Medical data processing method and device, processing equipment and storage medium

Abstract

The application provides a medical data processing method and device, processing equipment and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: obtaining medical data of a target user, wherein the medical data of the target user comprises data of a plurality of first-level indexes, and the data of each first-level index comprises data of a plurality of second-level indexes; determining a score of the first-level index according to the data of the plurality of second-level indexes in the data of the first-level index and a previously obtained association relationship between the second-level indexes in the first-level index; and obtaining a medical credit score of the target user according to the scores of the plurality of first-level indexes. Based on the association relationship and the score of the first-level index determined according to the data of the plurality of second-level indexes in the data of the first-level index, the score of the first-level index obtained is more accurate, and then the medical credit score of the target user is determined, so that the accuracy and reliability of the medical credit score of the target user can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a medical data processing method, apparatus, processing equipment, and storage medium. Background Technology

[0002] Credit-based healthcare plays a crucial role in improving the modernization of healthcare management, optimizing resource allocation, innovating service models, and enhancing the efficiency of medical services. Patients' credit records and integrity are paramount; therefore, the collection, application, and evaluation of credit information are critical.

[0003] In related technologies, a pre-set medical credit assessment model is used to accumulate the scores corresponding to various indicators of the patient to obtain the patient's medical credit score.

[0004] However, in related technologies, directly accumulating the scores corresponding to various indicators of patients can easily lead to problems with the accuracy and reliability of the obtained medical credit scores. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of the prior art by providing a medical data processing method, apparatus, processing equipment, and storage medium, so as to solve the problem that directly accumulating the scores corresponding to various indicators of patients in related technologies can easily lead to low accuracy and reliability of the obtained medical credit scores.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows:

[0007] In a first aspect, embodiments of the present invention provide a medical data processing method, comprising:

[0008] Acquire the medical data of the target user, wherein the medical data of the target user includes: data of multiple first-level indicators, and each first-level indicator includes data of multiple second-level indicators;

[0009] The score of the first-level indicator is determined based on the data of multiple second-level indicators in the data of the first-level indicator and the pre-obtained correlation between the second-level indicators in the first-level indicator.

[0010] The target user's medical credit score is obtained based on the scores of multiple first-level indicators.

[0011] Optionally, determining the score of the first-level indicator based on the data of the multiple second-level indicators in the data of the first-level indicator and the pre-acquired correlation between the second-level indicators in the first-level indicator includes:

[0012] The scores of the first-level indicators are determined based on the data of the multiple second-level indicators, the correlation relationships, and the order relationships among the first-level indicators; wherein, the order relationship is the order relationship between the first second-level indicator in the first-level indicators and the last second-level indicator in the adjacent first-level indicators, and the correlation relationship includes the order relationship among the second-level indicators in the first-level indicators.

[0013] Optionally, determining the score of the first-level indicator based on the data of the multiple second-level indicators in the data of the first-level indicator, the correlation relationship, and the order relationship among the first-level indicators includes:

[0014] The proportion of the second-level indicators in the first-level indicators is determined based on the proportion of the first-level indicators and the number of second-level indicator data in the first-level indicator data.

[0015] The score of the first-level indicator is determined based on the data of the multiple second-level indicators, the correlation, the order relationship between the first-level indicators, and the proportion of the second-level indicators.

[0016] Optionally, obtaining the target user's medical credit score based on the scores of multiple first-level indicators includes:

[0017] The target user's medical credit score is obtained by weighted summation of the weights and scores of multiple first-level indicators.

[0018] Optionally, before obtaining the medical credit score of the target user by weighted summation based on the weights and scores of multiple first-level indicators, the method further includes:

[0019] The contribution rate of multiple first-level indicators is determined based on their scores.

[0020] Based on the contribution rate of multiple first-level indicators, the multiple first-level indicators are ranked to determine their weights.

[0021] Optionally, determining the contribution rate of multiple first-level indicators based on their scores includes:

[0022] Based on the scores of multiple first-level indicators, calculate the feature values ​​of multiple first-level indicators;

[0023] The contribution rate of multiple first-level indicators is determined based on the feature values ​​of multiple first-level indicators.

[0024] Optionally, the method further includes:

[0025] The participation balance of the target user is determined based on the number of non-zero secondary indicators in the target user's medical data and the preset benchmark number of secondary indicators.

[0026] Optionally, the method further includes:

[0027] Based on the historical medical credit score curves of the target user at multiple historical time points, a fitted curve for the target user is obtained.

[0028] Based on the fitted curve, the future medical credit score of the target user at a future time point is determined.

[0029] Secondly, embodiments of the present invention also provide a medical data processing device, comprising:

[0030] The first acquisition module is used to acquire the medical data of the target user, wherein the medical data of the target user includes: data of multiple first-level indicators, and each first-level indicator includes data of multiple second-level indicators;

[0031] The determining module is used to determine the score of the first-level indicator based on the data of the multiple second-level indicators in the data of the first-level indicator and the pre-acquired correlation between the second-level indicators in the first-level indicator.

[0032] The second acquisition module is used to obtain the medical credit score of the target user based on the scores of multiple first-level indicators.

[0033] Optionally, the determining module is further configured to determine the score of the first-level indicator based on the data of the plurality of second-level indicators, the correlation relationship, and the order relationship among the first-level indicators; wherein, the order relationship is the order relationship between the first second-level indicator in the first-level indicators and the last second-level indicator in the adjacent first-level indicators; the correlation relationship includes: the order relationship among the second-level indicators in the first-level indicators.

