CN113643140B - Method, apparatus, device and medium for determining medical insurance expenditure influencing factors - Google Patents
Method, apparatus, device and medium for determining medical insurance expenditure influencing factors Download PDFInfo
- Publication number
- CN113643140B CN113643140B CN202110995997.9A CN202110995997A CN113643140B CN 113643140 B CN113643140 B CN 113643140B CN 202110995997 A CN202110995997 A CN 202110995997A CN 113643140 B CN113643140 B CN 113643140B
- Authority
- CN
- China
- Prior art keywords
- group
- medical insurance
- expenditure
- analyzed
- influence factors
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a method, a device, equipment and a computer readable medium for determining medical insurance expenditure influencing factors, and relates to the technical field of computers. One embodiment of the method comprises the following steps: dividing a consumption group into a plurality of groups according to medical insurance expenditure expense, and obtaining a group to be analyzed according to the expenditure change rate of the groups; extracting hospital characteristic information of the group to be analyzed and expenditure characteristic information of the group to be analyzed, and combining to generate characteristic data to be analyzed; inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result; and calculating to obtain the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity. According to the embodiment, the influence factors of the expenditure of the medical insurance fund can be positioned, so that the reasons of the expenditure of the medical insurance fund and the main risks of illegal behaviors are obtained.
Description
Technical Field
The present invention relates to the field of computer technology, and in particular, to a method, apparatus, device, and computer readable medium for determining medical insurance expenditure influencing factors.
Background
In the process of controlling the cost of medical insurance, the expenditure of the medical insurance fund is counted, and the main direction of the expenditure of the medical insurance fund is determined, usually by medical projects, medical types, hospital classifications and the like.
In addition, in the aspects of illegal violation and abuse of the hit medical insurance foundation, the generated medical expense is manually checked and marked or screened and marked through SQL through medical insurance violation, violation and medical waste principles.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art: because it is difficult to macroscopically and quantitatively locate what factors in a region affect the expense of the foundation of medical insurance, the reasons for affecting the expense of the foundation of medical insurance in that region cannot be effectively known, and the major risks describing the illegal behaviors in that region cannot be quantitatively described.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, apparatus, device, and computer readable medium for determining a medical insurance expenditure influencing factor, which can locate the influencing factor of medical insurance fund expenditure, and further learn the cause of the medical insurance fund expenditure and the main risk of illegal behaviors.
To achieve the above object, according to one aspect of the embodiments of the present invention, there is provided a method of determining a medical insurance expenditure influencing factor, including:
Dividing a consumption group into a plurality of groups according to medical insurance expenditure expense, and obtaining a group to be analyzed according to the expenditure change rate of the groups, wherein the group to be analyzed comprises an actual high consumption group;
extracting hospital characteristic information of the group to be analyzed and expenditure characteristic information of the group to be analyzed, and combining to generate characteristic data to be analyzed;
inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors;
and calculating to obtain the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity.
Dividing the consumer group into a plurality of groups according to medical insurance expenditure expense, and obtaining a group to be analyzed according to the expenditure change rate of the groups, wherein the group to be analyzed comprises an actual high consumer group and an actual common consumer group and comprises the following steps:
dividing a consumer group into a plurality of groups according to the order of medical insurance expenditure expense from more to less, wherein each group comprises the same number of people;
Calculating a rate of change of expenditure of the group based on the accumulated healthcare expenditure costs of the group;
and taking the segmentation point corresponding to the minimum expenditure change rate as a basis for dividing the actual high-consumption group from the actual common consumption group to obtain the group to be analyzed.
The hospital characteristic information of the group to be analyzed comprises: one or more of hospital identification, hospital grade, economic type, specialty type, and affiliated area;
the expense characteristic information of the group to be analyzed comprises: the drug duty cycle, the examination rate duty cycle, and the surgical rate duty cycle.
The method further comprises the steps of:
constructing and training a distributed model according to the analysis feature training data;
and after the trained distributed model is adjusted by adopting a preset parameter adjustment mode, determining the distributed medical insurance model by combining model evaluation indexes.
Before the distributed model is constructed and trained according to the analysis characteristic training data, the method further comprises the following steps:
and removing data with high correlation in the original analysis feature training data to obtain the analysis feature training data.
The combined model evaluation index determines the distributed medical insurance model, including:
combining model evaluation indexes, if the construction of the distributed medical insurance model fails, adjusting parameters of the distributed model to determine the distributed medical insurance model,
The adjustment parameters include one or more of adjusting a rate of change of expenditure of the analytical feature training data, increasing features of the analytical feature training data, discretizing the analytical feature training data, and replacing a distributed model.
The information quantity of the influence factors is obtained by calculation according to the model sharing degree of the influence factors and the data dividing points of the influence factors and the actual high-consumption group, and the information quantity comprises the following steps:
obtaining a predicted consumption group from the group to be analyzed according to the data dividing points of the influencing factors;
based on the number of the actual high-consumption groups in the predicted high-consumption groups and the number of the predicted high-consumption groups, obtaining high-consumption group accuracy;
and calculating the information quantity of the influence factors according to the high consumption group accuracy.
