technical solution, the specific construction of the risk assessment model in this embodiment relies on the existing big data processing model for calculation. First, the historical medical service risk data and historical medical service premium data within the continuous operation cycle of the same disease are collected, and then the additional coefficient Coe corresponding to the cost-effectiveness of each cycle is selected. iAnd the medical service risk data and medical service premium data associated with the corresponding period are used to generate training samples; finally, a model is built with a convolutional neural network, and the model is trained with the training samples to obtain a risk assessment model for the cost-effectiveness analysis parameters of each period.

[0102] As an embodiment of the present invention, the risk assessment module:

[0103] Obtain a risk assessment parameter set A output by a risk assessment model of cost-effectiveness analysis parameters for each period;

[0104] Analyze the number x of elements in set A that fall into the standard risk assessment parameter threshold interval; compare x with the preset standard number X that falls into the standard risk assessment parameter threshold interval to determine whether x is greater than X:

[0105] If yes, the risk situation is judged to be low;

[0106] If not, the risk situation is judged to be high and a warning signal is issued.

[0107] In the above technical scheme, the risk assessment module in this embodiment performs further analysis through the output parameters of the risk assessment model; first, obtain the risk assessment parameter set A output by the risk assessment model of the cost-effectiveness analysis parameters of each period; then, analyze the number x of elements in the set A that fall into the standard risk assessment standard parameter threshold interval; determine whether x is greater than X: if so, the risk situation is judged to be low; if not, the risk situation is judged to be high and a warning signal is issued.

[0108] As an embodiment of the present invention, the risk assessment module further includes performing sensitivity analysis on the low cost-effectiveness analysis result:

[0109] Acquire low-cost-effective incremental cost of medical input along with the acceptable value of patient treatment cycle Ac1;

[0110] Get the historical low cost-effectiveness of the incremental cost of medical input along with the standard acceptable value Ac2 of the patient treatment cycle;

[0111] If 90%Ac2≤Ac1≤110%Ac2, it is judged that economic risk occurs and the value sensitivity is high;

[0112] If Ac1 < 90% Ac2, it is judged that the economic risk is high and the value sensitivity is extremely high;

[0113] If Ac1>110%Ac2, it is judged that the economic risk is low and the value sensitivity is average.

[0114] In the above technical scheme, the risk assessment module in this embodiment is also configured to perform a sensitivity analysis on the results of the low-cost-effect analysis. Due to the different changes in cost-effect, corresponding high-cost, high-effect and low-cost, low-effect services will be generated according to the changes. The sensitivity of cost and effect is judged and reflected through economic risk and value sensitivity.

[0115] Specifically, by obtaining the acceptable value Ac1 of the incremental cost of low-cost and effective medical investment along the patient treatment cycle; and obtaining the standard acceptable value Ac2 of the historical incremental cost of low-cost and effective medical investment along the patient treatment cycle; if it is judged that 90%Ac2≤Ac1≤110%Ac2; then it is judged that there is an economic risk and the value sensitivity is high; if it is judged that Ac1<90%Ac2, then it is judged that the economic risk is high and the value sensitivity is extremely high; if it is judged that Ac1>110%Ac2, then it is judged that the economic risk is low and the value sensitivity is average.

[0116] It should be noted that the comparison value in this embodiment is obtained by adjusting the probability analysis method in the sensitivity data analysis; it also needs to be adjusted according to the influencing factors of the sensitivity data. If uncertain factors arise, multiple simulations are performed through the Monte Carlo model to obtain simulation results that obey the normal distribution.

[0117] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the defined scope, they should all fall within the protection scope of the present invention.

Claims

1. Big data medical risk assessment system, characterized by: include: A data acquisition module is used to obtain integrated medical service information data in the historical database; A value indicator selection module is used to screen medical service risk data and medical service premium data according to the integrated medical service information data, and obtain the surgical risk index and economic value index respectively according to the value indicator selection strategy; The medical service risk data include: preoperative accident risk parameters, intraoperative accident risk parameters, and postoperative accident risk parameters for the same type of diseases; The medical service premium data include: pre-operative accident risk premium, intra-operative accident risk premium, and post-operative accident risk premium for the same disease; Data analysis module, used to combine surgical risk index and economic value index to conduct cost-effectiveness analysis and determine whether it meets the requirements: If the requirements are met, a risk assessment is conducted; If the requirements are not met, a warning of low-value medical services will be issued; The risk assessment module is used to input historical medical service risk data and historical medical service premium data into a preset risk assessment model for training, output risk assessment parameters and determine risk situation information; The risk warning module is used to warn of risk situation information and issue warning signals.