[0034] Optionally, the determining module is further configured to determine the proportion of the second-level indicators in the first-level indicators based on the proportion of the first-level indicators and the number of second-level indicator data in the first-level indicator data; and to determine the score of the first-level indicators based on the data of the multiple second-level indicators, the correlation relationship, the order relationship between the first-level indicators, and the proportion of the second-level indicators.

[0035] Optionally, the second acquisition module is further configured to perform a weighted summation based on the weights of multiple first-level indicators and the scores of multiple first-level indicators to obtain the medical credit score of the target user.

[0036] Optionally, the device further includes:

[0037] The first determining module is used to determine the contribution rate of multiple first-level indicators based on their scores; and to sort the multiple first-level indicators based on their contribution rates to determine their weights.

[0038] Optionally, the first determining module is used to calculate the feature values ​​of the multiple first-level indicators based on the scores of the multiple first-level indicators; and to determine the contribution rate of the multiple first-level indicators based on the feature values ​​of the multiple first-level indicators.

[0039] Optionally, the device further includes:

[0040] The second determining module is used to determine the participation balance of the target user based on the number of non-zero second-level indicators in the target user's medical data and the preset number of second-level indicator benchmarks.

[0041] Optionally, the device further includes:

[0042] The third acquisition module is used to fit the historical medical credit score curves of the target user at multiple historical time points to obtain the fitted curve of the target user.

[0043] The third determining module is used to determine the future medical credit score of the target user at a future time point based on the fitted curve.

[0044] Thirdly, embodiments of the present invention also provide a processing device, including: a memory and a processor, wherein the memory stores a computer program executable by the processor, and the processor executes the computer program to implement the medical data processing method described in any of the first aspects above.

[0045] Fourthly, embodiments of the present invention also provide a storage medium storing a computer program, wherein when the computer program is read and executed, it implements the medical data processing method described in any of the first aspects above.

[0046] The beneficial effects of this invention are as follows: This invention provides a medical data processing method, comprising: acquiring medical data of a target user, the target user's medical data including: data of multiple first-level indicators, each first-level indicator including data of multiple second-level indicators; determining the score of a first-level indicator based on the data of multiple second-level indicators in the first-level indicator data and the pre-acquired correlation between the second-level indicators in the first-level indicator data; and obtaining the target user's medical credit score based on the scores of the multiple first-level indicators. By using the correlation between the second-level indicators in the first-level indicator data and the scores of the first-level indicators determined from the data of multiple second-level indicators in the first-level indicator data, the acquired scores of the first-level indicators are more accurate. Therefore, by determining the target user's medical credit score based on the medical credit scores of multiple target users, the accuracy and reliability of the target user's medical credit score can be improved. Attached Figure Description

[0047] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating a medical data processing method provided in an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of a first-level indicator and a second-level indicator provided for an embodiment of the present invention;

[0050] Figure 3 A flowchart illustrating a medical data processing method provided in an embodiment of the present invention;

[0051] Figure 4 A flowchart illustrating a medical data processing method provided in an embodiment of the present invention;

[0052] Figure 5 A flowchart illustrating a medical data processing method provided in an embodiment of the present invention;

[0053] Figure 6 A flowchart illustrating a medical data processing method provided in an embodiment of the present invention;

[0054] Figure 7 A flowchart illustrating a historical medical credit score curve at multiple historical time points, provided as an embodiment of the present invention;

[0055] Figure 8This is a rating diagram of target user a provided in an embodiment of the present invention;

[0056] Figure 9 A rating diagram of target user b provided in an embodiment of the present invention;

[0057] Figure 10 This is a rating diagram of target user c provided in an embodiment of the present invention;

[0058] Figure 11 This is a schematic diagram of the structure of a medical data processing device provided in an embodiment of the present invention;

[0059] Figure 12 This is a schematic diagram of a processing device provided in an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0061] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0062] In the description of this application, it should be noted that if the terms "upper", "lower", etc. appear to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship that the product of this application is usually placed in, it is only for the convenience of describing this application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0063] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Additionally, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0064] It should be noted that, where there is no conflict, the features in the embodiments of this application can be combined with each other.

[0065] This application provides a medical data processing method, the execution subject of which can be a processing device, which can be a terminal or a server. When the processing device is a terminal, the terminal can be any of the following devices: desktop computer, laptop computer, tablet computer, smartphone, etc.

[0066] Optionally, the processing device can communicate with platforms such as the national health information platform, medical security system, and elderly care service platform, and can collect data from various platforms to establish a regional personal medical credit information data center.

[0067] The following explanation uses the processing device as the execution subject to illustrate the medical data processing method provided in the embodiments of this application.

[0068] Figure 1 This is a flowchart illustrating a medical data processing method provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the method may include:

[0069] S101. Obtain the target user's medical data.

[0070] The target user's medical data includes data from multiple primary indicators, and each primary indicator includes data from multiple secondary indicators.

[0071] In some implementations, the processing device can obtain the target user's original medical data from multiple platforms such as the National Health Information Platform, the Medical Security System, and the Elderly Care Service Platform, based on multiple preset data collection standard tables, and then use a preset medical credit scoring table to score the original medical data to obtain the target user's medical data.

[0072] Optionally, multiple preset data collection standard tables may include dimensions such as: personal basic data, medical insurance data, medical behavior data, and public welfare behavior data.

[0073] It should be noted that the processing device can extract relevant feature indicators based on the personal medical credit data collection content in advance and generate a preset medical credit score table.