According to a second aspect of an embodiment of the present invention, there is provided an apparatus for determining a medical insurance expenditure influencing factor, including:
the expense module is used for dividing the consumption group into a plurality of groups according to the expense of medical insurance, and obtaining a group to be analyzed according to the expense change rate of the groups, wherein the group to be analyzed comprises an actual high consumption group;
The feature module is used for extracting hospital feature information of the group to be analyzed and expenditure feature information of the group to be analyzed, and combining the hospital feature information and the expenditure feature information of the group to be analyzed to generate feature data to be analyzed;
the analysis module is used for inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors;
and the output module is used for calculating the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity.
According to a third aspect of embodiments of the present invention, there is provided an electronic device for determining a medical insurance expenditure influencing factor, comprising:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the methods as described above.
According to a fourth aspect of embodiments of the present invention, there is provided a computer readable medium having stored thereon a computer program which when executed by a processor implements a method as described above.
One embodiment of the above invention has the following advantages or benefits: dividing a consumption group into a plurality of groups according to medical insurance expenditure expense, and obtaining a group to be analyzed according to the expenditure change rate of the groups, wherein the group to be analyzed comprises an actual high consumption group and an actual common consumption group; extracting hospital characteristic information of the group to be analyzed and expenditure characteristic information of the group to be analyzed, and combining to generate characteristic data to be analyzed; inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors; and calculating to obtain the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity. And obtaining an analysis result through the distributed medical insurance model, and then determining the importance of the influence factors according to the information quantity of the influence factors. Therefore, the influence factors of the expenditure of the medical insurance fund can be positioned, and the reasons of the expenditure of the medical insurance fund and the main risks of illegal behaviors are further known.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main flow of a method of determining medical insurance expenditure influencing factors in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of obtaining a population to be analyzed according to a rate of change of expenditure of a group according to an embodiment of the present invention;
FIG. 3 is a flow diagram of determining a distributed medical insurance model according to an embodiment of the present invention;
FIG. 4 is a flow chart of calculating the information amount of the influencing factors according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of the main structure of an apparatus for determining medical insurance expenditure influencing factors according to an embodiment of the present invention;
FIG. 6 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
fig. 7 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Currently in the field of medical insurance cost control, positioning expense influence factors comprise the following two schemes:
first, medical insurance professionals are familiar with the regional medical environment, medical insurance context, and medical insurance payment scheme. Corresponding policies are formulated according to the existing experience, and the flow direction of medical insurance expenditure is observed through the policy implementation effect, so that expenditure influencing factors are obtained. The scheme has the defects that the property of the affiliated land is strong, the medical environment of each area is different, and the influence factors are large in difference; in addition, the observation period is long, the timeliness is poor, only the influencing factors can be positioned qualitatively, and the quantitative result can not be obtained.
Second, medical insurance fund expenditure data is analyzed from multiple dimensions by classifying medical subjects such as hospitals, doctors and caregivers, and counting indexes such as hospital reimbursement costs, clinic reimbursement costs, and the like. The method needs to screen and split each dimension, has large workload and cannot comprehensively consider each factor. Such as: the medical expense of a certain area is high, and the medical expense is probably caused by a plurality of factors such as local geographic environment, hospital distribution, area subject industry, patient age and the like, and the statistical conclusion is often different from expert opinion, so that the accuracy and the interpretability are poor.
In the process of controlling the medical insurance expense, which factors of a region can influence the medical insurance fund expenditure cannot be macroscopically and quantitatively positioned, the influencing factors are reasonably screened and ordered, the reasons for influencing the medical insurance fund expenditure of the region can be effectively observed, and finally, the expenditure of the medical insurance fund can be more effectively reduced by preferentially controlling some high influencing factors.
In addition, due to the lack of quantitative traceability summary of medical violations and waste facts, main risk factors describing regional violations cannot be quantified, so that several factors are monitored and controlled in a focused manner, and complex medical insurance violations can be found more easily.
In order to solve the problem that the factors which are difficult to locate in a region affect the expenditure of the medical insurance fund, the following technical scheme in the embodiment of the invention can be adopted.
Referring to fig. 1, fig. 1 is a schematic diagram of a main flow of a method for determining a medical insurance expenditure influencing factor according to an embodiment of the present invention, and an analysis result is obtained through a distributed medical insurance model, so as to output the influencing factor according to information. As shown in fig. 1, the method specifically comprises the following steps:
s101, dividing a consumer group into a plurality of groups according to medical insurance expenditure expense, and obtaining a group to be analyzed according to the expenditure change rate of the groups, wherein the group to be analyzed comprises an actual high-consumption group.
In an embodiment of the present invention, to determine the influencing factors of the medical insurance expenditure, rules need to be mined in the medical insurance expenditure costs of a large number of patients. First, the actual high-consumption group is located. Second, it is sought what factors lead to a virtually high consumer population. Finally, the influencing factors of medical insurance expenditure are quantified. And providing the direction of the adjustment of the follow-up medical insurance policy of the region according to the value corresponding to the influence factor.
In embodiments of the present invention, the community involved in the expense of medical insurance is referred to as the consumer community. Then, analyzing in the consumer group to obtain an actual high consumer group and an actual ordinary consumer group. The actual high consumer group pays more for medical insurance than the actual ordinary consumer group.