2. The big data medical risk assessment system according to claim 1, characterized in that: The value indicator selection strategy includes: By calculating the medical service risk data: By formula Calculate the surgical risk index H v ; Among them, α1, α2, α3 are all preset weight coefficients, and α1, α2, α3 are all greater than 0; f1 is a preset function; D P is the preoperative accident risk parameter, I s is the risk parameter for intraoperative accidents, R p is the risk parameter for postoperative accidents; D P0 is the standard preoperative accident risk parameter, I s0 is the standard intraoperative accident risk parameter, R p0 It is the standard postoperative accident risk parameter; By calculating the medical service premium data: By formula Calculate the economic value index E v ; Among them, μ1, μ2, μ3 are all preset weight coefficients, and μ1, μ2, μ3 are all greater than 0; f2 is a preset function; Cd P is the preoperative accident risk premium parameter, Ci s is the risk premium parameter for intraoperative accidents; Cr p is the postoperative accident risk premium parameter; Cd P0 is the standard preoperative accident risk premium parameter, Ci s0 is the standard intraoperative accident risk premium parameter; Cr p0 It is the standard postoperative accident risk premium parameter.

3. The big data medical risk assessment system according to claim 1, characterized in that: The data analysis module: Obtain the surgical risk index H within consecutive surgical cycles for the same disease v Size periodic change curve Q Hj The economic value index E of the same continuous surgery cycle corresponding to the same disease v Size periodic change curve Q Ej ; Among them, the completion of preoperative, intraoperative, and postoperative treatment of the current similar disease is considered a whole surgical cycle, and j is the number of surgical cycles; Establish the periodic change curve Q of surgical risk index in the same coordinate system Hj and the preset standard surgical risk index periodic change curve Q Hith ; And establish the periodic change curve Q of the economic value index in the same coordinate system Ej and the preset standard economic value index cyclical change curve Q Eith ; Determine the Q Hj and Q Hith The first area difference ΔS1; Determine the Q Ej and Q Eith The second area difference ΔS2.

4. The big data medical risk assessment system according to claim 3, characterized in that: Cost-effectiveness analysis is performed based on the first area difference ΔS1 and the second area difference ΔS2: By formula Calculate the additional coefficient Coe in the i-th continuous operation cycle i ; Where n is the total number of consecutive surgical cycles for the same disease, and i∈[1,n]; w1, w2 are the preset deviation coefficients; ΔS 1i is the first area difference of the i-th consecutive surgical cycle; ΔS 2i is the second area difference of the i-th consecutive surgical cycle; ΔS 1i0 ΔS is the standard value of the first area difference of the same number of consecutive surgical cycles; 2i0 is the standard value of the first area difference of the same number of consecutive surgical cycles; p i is the preset weight coefficient of the area difference obtained in the i-th consecutive surgical cycle.

5. The big data medical risk assessment system according to claim 4, characterized in that: The additional coefficient Coe in the i-th consecutive operation cycle i Corresponding to the preset standard threshold interval [Coe A , Coe B ] for comparison: If Coe i ∈[Coe A , Coe B ], it is judged to be consistent with the cost-effectiveness change and a risk assessment is conducted; like If the cost-effectiveness is not met, a warning signal is generated.

6. The big data medical risk assessment system according to claim 1, characterized in that: The construction process of the risk assessment model is as follows: Collect historical medical service risk data and historical medical service premium data within consecutive surgical cycles for the same disease, and select the additional coefficient Coe corresponding to the cost-effectiveness of each cycle i and the medical service risk data and medical service premium data associated with the corresponding period to generate training samples; A convolutional neural network model was built and trained with training samples to obtain a risk assessment model for cost-effectiveness analysis parameters in each cycle.

7. The big data medical risk assessment system according to claim 6, characterized in that: The risk assessment module: Obtaining a risk assessment parameter set A output by a risk assessment model of the cost-effectiveness analysis parameters of each cycle; Analyze the number x of elements in set A that fall into the standard risk assessment parameter threshold interval; compare x with the preset standard number X that falls into the standard risk assessment parameter threshold interval to determine whether x is greater than X: If yes, the risk situation is judged to be low; If not, the risk situation is judged to be high and a warning signal is issued.

8. The big data medical risk assessment system according to claim 1, characterized in that: The risk assessment module also includes a sensitivity analysis of the low-cost-effectiveness analysis results: Acquire the acceptable value Ac1 of the incremental cost of low-cost and effective medical investment along with the patient's treatment cycle; Get the historical low-cost-effectiveness medical input incremental cost along with the standard acceptable value Ac2 of the patient treatment cycle; If 90%Ac2≤Ac1≤110%Ac2, it is judged that economic risk occurs and the value sensitivity is high; If Ac1 < 90% Ac2, it is judged that the economic risk is high and the value sensitivity is extremely high; If Ac1>110%Ac2, it is judged that the economic risk is low and the value sensitivity is average.

Images