[0074] S102. Based on the data of multiple second-level indicators in the data of the first-level indicators, and the correlation between the second-level indicators in the first-level indicators obtained in advance, determine the score of the first-level indicators.

[0075] Among them, there are corresponding correlations between the second-level indicators in each first-level indicator.

[0076] In this embodiment, determining the score for each first-level indicator can yield multiple scores for each first-level indicator. Optionally, the processing device can determine the score for each first-level indicator simultaneously or sequentially; this embodiment does not impose specific limitations on this.

[0077] S103. Based on the scores of multiple primary indicators, obtain the medical credit score of the target user.

[0078] In some implementations, the processing device can calculate the sum of scores for multiple primary indicators to obtain the target user's medical credit score. This medical credit score can be used to characterize the target user's level of creditworthiness in seeking medical treatment.

[0079] In practical applications, determining the medical credit score of target users can enable credit-based medical treatment, ushering in a new era of smart healthcare. By combining the Internet with credit, patients can no longer queue for medical treatment or pay at the clinic. Within a certain range of medical expenses and limits, they can enjoy the service of receiving treatment first.

[0080] In summary, this invention provides a medical data processing method, comprising: acquiring medical data of a target user, the target user's medical data including data of multiple first-level indicators, each first-level indicator including data of multiple second-level indicators; determining the score of a first-level indicator based on the data of multiple second-level indicators in the first-level indicator data and the pre-acquired correlation between the second-level indicators in the first-level indicator data; and obtaining the target user's medical credit score based on the scores of the multiple first-level indicators. By using the correlation between the second-level indicators in the first-level indicator data and the scores of the first-level indicators determined from the data of multiple second-level indicators in the first-level indicator data, the acquired scores of the first-level indicators are more accurate. Therefore, by determining the target user's medical credit score based on the medical credit scores of multiple target users, the accuracy and reliability of the target user's medical credit score can be improved.

[0081] Optionally, the processing device can obtain the target user's medical data based on the target user's ID number. Additionally, the processing device can collect basic personal information, basic medical insurance information, medical insurance violation information, medical behavior information, and public welfare behavior information in real-time or T+1 manner.

[0082] In some implementation methods, the collection criteria for basic personal information are shown in Table 1:

[0083] Table 1

[0084]

[0085] In some implementation methods, the collection standards for basic medical insurance information are shown in Table 2:

[0086] Table 2

[0087]

[0088]

[0089] In some implementation methods, the collection criteria for medical insurance violation information are shown in Table 3:

[0090] Table 3

[0091]

[0092] In some implementation methods, the collection criteria for medical behavior information are shown in Table 4:

[0093] Table 4

[0094]

[0095]

[0096]

[0097]

[0098] In some implementation methods, the collection criteria for information on public welfare activities are shown in Table 5:

[0099] Table 5

[0100]

[0101] It should be noted that the first-level indicators are divided into static and dynamic indicators. Static indicators may include: basic personal information and basic medical insurance information; dynamic indicators may include: medical insurance violation information, medical behavior information, and public welfare behavior information. Among them, the upper limit of the score range for static indicators is 100 points; dynamic indicators are divided into benign and malignant. Benign indicators are bonus items, with an upper limit of 100 points; malignant indicators are deduction items, with a lower limit of 0 points.

[0102] In some implementations, the preset medical credit scoring form can be as shown in Table 6:

[0103] Table 6

[0104]

[0105]

[0106]

[0107]

[0108] Optionally, the process of determining the score of the first-level indicator in S102 above, based on the data of multiple second-level indicators in the data of the first-level indicator and the pre-obtained correlation between the second-level indicators in the first-level indicator, may include: determining the score of the first-level indicator based on the data of multiple second-level indicators, the correlation, and the order relationship between the first-level indicators.

[0109] The sequential relationship can be the order between the first second-level indicator in the first-level indicator and the last second-level indicator in the adjacent first-level indicator; the correlation relationship includes the order between the second-level indicators in the first-level indicator.

[0110] In some implementations, the correlation between second-level indicators within the first-level indicators can include: the order of the second-level indicators and the ranking of the second-level indicators. The ranking can be used to characterize the influence of some second-level indicators within the first-level indicators on other second-level indicators. For example, in Table 6, if A6 is "other", the scores of A4 and A5 are disregarded; if B1 is 0, the scores of B2 and B3 are disregarded; if B2 is 0, the score of B3 is disregarded.

[0111] Optionally, the second-level indicators in each first-level indicator can be distributed on a circle, and the direction on which the order relationship is based can be clockwise or counterclockwise.

[0112] Figure 2 A schematic diagram of a first-level indicator and a second-level indicator provided for an embodiment of the present invention, as shown below. Figure 2As shown, the first-level indicators can include: personal basic information A, medical insurance basic information B, medical insurance violation information C, medical behavior information D, and public welfare behavior information E. Among them, personal basic information A can include: A1 age, A2 marital status, A3 fertility status, A4 employer type, A5 years of service, and A6 employment status; medical insurance basic information B can include: B1 insurance status, B2 insured person's payment status, and B3 insured person's medical insurance payment base; medical insurance violation information C can include: insured person's medical insurance warning records; medical behavior information D can include: D1 online appointment registration records, D2 electronic prescription drug purchase records, D3 number of times examination reports were downloaded, D4 number of times test reports were downloaded, and D5 number of times questionnaires were participated in; public welfare behavior information E can include: E1 records of elderly care public welfare activities, E2 volunteer service records, E3 voluntary blood donation, and E4 voluntary hematopoietic stem cell donation.