Referring to fig. 2, fig. 2 is a schematic flow chart of obtaining a population to be analyzed according to a group payout change rate according to an embodiment of the present invention, and specifically includes the following steps:
s201, dividing the consumer group into a plurality of groups according to the order of more medical insurance expenditure, wherein the number of people in each group is the same.
In the embodiment of the invention, the consumer groups are required to be divided into a plurality of groups according to the order of more medical insurance expenditure. Specifically, the consumer group includes the following features: the total expense of medical insurance, the cost proportion in the medical insurance scope and the hospitalization duration. The total expense cost of medical insurance, the cost proportion in the medical insurance range and the hospitalization duration are collectively called zhuyuan_data_feature.
Wherein, the total expense of medical insurance = overall payment expense + the large expense of medical insurance;
in-doctor-insurance-scope fee ratio = in-doctor-insurance-scope fee/total cost;
duration of hospitalization = time of discharge-time of admission.
As one example, parameters such as hospitalization information ID, hospital ID, time of admission, time of discharge, overall payment, large expense of medical insurance, in-scope of medical insurance, total expense, medical behavior, and category of participation in the hospitalization transaction data master table zhuyuan_data in the Hadoop Distributed File System (HDFS) are extracted using a computing engine spark. And calculating the total expense of medical insurance, the expense ratio in the medical insurance range and the hospitalization duration according to the extracted parameters.
Secondly, aiming at the data of the consumer groups, the data are ordered according to the order of more medical insurance expenditure. As one example, an index id is set for each data, with the range of index i being (1, data_num), according to the total medical insurance expenditure total_pay field, sort from large to small sort (asc=false). The maximum value of data_num is the data amount of the consumer group.
The ordered consumer group is then divided into a plurality of groupings, each of the same number of people included in the grouping. As one example, the total expense for medical insurance is evenly grouped by zhuyuan_data_feature data amount data_num. Such as: the number of packets is set to 100 groups, and the data amount n= (data_num)/100 of the i-th group, the bin_num of the i-th group i The range is as follows:
(i-1)*n+1≤bin_num i ≤i*n
intermediate number bin_num_value of i-th group i The calculation method comprises the following steps:
s202, calculating the expenditure change rate of the grouping based on the accumulated medical insurance expenditure expense of the grouping.
For each group, the rate of change of the payout may be calculated based on the accumulated expense of medical insurance. I.e., the change in the expense of medical insurance in each group.
Specifically, the total medical insurance expenditure total_pay_bin in each group and the accumulated medical insurance expenditure total_pay_bin_cut of the group are calculated i The calculation formula is as follows:
total_pay_bin_cum i ＝total_pay_bin 0 +…+total_pay_bin i
the cumulative healthcare expenditure of the packet accounts for the total_path_bin_cum_rate i The method comprises the following steps:
the total_path_bin_sum is the total medical insurance expense in zhuyuan_data_feature.
Calculating the expense change rate point_slope_growth_rate of the group according to the accumulated medical insurance expense ratio of the group i ：
S203, taking the segmentation point corresponding to the minimum expenditure change rate as a basis for dividing the actual high-consumption group and the actual common consumption group to obtain a group to be analyzed.
For each group, calculating the payout change rate of the group, and determining the minimum payout change rate from the payout change rates. The minimum rate of change of expenditure characterizes the increase in accumulated medical insurance expenditure costs that has tended to cease. Therefore, the segmentation point corresponding to the minimum expenditure change rate is used as the basis for dividing the actual high-consumption group and the actual common consumption group, and the group to be analyzed is obtained.
Specifically, the point_num of the cut point is calculated as follows:
in equation 3, 0.1 is a preset parameter. Extracting data smaller than or equal to the point_num as data of an actual high-consumption group by taking the point_num as a segmentation point; randomly extracting the data of the point_num from the data of the data_num-point_num, wherein the data of the point_num is taken as the data of an actual common consumer group.
As one example, the data of the actual high consumer group and the data of the actual ordinary consumer group are combined into data, and a column of targets is added. The data corresponding target field value of the actual high consumption group is set to be 1, and the data corresponding target field value of the common consumption group is set to be 0.
In the embodiment of fig. 3, actual high-consumption groups are screened from the consumer groups according to medical insurance expense. And further taking the actual high-consumption group as an analysis object to determine medical insurance expenditure influencing factors.
S102, extracting hospital characteristic information of the group to be analyzed and expenditure characteristic information of the group to be analyzed, and combining to generate characteristic data to be analyzed.
In order to improve the accuracy of determining medical insurance expenditure influencing factors, feature information of a group to be analyzed needs to be extracted. It should be noted that, since the group to be analyzed includes not only the actual high-consumption group but also the actual ordinary-consumption group, the above-mentioned feature information includes not only the feature information of the actual high-consumption group but also the feature information of the actual ordinary-consumption group. The purpose of this is to: and determining medical insurance expenditure influencing factors by comparing the characteristic information of the actual high-consumption group with the characteristic information of the actual common consumption group.
From multiple dimensional analyses in the historical data, fields are extracted that may impact medical insurance costs. Specifically, the characteristic information of the group to be analyzed can be classified into hospital characteristic information of the group to be analyzed and expense characteristic information of the group to be analyzed according to both hospital and expense aspects.