[0113] For example, the first and second level indicators in personal basic information A can be A1 age, and the last and second level indicators in public welfare behavior information E adjacent to personal basic information A can be E4 voluntary hematopoietic stem cell donation; the first and second level indicators in public welfare behavior information E can be E1 elderly care public welfare activity record, and the last and second level indicators in medical behavior information D adjacent to public welfare behavior information E can be D12 whether real-name authentication is used.

[0114] It should be noted that the above Figure 2 The first-level and second-level indicators in this example are merely examples. Both the first-level and second-level indicators can be expanded based on medical credit-related data indicators. Furthermore, the correlation between the second-level indicators and the order relationship between the first-level indicators can be determined based on the expansion of the data indicators. This application does not impose specific limitations on these aspects.

[0115] Optional, Figure 3 This is a flowchart illustrating a medical data processing method provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the process of determining the score of the first-level indicator based on the data of multiple second-level indicators in the first-level indicator data, the correlation relationship, and the order relationship between the first-level indicators can include:

[0116] S301. Determine the proportion of the second-level indicators in the first-level indicators based on the proportion of the first-level indicators and the number of second-level indicator data in the first-level indicator data.

[0117] In some implementations, the first-level index is set as the first-level axis of polar coordinates, and the proportion of the first-level index can be represented by the angle α between the first-level axes as 360 / Y, where Y can represent the number of first-level indexes.

[0118] In some implementations, the second-level indicators are set as polar coordinate secondary axes, and the proportion of the second-level indicators can be represented by the angle βn between the secondary axes as: α / Nn, where Nn is the number of N second-level indicators under the nth first-level indicator.

[0119] S302. Determine the score of the first-level indicator based on the data, correlation, order relationship between the first-level indicators, and proportion of the second-level indicators.

[0120] In some implementations, the processing device uses a preset calculation formula to determine the score of the first-level indicator based on the data and correlation of multiple second-level indicators, the order relationship between the first-level indicators, and the proportion of the second-level indicators.

[0121] It should be noted that, with Figure 2 For example, the score of the first-level indicator can be the area of ​​the closed polygon formed by all the second-level indicators under the first-level indicator, and the score of the first-level indicator can be calculated based on the area calculation formula.

[0122] The following combination Figure 2 For example:

[0123] Personal basic information score: Where β1 = α / 6.

[0124] Basic Medical Insurance Information Score: Where β2 = α / 3.

[0125] Score for medical insurance violation information: Where β3 = α.

[0126] Medical behavior information score: Where β4 = α / 12.

[0127] Score for public service activities: Where β5 = α / 4.

[0128] In this embodiment of the application, the target user's credit score can be used to classify the target user's credit, as shown in Table 7. The higher the score, the higher the credit level. The credit classification can be calculated as: (total assessment score S / upper limit of model score) * 100%, and the upper limit of model score can be: 29545 ≈ 30000.

[0129] Table 7

[0130] interval grade (0,10％] Level 1 (10％,20％] Level 2 (20％,30％] Level 3 (30％,40％] Level 4 (40％,50％] Level 5 (50％,60％] Level 6 (60％,70％] Level 7 (70％,80％] Level 8 (80％,90％] Level 9 (90％,100％] Level 10

[0131] Optionally, the process of obtaining the target user's medical credit score based on the scores of multiple first-level indicators in S103 above may include: weighted summation based on the weights of multiple first-level indicators and the scores of multiple first-level indicators to obtain the target user's medical credit score.

[0132] Among them, the weights of multiple first-level indicators can all be non-zero values, or they can include both zero and non-zero values ​​at the same time.

[0133] Optional, Figure 4 This is a flowchart illustrating a medical data processing method provided in an embodiment of the present invention, as shown below. Figure 4 As shown, before the process of obtaining the target user's medical credit score by weighted summation based on the weights and scores of multiple primary indicators, the method further includes:

[0134] S401. Determine the contribution rate of multiple primary indicators based on their scores.

[0135] S402. Based on the contribution rate of multiple primary indicators, sort the multiple primary indicators and determine the weight of the multiple primary indicators.

[0136] The processing device can determine the correlation between multiple primary indicators based on their scores. When it is determined that the multiple primary indicators are correlated, independent, or uncorrelated, principal component analysis can be performed, and the above-mentioned processes S401 to S402 can be executed.

[0137] In some implementations, the scores of multiple first-level indicators for the i-th person are denoted as: X i1 X i2 X i3 X i4 X i5 Where i = 1, ..., n. This can be represented by a matrix as:

[0138]

[0139] The processing equipment can obtain the coefficient matrix and then perform KMO and Bartlett's sphericity tests. If the KMO statistic is greater than 0.7 and the significance (sig) value of the Bartlett's sphericity test is less than or equal to 0.05, the selected variables are suitable for principal component analysis.

[0140] The KMO statistic is defined as follows:

[0141]

[0142] Note: Where r ij Let P be the simple correlation coefficient between the i-th variable and the j-th variable.ij Let be the partial correlation coefficient between the i-th and j-th variables after controlling for the remaining variables. The KMO test is used to examine the correlation and partial correlation between variables, with a value ranging from 0 to 1. The closer the value is to 1, the stronger the correlation and the lower the partial correlation between the variables, and the more suitable the sample data is for principal component analysis and factor analysis. According to Kaiser's research experience, MSA > 0.9 indicates very suitable, 0.8-0.9 indicates suitable, 0.7-0.8 indicates average, 0.6-0.7 indicates acceptable, 0.5-0.6 indicates not very suitable, and below 0.5 indicates extremely unsuitable.