In one embodiment of the invention, the hospital characteristic information of the population to be analyzed includes: one or more of hospital identification, hospital grade, economic type, specialty type, and affiliated area;
the expense characteristic information of the group to be analyzed comprises: the drug duty cycle, the examination rate duty cycle, and the surgical rate duty cycle.
In a specific implementation process, the characteristics of the extracted population to be analyzed are determined as follows:
patient: gender, age, medical behavior, and category of participants;
and (3) hospitals: hospital grade, economy type, specialty type, area of ownership;
disease: disease coding (ICD), treatment outcome, department;
cost is: the hospitalization duration, the cost ratio in the medical insurance range, the medicine ratio, the examination cost ratio and the operation cost ratio.
As an example, spark extracts data such as a hospital ID, a hospital level, an economic type, a specialty type, a region of the hospital information main table hos_info in the HDFS library, and uses a hospital ID field for data in S201 to perform lateral merging to obtain data2.
The spark extracts hospitalization information ID, gender, age, treatment result, disease code ICD10, western medicine fee, chinese medicine preparation fee, pathological diagnosis fee, laboratory diagnosis fee, imaging diagnosis fee, clinical diagnosis project fee, other diagnosis fee, operation fee and total fee in Main table main_INC_DOC of the medical records in the HDFS library. Wherein the above fields are combined into the following three new features:
medicine ratio= (western medicine fee + Chinese medicine preparation fee)/total cost;
examination fee ratio= (pathological diagnosis fee + laboratory diagnosis fee + imaging diagnosis fee + clinical diagnosis item fee + other diagnosis fee)/total fee;
surgical fee duty ratio = surgical fee/total fee;
and after the characteristics are processed, the data3 is obtained by transverse combination with the data2 by using the hospitalization information ID field.
From two aspects of hospital characteristics and expenditure characteristics, characteristic data to be analyzed are generated, and accurate analysis of medical insurance expenditure influencing factors is facilitated.
S103, inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors.
In the embodiment of the invention, the analysis of the characteristic data is realized by using a distributed medical insurance model. Wherein the distributed medical insurance model is a model which is obtained by training on the basis of a distributed system. As one example, the distributed medical insurance model employs one of the following: distributed decision trees, distributed random forests, distributed xgboost, and distributed lightGBM.
Referring to fig. 3, fig. 3 is a schematic flow chart of determining a distributed medical insurance model according to an embodiment of the present invention, specifically including the following steps:
s301, constructing and training a distributed model according to the analysis feature training data.
In the embodiment of the invention, the distributed model is obtained based on the training of the analysis characteristic training data. Analytical feature training data is data used to train a distributed model. Wherein the analysis feature training data includes hospital feature training data and expense feature training data.
In one embodiment of the invention, in order to improve the accuracy of the model, the data with high correlation can be removed first to obtain the analysis feature training data. And then, constructing and training a distributed model according to the analysis characteristic training data. And removing the data with high correlation in the original analysis characteristic training data to obtain the analysis characteristic training data.
Illustratively, correlation matrix detection is adopted for original analysis feature training data, the original analysis feature training data with correlation higher than 90% is deleted, feature independence is guaranteed, and then the analysis feature training data is remained.
Furthermore, for class-independent features, such as: sex, medical behavior, hospital grade, region to which the hospital belongs, hospital economic type, hospital specialty type, ICD, treatment result, hospitalization department, etc., one-hot independent encoding is adopted, and word embedding is performed on the disease type.
Word embedding is a generic term for a model that vectorizes words, the core idea being to map each word to a dense vector on a low dimensional space. Diseases as high-dimensional words can be mapped to them in a low-dimensional manner.
And constructing and training a distributed model by adopting frames such as spark or mmspark and the like according to the analysis characteristic training data. The distributed model adopts one of the following: distributed decision trees, distributed random forests, distributed xgboost, and distributed lightGBM.
S302, after the trained distributed model is adjusted by adopting a preset parameter adjusting mode, the distributed medical insurance model is determined by combining model evaluation indexes.
According to the analysis characteristic training data, a trained distributed model is obtained, and the trained distributed model can be adjusted in a preset parameter adjusting mode. As one example, the preset parameter tuning modes include one or more of the following: grid search tuning, random search tuning, and bayesian tuning.
After the trained distributed model is adjusted, model evaluation indexes are combined to determine the distributed medical insurance model. As one example, the model evaluation index includes one or more of an area enclosed with the coordinate Axis (AUC), accuracy, recall, and F1score under the ROC curve.
As an example, where the model evaluation index includes an AUC, if the AUC value is less than 0.9, it is indicated that the construction of the distributed medical insurance model fails, and the trained distributed model is adjusted. In the case of AUC values greater than 0.9, then this indicates that the distributed medical insurance model was constructed successfully.
In one embodiment of the invention, the success of constructing the distributed medical insurance model can be ensured by adjusting parameters when the construction of the distributed medical insurance model fails. Wherein the adjustment parameters include one or more of: and adjusting the expenditure change rate of the analysis feature training data, increasing the features of the analysis feature training data, discretizing the analysis feature training data and replacing the distributed model.