[0143] Bartlett's test of sphericity determines whether the correlation coefficient matrix is ​​an identity matrix, i.e., it tests whether the variables are independent of each other. When the test result (sig) value (this is the result output by SPSS calculation) is less than or equal to 0.05, the variables are considered to be independent to a certain extent and uncorrelated, and principal component analysis can be performed.

[0144] It should be noted that the processing device standardizes the above matrix, solves the characteristic equation, and obtains its corresponding eigenvalue λ. j and the corresponding feature vector U j The eigenvalues ​​are then rearranged in descending order: λ1≥λ2≥…≥λ5≥0. At this point, the new index variable is composed of the eigenvectors.

[0145]

[0146] In one possible implementation, the processing device can calculate the principal component contribution rate, the cumulative contribution rate, and determine the number of principal components, wherein the principal component value refers to the first-level index.

[0147] The principal component contribution rate can be expressed as:

[0148]

[0149] The cumulative contribution rate can be expressed as:

[0150]

[0151] Where λ represents the characteristic value corresponding to the first-level indicator.

[0152] In this embodiment, multiple first-level indicators have a certain order, and the number of principal components m can be determined according to a cumulative contribution rate ≥ 80%. λ1, λ2, ..., λ mThis corresponds to the first, second, ..., m-th (m≤5) principal components. The first principal component has the largest contribution rate and the strongest explanatory power for the original variables, with the explanatory power of the remaining principal components decreasing sequentially. The weight of each principal component is determined by its variance contribution rate. The weights of each principal component are expressed as follows:

[0153]

[0154] Where λ represents the characteristic value corresponding to the first-level indicator. This represents a new indicator variable.

[0155] Additionally, for other first-level indicators that are not principal components, their weights can be set to 0.

[0156] Optional, Figure 5 This is a flowchart illustrating a medical data processing method provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the process of determining the contribution rate of multiple first-level indicators based on their scores in S401 above may include:

[0157] S501. Calculate the characteristic values ​​of multiple first-level indicators based on their scores.

[0158] In some implementations, the processing device can determine a matrix of multiple first-level indicators based on the scores of multiple first-level indicators, and calculate the feature values ​​of multiple first-level indicators based on the matrix of multiple first-level indicators.

[0159] It should be noted that a matrix of multiple first-level indicators can be represented as follows:

[0160]

[0161] Where X1, X2, X3, X4, and X5 represent the scores of multiple first-level indicators.

[0162] Optionally, the processing device can standardize the matrix of multiple first-level indicators, solve the characteristic equation, and obtain the characteristic values ​​of the multiple first-level indicators.

[0163] S502. Determine the contribution rate of multiple first-level indicators based on their characteristic values.

[0164] In this embodiment of the application, the contribution rate of each first-level indicator can be: The contribution rate of at least one primary indicator can be:

[0165] It should be noted that the processing equipment can use an evaluation model to achieve the process of determining the medical credit score of the target user.

[0166] Optionally, the method may further include: determining the participation balance of the target user based on the number of non-zero secondary indicators in the target user's medical data and the preset number of secondary indicator benchmarks.

[0167] The preset number of second-level indicator benchmarks can be the sum of the number of second-level indicator benchmarks in each first-level indicator.

[0168] In some implementations, the processing device employs an analytical model to determine the participation balance of the target user based on the proportion of the number of non-zero secondary indicators in the target user's medical data to the preset baseline number of secondary indicators.

[0169] In this context, the number of non-zero secondary indicators in the target user's medical data can be n, and the sum of the baseline number of secondary indicators in each primary indicator can be expressed as: N A +N B +N C +N D +N E Then, the participation equilibrium of the target users can be expressed as:

[0170]

[0171] It should be noted that, Figure 2 The number of triangles representing the target users can reflect the balance of credit participation among the target users.

[0172] Optional, Figure 6 This is a flowchart illustrating a medical data processing method provided in an embodiment of the present invention, as shown below. Figure 6 As shown, the method may further include:

[0173] S601. Fit the historical medical credit score curves of the target user at multiple historical time points to obtain the fitted curve of the target user.

[0174] S602. Based on the fitted curve, determine the future medical credit score of the target user at a future time point.

[0175] In this process, a predictive model can be used to execute the above S601 to S602 processes.

[0176] In this embodiment of the application, due to the dynamic changes in users' personal credit, static models can no longer meet the needs, and it is necessary to study and implement dynamic credit scoring methods. Therefore, it is necessary to track users' credit information, continuously add new information, and obtain dynamic credit scores accordingly. By analyzing the score structure and credit trends of an individual's credit over any number of research periods, it is possible to more accurately predict and assess an individual's credit status.

[0177] Figure 7 This invention provides a flowchart illustrating historical medical credit score curves at multiple historical time points, as shown in the embodiment of the invention. Figure 7 As shown, the horizontal axis t represents the log, and the vertical axis represents the credit value St.

[0178] In some implementations, the curve is transformed into a linear curve by variable substitution: S = In(St), T = In(t); t represents a specific time, and St represents the credit value at the specific time t. The optimal value is obtained by taking the condition of "minimum sum of squared residuals" and fitting it into the optimal straight line and the optimal curve.

[0179] The standard curve, which is a straight line, is represented by the following formula: S = a + bT. Where b is the slope of the line (regression coefficient), and a is the intercept. Historical medical credit scores at multiple historical time points can be represented as (Ti, Si), where i = 1, 2, ..., n.

[0180] The error equation can be expressed in terms of residuals vi as: v1 = S1 - (a + bT1), v2 = S2 - (a + bT2) ... vn = Sn - (a + bTn). To minimize the sum of squared residuals, we need to make Σvi 2 =Σ[Si-(a+bTi)]=min. Therefore, we must simultaneously take the partial derivatives with respect to a and b and make them zero to obtain the simultaneous equations.

[0181] Solving the system of equations yields:

[0182]

[0183]

[0184] Then, the fitted curve for the target user can be obtained.

[0185] In practical applications, the credit results obtained from the predictive model are further analyzed to assess the medical credit of the regional population. By performing attribute analysis, comparison, and calculation on users with different credit ratings, a probability formula for predicting future default behavior is derived, and user behavior information is used to implement risk control. Alternatively, the change function of a specific credit indicator can be analyzed to determine the magnitude of the impact of different indicators on the credit score.

[0186] This application provides a medical data processing method that can be applied to the application stage of health insurance. Insurance companies can refer to patients' medical credit assessment results to rate them and determine whether customers meet the application requirements, providing a basis for the insurance company's underwriting process and ensuring its systematization and transparency. It can also be applied to the field of medical loans, where banks can provide different loan services based on patients' medical credit assessment results. Furthermore, it can be applied to the field of medical assistance. When establishing a medical assistance system, different standards of assistance can be formulated based on patients' medical credit assessment results, rather than using a single rigid standard to determine the scope and standards of assistance recipients. Through continuous trial and adjustment, a medical assistance system that balances fairness and efficiency can be developed.

[0187] The following are examples.

[0188] Example 1

[0189] Personal medical credit inquiry request: Receive personal medical credit inquiry request from target user A. The request content includes name and ID number.

[0190] Medical credit data search: Based on the ID card number of target user A, search the basic data center of personal medical credit in City X and match the target user A's basic personal information, medical insurance information, medical behavior information, and public welfare behavior information.

[0191] Medical credit assessment: Determine the personal medical credit score of target user a, as shown in Table 8.

[0192] Table 8

[0193]

[0194]

[0195]

[0196] The final score is obtained by calculating the area of ​​the shaded region in the graph obtained by scoring according to the evaluation model. Figure 8 This is a schematic diagram of the rating of target user a provided in an embodiment of the present invention, such as... Figure 8 As shown, the scores for each first-level indicator are as follows:

[0197] Personal Information Score:

[0198] Basic Medical Insurance Information Score:

[0199] Score for medical insurance violation information:

[0200] Medical behavior information score:

[0201] Score for public service activities:

[0202] Total Assessment Score: S n =S A +S B +S C +S D +S E =15193

[0203] It can be determined that the credit rating of target user A is level 6.

[0204] Example 2

[0205] Personal medical credit inquiry request: Receive personal medical credit inquiry request from target user b. The request content includes name and ID number.

[0206] Medical credit data search: Based on the ID card number of target user b, search the basic data center of personal medical credit in City X and match target user b's basic personal information, medical insurance information, medical behavior information, and public welfare behavior information.

[0207] Medical credit assessment: Determine the personal medical credit score of target user b, as shown in Table 9.

[0208] Table 9

[0209]

[0210]

[0211]

[0212] The final score is obtained by calculating the area of ​​the shaded region in the graph obtained by scoring according to the evaluation model. Figure 9 This is a schematic diagram of the rating of target user b provided in an embodiment of the present invention, such as... Figure 9 As shown, the scores for each first-level indicator are as follows:

[0213] Personal Information Score:

[0214] Basic Medical Insurance Information Score:

[0215] Score for medical insurance violation information:

[0216] Medical behavior information score:

[0217] Score for public service activities:

[0218] Total Assessment Score: S n =S A +S B +S C +S D +S E =18173

[0219] It can be determined that the credit rating of target user B is level 7.

[0220] The total difference in credit scores between target user A and target user B is 431 points. After the evaluation model calculates the scores, the difference between the two scores is 2980, which is more than 6 times larger, allowing for a more refined credit rating of the two users.

[0221] Example 3

[0222] Personal medical credit inquiry request: Receive personal medical credit inquiry request from target user c. The request content includes name and ID number.

[0223] Medical credit data search: Based on the ID card number of target user C, search the basic data center of personal medical credit in City X and match the target user C's basic personal information, medical insurance information, medical behavior information, and public welfare behavior information.

[0224] Medical credit assessment: Determine the personal medical credit score table for target user c, as shown in Table 10.

[0225] Table 10

[0226]

[0227]

[0228]

[0229] The final score is obtained by calculating the area of ​​the shaded region in the graph obtained by scoring according to the evaluation model. Figure 10 This is a schematic diagram of the rating of target user c provided in an embodiment of the present invention, such as... Figure 10 As shown, the scores for each first-level indicator are as follows:

[0230] Personal Information Score:

[0231] Basic Medical Insurance Information Score:

[0232] Score for medical insurance violation information:

[0233] Medical behavior information score:

[0234] Score for public service activities:

[0235] Total Assessment Score: S n =S A +S B +S C +S D +S E =14921

[0236] It can be determined that the credit rating of target user C is level 5.

[0237] As can be seen from the above, this example highlights the ranking relationship between secondary indicators. It shows that because the medical insurance payment status is "sealed", even if the insured user c's medical insurance payment base score is 80 points, the area from "insured status" to "insured person's medical insurance payment base" in the model coordinates is zero because the payment status has a priori determining effect on the payment base, i.e., a ranking relationship. This results in the area being zero, thus affecting the credit score and rating.

[0238] In summary, the medical data processing method provided in this application improves the construction of the medical credit system. Through interconnection and information sharing between platforms containing medical credit-related data, it achieves timely, complete, and accurate collection of personal medical credit data, overcoming the problems of data silos and data integration between platforms. It innovates the type of medical and health supervision, promoting individuals to consciously regulate their behavior through mechanisms of rewarding good faith and punishing bad faith; it enhances the patient's medical experience and optimizes the treatment process; and it supports the development of businesses such as medical loans, commercial insurance underwriting qualification review, medical assistance, and health poverty alleviation.

[0239] Furthermore, it can strengthen medical insurance supervision. The construction of credit-based healthcare provides valuable information support for the control and intelligent supervision of medical insurance costs, enabling targeted regulatory measures based on the credit classification of population groups. It promotes the construction of a social credit system, establishing credit files for individuals in the medical field and using a time-frame approach for dynamic evaluation, which can serve as part of the social credit system. It highlights the correlation between credit indicators, refines credit structure analysis, and provides a basis for relevant management decisions.

[0240] The following describes the medical data processing apparatus, processing equipment, and storage medium used to execute the medical data processing method provided in this application. For the specific implementation process and technical effects, please refer to the relevant content of the above-mentioned medical data processing method, which will not be repeated below.

[0241] Figure 11 This is a schematic diagram of the structure of a medical data processing device provided in an embodiment of the present invention, as shown below. Figure 11 As shown, the device may include:

[0242] The first acquisition module 1101 is used to acquire the medical data of the target user, the medical data of the target user includes: data of multiple first-level indicators, and each first-level indicator includes data of multiple second-level indicators;

[0243] The determining module 1102 is used to determine the score of the first-level indicator based on the data of the multiple second-level indicators in the data of the first-level indicator and the pre-acquired correlation between the second-level indicators in the first-level indicator.

[0244] The second acquisition module 1103 is used to obtain the medical credit score of the target user based on the scores of multiple first-level indicators.

[0245] Optionally, the determining module 1102 is further configured to determine the score of the first-level indicator based on the data of the plurality of second-level indicators, the correlation relationship, and the order relationship among the first-level indicators; wherein, the order relationship is the order relationship between the first second-level indicator in the first-level indicators and the last second-level indicator in the adjacent first-level indicators, and the correlation relationship includes: the order relationship among the second-level indicators in the first-level indicators.

[0246] Optionally, the determining module 1102 is further configured to determine the proportion of the second-level indicators in the first-level indicators based on the proportion of the first-level indicators and the number of second-level indicator data in the first-level indicator data; and to determine the score of the first-level indicators based on the data of the multiple second-level indicators, the correlation relationship, the order relationship between the first-level indicators, and the proportion of the second-level indicators.

[0247] Optionally, the second acquisition module 1103 is further configured to perform a weighted summation based on the weights of multiple first-level indicators and the scores of multiple first-level indicators to obtain the medical credit score of the target user.

[0248] Optionally, the device further includes:

[0249] The first determining module is used to determine the contribution rate of multiple first-level indicators based on their scores; and to sort the multiple first-level indicators based on their contribution rates to determine their weights.

[0250] Optionally, the first determining module is used to calculate the feature values ​​of the multiple first-level indicators based on the scores of the multiple first-level indicators; and to determine the contribution rate of the multiple first-level indicators based on the feature values ​​of the multiple first-level indicators.

[0251] Optionally, the device further includes:

[0252] The second determining module is used to determine the participation balance of the target user based on the number of non-zero second-level indicators in the target user's medical data and the preset number of second-level indicator benchmarks.

[0253] Optionally, the device further includes:

[0254] The third acquisition module is used to fit the historical medical credit score curves of the target user at multiple historical time points to obtain the fitted curve of the target user.

[0255] The third determining module is used to determine the future medical credit score of the target user at a future time point based on the fitted curve.

[0256] The above-described device is used to execute the method provided in the foregoing embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0257] These modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a system-on-a-chip (SOC).

[0258] Figure 12This is a schematic diagram of the structure of a processing device provided in an embodiment of the present invention, as shown below. Figure 12 As shown, the processing device includes: processor 1201 and memory 1202.

[0259] The memory 1202 is used to store programs, and the processor 1201 calls the programs stored in the memory 1202 to execute the above method embodiments. The specific implementation and technical effects are similar, and will not be described again here.

[0260] Optionally, the present invention also provides a program product, such as a computer-readable storage medium, including a program that, when executed by a processor, is used to perform the above-described method embodiments.