I.e., combining model evaluation indexes, if the construction of the distributed medical insurance model fails, adjusting parameters of the distributed medical insurance model to determine the distributed medical insurance model,
adjusting parameters includes one or more of adjusting a rate of change of expenditure of the analytical feature training data, adding features of the analytical feature training data, discretizing the analytical feature training data, and replacing the distributed model.
In one embodiment of the invention, the distributed model uses a distributed random forest, and the AUC can reach 0.97.
In the embodiment of fig. 3, after the distributed model is constructed, the distributed medical insurance model is determined in a preset parameter adjustment manner and model evaluation indexes.
After the distributed medical insurance model is determined, the characteristic data to be analyzed is input into the distributed medical insurance model, and an analysis result is obtained, wherein the analysis result comprises influence factors, model contribution degree feature_importance of the influence factors and data dividing points of the influence factors. The data segmentation points of the influence factors are segmentation points with the largest statistics times of the influence factors in the distributed medical insurance model.
In embodiments of the present invention, the medical insurance expense influencing factors may include a plurality in particular. As one example, 10 influencing factors are determined from a distributed medical insurance model. The influencing factors may be screened based on their model contribution.
Specifically, the influence factors are determined based on the distributed medical insurance model, and then the influence factors are ranked in order of more to less model contribution of the influence factors. And sequentially accumulating the model contribution degrees of the influence factors, and taking the influence factors related to the accumulated result as the screened influence factors when the accumulated result is larger than a preset accumulated contribution threshold.
And after sorting according to feature_importance, calculating the factor accumulation contribution degree. After sorting, the cumulative contribution of the ith factor is as follows:
feature_importance_cum i
＝feature_importance 0 +…+feature_importance i
Equation 4
As one example, the preset cumulative contribution threshold is 0.95, i.e., feature_import_com i And if the number is more than or equal to 0.95, the first i influence factors are the screened influence factors.
S104, calculating to obtain the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity.
After the model contribution degree of the influence factors and the data dividing points of the influence factors are known, in order to quantitatively process the influence factors so as to determine the influence of the influence factors on medical insurance expenditure, the information quantity of the influence factors is calculated according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups.
Referring to fig. 4, fig. 4 is a schematic flow chart of calculating the information amount of the influence factor according to the embodiment of the present invention, specifically including the following steps:
s401, obtaining a predicted high-consumption group in the group to be analyzed according to the data dividing points of the influence factors.
For the influencing factors, the group to be analyzed can be divided into two parts according to the data dividing points of the influencing factors, namely a predicted high-consumption group and a predicted common consumption group. Of course, for different influencing factors, the predicted high-consumption group and the predicted common consumption group obtained by segmentation may be different due to different data segmentation points.
S402, obtaining the accuracy of the high consumption group based on the number of the actual high consumption groups in the predicted high consumption groups and the number of the predicted high consumption groups.
Having determined the actual high consumer groups from the rate of change of the spending in S101, the actual high consumer groups among the high consumer groups can be known. Further, high consumer group accuracy is known based on predicting the number of actual high consumer groups in the consumer groups and predicting the number of high consumer groups. That is, the ratio of the number of actual high consumer groups in the predicted high consumer groups to the number of predicted high consumer groups is equal to the high consumer group accuracy.
As an example, the ith influencing factor factors i For example, the model contribution degree is factor_value i The data dividing point is the factors_split_poiht i 。
Using factors split point i Dividing the data set data into two parts predicts a consumer group part pred pos i And predicting a common consumer group part_pred_neg i Then use the factors i The obtained high consumer group accuracy is:
wherein, part_pred_pos_target1-num i Is part_pred_pos i Data size of 1 in target field, part_pred_pos_num i Is part_pred_pos i Is a total data amount in (a).
S403, calculating the information quantity of the influence factors according to the high consumption group accuracy.
The information quantity refers to a measure of how much information is, and in the embodiment of the invention, the importance of the influencing factors is measured by the information quantity. Specifically, the information quantity of the influencing factors can be calculated according to the high accuracy of the consumer groups.
Illustratively, the influencing factors are available according to information amount calculation formulas i Information quantity factors_info_content for dividing high consumption crowd i The following are provided:
where point_num is the actual high consumer group number obtained in S101.
factors_info_content i The information amount of the influence factor is obtained by calculating factor_info_content for each influence factor.
After the information quantity of each influence factor is calculated, the influence factors can be output according to the order of the information quantity from large to small. Obviously, the influence of the first output influence factors on the medical insurance expenditure is larger; the influence factor of the back output has less influence on the medical insurance expenditure.
In the embodiment of fig. 4, the influence factors are quantified according to the model sharing degree of the influence factors and the data segmentation points of the influence factors, so as to lay a foundation for determining the influence of the influence factors.
In the technical scheme provided by the embodiment of the invention, the consumption group is divided into a plurality of groups according to the medical insurance expenditure expense, and the expenditure change rate of the groups is used for obtaining the group to be analyzed, wherein the group to be analyzed comprises an actual high consumption group; extracting hospital characteristic information of the group to be analyzed and expenditure characteristic information of the group to be analyzed, and combining to generate characteristic data to be analyzed; inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors; and calculating to obtain the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity. And obtaining an analysis result through the distributed medical insurance model, and then determining the importance of the influence factors according to the information quantity of the influence factors. Therefore, the influence factors of the expenditure of the medical insurance fund can be positioned, and the reasons of the expenditure of the medical insurance fund and the main risks of illegal behaviors are further known.
Compared with the prior art, the technical scheme of the embodiment of the invention solves the defects that the technical scheme based on the experience scheme of the medical insurance industry has strong attribution and poor timeliness and cannot quantitatively obtain influencing factors. The problems of large workload, low accuracy and poor interpretability of each medical insurance detail index are solved based on the complex screening of the medical insurance expense statistical scheme.
Referring to fig. 5, fig. 5 is a schematic diagram illustrating a main structure of an apparatus for determining a medical insurance expense influence factor according to an embodiment of the present invention, where the apparatus for determining a medical insurance expense influence factor may implement a method for determining a medical insurance expense influence factor, and as shown in fig. 5, the apparatus for determining a medical insurance expense influence factor specifically includes:
the expense module 501 is used for dividing the consumption group into a plurality of groups according to the expense of medical insurance, and obtaining a group to be analyzed according to the expense change rate of the groups, wherein the group to be analyzed comprises an actual high consumption group;
the feature module 502 is configured to extract hospital feature information of the group to be analyzed and expense feature information of the group to be analyzed, and combine the hospital feature information and the expense feature information to generate feature data to be analyzed;
the analysis module 503 is configured to input the feature data to be analyzed into a distributed medical insurance model, and obtain an analysis result, where the analysis result includes an influence factor, a model contribution degree of the influence factor, and a data dividing point of the influence factor;
And the output module 504 is configured to calculate an information amount of the influencing factor according to the model contribution degree of the influencing factor, the data dividing point of the influencing factor, and the actual high-consumption group, and output the influencing factor according to the information amount.
In one embodiment of the present invention, the expense module 501 is specifically configured to divide the consumer group into a plurality of groups according to the order of more expense of medical insurance, where each group includes the same number of people;
calculating a rate of change of expenditure of the group based on the accumulated healthcare expenditure costs of the group;
and taking the segmentation point corresponding to the minimum expenditure change rate as a basis for dividing the actual high-consumption group from the actual common consumption group to obtain the group to be analyzed.
In one embodiment of the invention, the hospital characteristic information of the population to be analyzed comprises: one or more of hospital identification, hospital grade, economic type, specialty type, and affiliated area;
the expense characteristic information of the group to be analyzed comprises: the drug duty cycle, the examination rate duty cycle, and the surgical rate duty cycle.
In one embodiment of the present invention, the analysis module 503 is further configured to construct and train a distributed model according to the analysis feature training data;
And after the trained distributed model is adjusted by adopting a preset parameter adjustment mode, determining the distributed medical insurance model by combining model evaluation indexes.
In one embodiment of the present invention, the analysis module 503 is further configured to reject data with high correlation in the original analysis feature training data, so as to obtain the analysis feature training data.
In one embodiment of the present invention, the analysis module 503 is specifically configured to combine the model evaluation index, and if the construction of the distributed medical insurance model fails, adjust parameters of the distributed model to determine the distributed medical insurance model,
the adjustment parameters include one or more of adjusting a rate of change of expenditure of the analytical feature training data, increasing features of the analytical feature training data, discretizing the analytical feature training data, and replacing a distributed model.
In one embodiment of the present invention, the output module 504 is specifically configured to obtain a predicted consumer group from the group to be analyzed according to the data dividing point of the influencing factor;
based on the number of the actual high-consumption groups in the predicted high-consumption groups and the number of the predicted high-consumption groups, obtaining high-consumption group accuracy;
And calculating the information quantity of the influence factors according to the high consumption group accuracy.
FIG. 6 illustrates an exemplary system architecture 600 of a method of determining a medical insurance expense impact factor or an apparatus of determining a medical insurance expense impact factor to which embodiments of the present invention may be applied.
As shown in fig. 6, the system architecture 600 may include terminal devices 601, 602, 603, a network 604, and a server 605. The network 604 is used as a medium to provide communication links between the terminal devices 601, 602, 603 and the server 605. The network 604 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 605 via the network 604 using the terminal devices 601, 602, 603 to receive or send messages, etc. Various communication client applications such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only) may be installed on the terminal devices 601, 602, 603.
The terminal devices 601, 602, 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 605 may be a server providing various services, such as a background management server (by way of example only) providing support for shopping-type websites browsed by users using terminal devices 601, 602, 603. The background management server may analyze and process the received data such as the product information query request, and feedback the processing result (e.g., the target push information, the product information—only an example) to the terminal device.
It should be noted that, the method for determining the medical insurance expense influence factor provided by the embodiment of the present invention is generally executed by the server 605, and accordingly, the device for determining the medical insurance expense influence factor is generally disposed in the server 605.
It should be understood that the number of terminal devices, networks and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 7, there is illustrated a schematic diagram of a computer system 700 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 7 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, ROM 702, and RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output portion 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 701.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes a payout module, a feature module, an analysis module, and an output module. The names of these modules do not constitute a limitation on the module itself in some cases, and for example, the expense module may also be described as "for dividing the consumption group into a plurality of groups according to the medical insurance expense, and deriving the population to be analyzed, including the actual high consumption group, from the expense change rate of the groups".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include:
dividing a consumption group into a plurality of groups according to medical insurance expenditure expense, and obtaining a group to be analyzed according to the expenditure change rate of the groups, wherein the group to be analyzed comprises an actual high consumption group;
extracting hospital characteristic information of the group to be analyzed and expenditure characteristic information of the group to be analyzed, and combining to generate characteristic data to be analyzed;
inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors;
and calculating to obtain the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity.