[0261] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0262] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0263] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0264] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0265] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A medical data processing method, characterized in that, include: Acquire the medical data of the target user, wherein the medical data of the target user includes: data of multiple first-level indicators, and each first-level indicator includes data of multiple second-level indicators; The score of the first-level indicator is determined based on the data of multiple second-level indicators in the data of the first-level indicator and the pre-obtained correlation between the second-level indicators in the first-level indicator. The target user's medical credit score is obtained based on the scores of multiple first-level indicators; The step of determining the score of the first-level indicator based on the data of multiple second-level indicators in the data of the first-level indicator and the pre-acquired correlation between the second-level indicators in the first-level indicator includes: The scores of the first-level indicators are determined based on the data of the multiple second-level indicators, the correlation relationships, and the order relationships among the first-level indicators; wherein, the order relationship is the order relationship between the first second-level indicator in the first-level indicators and the last second-level indicator in the adjacent first-level indicators, and the correlation relationship includes the order relationship among the second-level indicators in the first-level indicators. The step of determining the score of the first-level indicator based on the data of the multiple second-level indicators in the data of the first-level indicator, the correlation relationship, and the order relationship between the first-level indicators includes: The proportion of the second-level indicators in the first-level indicators is determined based on the proportion of the first-level indicators and the number of second-level indicator data in the data of the first-level indicators. The score of the first-level indicator is determined based on the data of the multiple second-level indicators, the correlation, the order relationship between the first-level indicators, and the proportion of the second-level indicators. The step of obtaining the target user's medical credit score based on the scores of multiple first-level indicators includes: The target user's medical credit score is obtained by weighting and summing the weights and scores of multiple first-level indicators. Before obtaining the medical credit score of the target user by weighted summation based on the weights and scores of multiple first-level indicators, the method further includes: The contribution rate of multiple first-level indicators is determined based on their scores. Based on the contribution rate of multiple first-level indicators, the multiple first-level indicators are sorted to determine the weight of the multiple first-level indicators. Before determining the contribution rate of multiple first-level indicators based on their scores, the method further includes: Based on the scores of multiple first-level indicators, determine the correlation between the multiple first-level indicators; If multiple first-level indicators are correlated, independent, or uncorrelated, then principal component analysis is performed. The method further includes: Calculate the principal component contribution rate and cumulative contribution rate to determine the number of principal components. The principal component value refers to the first-level indicator. The first principal component has the largest contribution rate and the strongest ability to explain the original variables, while the explanatory power of the remaining principal components decreases in that order. The weight of each principal component is determined by the variance contribution rate of that principal component. The method further includes: The participation balance of the target user is determined based on the number of non-zero secondary indicators in the target user's medical data and the preset benchmark number of secondary indicators. The preset number of second-level indicator benchmarks is the sum of the number of second-level indicator benchmarks in each first-level indicator; The participation balance of the target users is represented as follows: in, The number of non-zero second-level indicators in the target user's medical data. This is the sum of the number of second-level indicator benchmarks in each of the first-level indicators.

2. The method according to claim 1, characterized in that, The step of determining the contribution rate of multiple first-level indicators based on their scores includes: Based on the scores of multiple first-level indicators, calculate the feature values ​​of multiple first-level indicators; The contribution rate of multiple first-level indicators is determined based on the feature values ​​of multiple first-level indicators.

3. The method according to claim 1, characterized in that, The method further includes: Based on the historical medical credit score curves of the target user at multiple historical time points, a fitted curve for the target user is obtained. Based on the fitted curve, the future medical credit score of the target user at a future time point is determined.

4. A medical data processing device, characterized in that, include: The first acquisition module is used to acquire the medical data of the target user, wherein the medical data of the target user includes: data of multiple first-level indicators, and each first-level indicator includes data of multiple second-level indicators; The determining module is used to determine the score of the first-level indicator based on the data of the multiple second-level indicators in the data of the first-level indicator and the pre-acquired correlation between the second-level indicators in the first-level indicator. The second acquisition module is used to obtain the medical credit score of the target user based on the scores of multiple first-level indicators; The determining module is specifically used to determine the score of the first-level indicator based on the data of the multiple second-level indicators, the correlation relationship, and the order relationship between the first-level indicators; wherein, the order relationship is the order relationship between the first second-level indicator in the first-level indicators and the last second-level indicator in the adjacent first-level indicators, and the correlation relationship includes: the order relationship between the second-level indicators in the first-level indicators. The determining module is specifically used to determine the proportion of the second-level indicators in the first-level indicators based on the proportion of the first-level indicators and the number of second-level indicator data in the data of the first-level indicators; and to determine the score of the first-level indicators based on the data of the multiple second-level indicators, the correlation relationship, the order relationship between the first-level indicators, and the proportion of the second-level indicators. The second acquisition module is specifically used to perform a weighted summation based on the weights of multiple first-level indicators and the scores of multiple first-level indicators to obtain the medical credit score of the target user. The device further includes: The first determining module is used to determine the contribution rate of multiple first-level indicators based on their scores; and to sort the multiple first-level indicators based on their contribution rates to determine their weights. The first determining module can also be used to determine the correlation between multiple first-level indicators based on their scores; if the multiple first-level indicators are correlated but independent or uncorrelated, then principal component analysis is performed. The first determining module can also be used to calculate the principal component contribution rate and cumulative contribution rate, and determine the number of principal components. The principal component value refers to the first-level index. The first principal component has the largest contribution rate and the strongest ability to explain the original variable, while the explanatory power of the remaining principal components decreases in sequence. The weight of each principal component is determined by the variance contribution rate of the principal component. The device further includes: The second determining module is used to determine the participation balance of the target user based on the number of non-zero second-level indicators in the target user's medical data and the preset number of second-level indicator benchmarks; the preset number of second-level indicator benchmarks is the sum of the number of second-level indicator benchmarks in each first-level indicator. The participation balance of the target users is represented as follows: in, The number of non-zero second-level indicators in the target user's medical data. This is the sum of the number of second-level indicator benchmarks in each of the first-level indicators.

5. A processing device, characterized in that, include: A memory and a processor, the memory storing a computer program executable by the processor, the processor executing the computer program to implement the medical data processing method according to any one of claims 1-3.

6. A storage medium, characterized in that, The storage medium stores a computer program, which, when read and executed, implements the medical data processing method according to any one of claims 1-3.

Images