According to the technical scheme of the embodiment of the invention, the consumption group is divided into a plurality of groups according to the medical insurance expenditure expense, and the expenditure change rate of the groups is used for obtaining a group to be analyzed, wherein the group to be analyzed comprises an actual high consumption group and an actual common consumption group; extracting hospital characteristic information of the group to be analyzed and expenditure characteristic information of the group to be analyzed, and combining to generate characteristic data to be analyzed; inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors; and calculating to obtain the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity. And obtaining an analysis result through the distributed medical insurance model, and then determining the importance of the influence factors according to the information quantity of the influence factors. Therefore, the influence factors of the expenditure of the medical insurance fund can be positioned, and the reasons of the expenditure of the medical insurance fund and the main risks of illegal behaviors are further known.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (7)
1. A method of determining a medical insurance expenditure influencing factor, comprising:
dividing a consumption group into a plurality of groups according to medical insurance expenditure expense, and obtaining a group to be analyzed according to the expenditure change rate of the groups, wherein the group to be analyzed comprises an actual high consumption group and an actual common consumption group and comprises the following steps: dividing a consumer group into a plurality of groups according to the order of medical insurance expenditure expense from more to less, wherein each group comprises the same number of people; calculating a rate of change of expenditure of the group based on the accumulated healthcare expenditure costs of the group; the segmentation point corresponding to the minimum expenditure change rate is used as a basis for dividing the actual high-consumption group from the actual common consumption group, and the group to be analyzed is obtained;
extracting hospital characteristic information of the group to be analyzed and expenditure characteristic information of the group to be analyzed, and combining to generate characteristic data to be analyzed;
Inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors; wherein, according to analyzing the characteristic training data, build and train the distributed model; after the trained distributed model is adjusted by adopting a preset parameter adjustment mode, the distributed medical insurance model is determined by combining model evaluation indexes, and the analysis characteristic training data comprise hospital characteristic training data and expenditure characteristic training data; the data dividing points of the influence factors are dividing points with the largest statistics times of the influence factors in the distributed medical insurance model;
calculating to obtain the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high consumption group, and outputting the influence factors according to the information quantity, wherein the high consumption group is obtained in the group to be analyzed according to the data dividing points of the influence factors; based on the number of the actual high-consumption groups in the predicted high-consumption groups and the number of the predicted high-consumption groups, obtaining high-consumption group accuracy; and calculating the information quantity of the influence factors according to the high consumer group accuracy, wherein the information quantity is used for measuring the importance of the influence factors.
2. The method of determining medical insurance expenditure influencing factors according to claim 1, wherein the hospital characteristic information of the population to be analyzed comprises: one or more of hospital identification, hospital grade, economic type, specialty type, and affiliated area;
the expense characteristic information of the group to be analyzed comprises: the drug duty cycle, the examination rate duty cycle, and the surgical rate duty cycle.
3. The method of determining medical insurance expenditure influencing factors according to claim 1, wherein prior to constructing and training the distributed model based on the analytical signature training data, further comprising:
and eliminating data with high correlation in the original analysis feature training data to obtain the analysis feature training data.
4. The method of determining medical insurance expenditure influencing factors according to claim 1, wherein said determining said distributed medical insurance model in combination with model evaluation metrics comprises:
if the construction of the distributed medical insurance model fails by combining with model evaluation indexes, parameters are adjusted to the distributed model to determine the distributed medical insurance model,
the adjustment parameters include one or more of adjusting a rate of change of expenditure of the analytical feature training data, increasing features of the analytical feature training data, discretizing the analytical feature training data, and replacing a distributed model.
5. An apparatus for determining a medical warranty impact factor for implementing the method for determining a medical warranty impact factor of claim 1, comprising:
the expense module is used for dividing the consumption group into a plurality of groups according to the expense of medical insurance, and obtaining a group to be analyzed according to the expense change rate of the groups, wherein the group to be analyzed comprises an actual high consumption group and an actual common consumption group;
the feature module is used for extracting hospital feature information of the group to be analyzed and expenditure feature information of the group to be analyzed, and combining the hospital feature information and the expenditure feature information of the group to be analyzed to generate feature data to be analyzed;
the analysis module is used for inputting the characteristic data to be analyzed into a distributed medical insurance model to obtain an analysis result, wherein the analysis result comprises influence factors, model contribution degrees of the influence factors and data dividing points of the influence factors;
and the output module is used for calculating the information quantity of the influence factors according to the model contribution degree of the influence factors, the data dividing points of the influence factors and the actual high-consumption groups, and outputting the influence factors according to the information quantity.
6. An electronic device for determining a medical insurance expenditure influencing factor, comprising:
One or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-4.
7. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110995997.9A CN113643140B (en) | 2021-08-27 | 2021-08-27 | Method, apparatus, device and medium for determining medical insurance expenditure influencing factors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110995997.9A CN113643140B (en) | 2021-08-27 | 2021-08-27 | Method, apparatus, device and medium for determining medical insurance expenditure influencing factors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113643140A CN113643140A (en) | 2021-11-12 |
| CN113643140B true CN113643140B (en) | 2023-05-30 |
Family
ID=78424272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110995997.9A Active CN113643140B (en) | 2021-08-27 | 2021-08-27 | Method, apparatus, device and medium for determining medical insurance expenditure influencing factors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113643140B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492885A (en) * | 2018-10-25 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance risk project analysis method device, terminal and readable medium |
| CN109785155A (en) * | 2018-12-13 | 2019-05-21 | 平安医疗健康管理股份有限公司 | Method and Related product based on medical insurance reimbursement model adjustment medical insurance strategy |
| CN109949167A (en) * | 2019-02-20 | 2019-06-28 | 太平洋医疗健康管理有限公司 | Medical insurance dynamic financing method and system based on big data modeling analysis |
| CN111383123A (en) * | 2018-12-29 | 2020-07-07 | 天津幸福生命科技有限公司 | Clinical medical expense statistical method and device, storage medium and electronic equipment |
| CN112926879A (en) * | 2021-03-26 | 2021-06-08 | 平安科技（深圳）有限公司 | Payment scheme decision method, device and equipment for disease diagnosis related grouping |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160371453A1 (en) * | 2015-06-19 | 2016-12-22 | Healthgrades Operating Company, Inc. | Analytical data processing for consumer health scores |
| US20200219610A1 (en) * | 2017-07-05 | 2020-07-09 | Koninklijke Philips N.V. | System and method for providing prediction models for predicting a health determinant category contribution in savings generated by a clinical program |
-
2021
- 2021-08-27 CN CN202110995997.9A patent/CN113643140B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492885A (en) * | 2018-10-25 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance risk project analysis method device, terminal and readable medium |
| CN109785155A (en) * | 2018-12-13 | 2019-05-21 | 平安医疗健康管理股份有限公司 | Method and Related product based on medical insurance reimbursement model adjustment medical insurance strategy |
| CN111383123A (en) * | 2018-12-29 | 2020-07-07 | 天津幸福生命科技有限公司 | Clinical medical expense statistical method and device, storage medium and electronic equipment |
| CN109949167A (en) * | 2019-02-20 | 2019-06-28 | 太平洋医疗健康管理有限公司 | Medical insurance dynamic financing method and system based on big data modeling analysis |
| CN112926879A (en) * | 2021-03-26 | 2021-06-08 | 平安科技（深圳）有限公司 | Payment scheme decision method, device and equipment for disease diagnosis related grouping |
Non-Patent Citations (4)
| Title |
|---|
| 中国农村居民医疗消费支出不平等及其演变;赵广川 等;《统计研究》;第32卷(第10期);全文 * |
| 医疗保险对农民工消费支出的影响研究;陈虹 等;《经济研究参考》(第19期);全文 * |
| 城市医院医疗费用上涨影响因素结构方程模型分析;陈子敏 等;《河南职工医学院学报》(第02期);全文 * |
| 大数据背景下职工医保基金费用控制研究;黄欣晨 等;《智能计算机与应用》;第10卷(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113643140A (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9785792B2 (en) | Systems and methods for processing requests for genetic data based on client permission data | |
| KR102119790B1 (en) | Clinical outcome tracking and analysis | |
| WO2021174944A1 (en) | Message push method based on target activity, and related device | |
| Wakefield et al. | A Bayesian model for cluster detection | |
| Lanzarone et al. | A patient stochastic model to support human resource planning in home care | |
| US20120271612A1 (en) | Predictive modeling | |
| US9646135B2 (en) | Clinical outcome tracking and analysis | |
| EP4027348A2 (en) | Affinity prediction method and apparatus, method and apparatus for training affinity prediction model, device and medium | |
| CN109634941A (en) | Medical data processing method, device, electronic equipment and storage medium | |
| CN113254542A (en) | Data visualization processing method and device and electronic equipment | |
| Alibrahim et al. | An agent-based simulation model of patient choice of health care providers in accountable care organizations | |
| Mac McCullough et al. | Local public health department adoption and use of electronic health records | |
| CN109543117A (en) | Service push method and terminal device based on intelligent recommendation | |
| CN107291835B (en) | Search term recommendation method and device | |
| US11842810B1 (en) | Real-time feedback systems for tracking behavior change | |
| CN113628751A (en) | Gastric cancer prognosis prediction method and device and electronic equipment | |
| CN113643140B (en) | Method, apparatus, device and medium for determining medical insurance expenditure influencing factors | |
| US20230088044A1 (en) | End-to-end prospecting platform utilizing natural language processing to reverse engineer client lists | |
| CN113706223B (en) | Data processing method and device | |
| CN115620886A (en) | Data auditing method and device | |
| CN116504401A (en) | Intelligent physical examination project recommendation method and device | |
| CN112488857B (en) | Event identification method, device, electronic equipment and storage medium | |
| EP3493082A1 (en) | A method of exploring databases of time-stamped data in order to discover dependencies between the data and predict future trends | |
| CN115391666A (en) | Hospital online recommendation method and device, computer equipment and storage medium | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |