Data analysis method and device for mother and infant medical insurance product development and medium
By acquiring and analyzing multi-dimensional medical data from multiple data sources, a theme database for maternal and infant medical insurance product development has been formed, which solves the problems of insufficient data and quality, realizes accurate risk assessment and product adjustment, and improves the accuracy of product design and pricing.
Patent Information
- Application Number
- CN202411184556.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-06
AI Technical Summary
In the development of maternal and infant medical insurance products, we face challenges such as insufficient medical and health data and inconsistent data quality, which limits the full use of the value of big data and is difficult to achieve accurate population and market segmentation, resulting in inaccurate product design and pricing.
Multi-dimensional medical data is obtained through multiple data sources, a theme database for maternal and infant medical insurance product development is formed, data labeling, cleaning and analysis is carried out, risk and cost indicators are evaluated, and cost analysis reports are generated for product adjustment.
It improves the richness and diversity of data, screens out key information, improves data processing efficiency and analysis accuracy, provides scientific decision-making basis, and formulates more reasonable insurance products and rates.
Smart Images

Figure CN119088886A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data analysis technology, and in particular to a data analysis method, device and medium for developing maternal and infant medical insurance products. Background Art
[0002] In the current social context, maternal and child health has become the focus of public attention, and with it comes an urgent need for maternal and child health insurance products. Traditional commercial health insurance often fails to fully cover specific medical needs during pregnancy, delivery and the postpartum period, especially there is a clear gap in the protection of congenital diseases of older pregnant women and newborns. With the relaxation of fertility policies, the enhancement of people's health awareness and the improvement of economic levels, consumers are increasingly demanding insurance products that can provide comprehensive maternal and child health protection, hoping to effectively alleviate the economic pressure of childbirth and raising children through insurance mechanisms, thereby promoting the increase of fertility rates and the stability of social families.
[0003] In response to this market demand, the maternal and child health insurance market is experiencing a rapid expansion globally, especially in China, indicating that this field has huge development potential and market space. The government's positive policy orientation has provided strong support for the development of the maternal and child health insurance industry and accelerated the growth of the market. At the same time, technological innovation, especially the widespread application of big data and artificial intelligence technology, is leading the maternal and child health insurance industry to transform towards digitalization and intelligence, making products and services more in line with consumers' diversified and personalized needs, and promoting the industry to move towards customized services.
[0004] However, although the application of data analysis technology in the field of commercial health insurance has demonstrated its great potential in customer insight and demand analysis, and promoted the customization and rationalization of product design, in the process of developing maternal and child medical insurance products, it still faces challenges such as insufficient medical and health data and uneven data quality, which limits the full use of the value of big data. Therefore, how to effectively collect and analyze customer information and health and medical big data, achieve accurate population and market segmentation, and then develop innovative maternal and child medical insurance products that meet the needs of potential customers, have detailed liability design, and accurate pricing has become a key issue that the current health insurance industry needs to solve. Summary of the invention
[0005] The embodiments of the present application provide a data analysis method, device and medium for the development of maternal and infant medical insurance products to solve the above-mentioned technical problems.
[0006] On the one hand, the present application embodiment provides a data analysis method for developing maternal and infant medical insurance products, including: Acquire multidimensional medical data through multiple data sources, and extract data from the multidimensional medical data to form a subject database for maternal and child medical insurance product development; Marking the maternal and infant medical data in the maternal and infant medical insurance product development subject database, and performing data cleaning on the marked maternal and infant medical data; Data analysis is performed on the marked and cleaned maternal and infant medical data to evaluate the risk cost indicators of maternal and infant medical insurance products corresponding to the maternal and infant medical data, and a corresponding cost analysis report is generated based on the data analysis results.
[0007] In one implementation of the present application, obtaining multidimensional medical data through multiple data sources includes: Determine multiple data sources for health and medical data collection, and respectively establish secure data transmission channels between the multiple data sources; Acquire multidimensional medical data from the multiple data sources through the secure data transmission channel, and store the structured and unstructured multidimensional medical data in the data lake based on database underlying aggregation technology and image file aggregation technology; The multi-dimensional medical data at least includes: physiological indicators of pregnant women, prenatal examination results, delivery records, and health conditions and test data of newborns.
[0008] In one implementation of the present application, data extraction is performed in the multidimensional medical data to form a subject database for maternal and child medical insurance product development, including: Based on a designated diagnosis code, obtaining maternal and child data from the multidimensional medical data; wherein the designated diagnosis code is used to indicate a diagnosis code whose first digit is a designated value; Determine the difference between the admission date and the discharge date of each medical data, and compare the difference with the specified time period; When the difference is less than the specified time length, determining that the user type corresponding to the medical data is a newborn, so as to obtain corresponding newborn data in the multidimensional medical data; The maternal and infant medical data corresponding to the maternal data and the newborn data are determined, and a maternal and infant medical insurance product development subject database corresponding to the maternal and infant medical data is formed.
[0009] In one implementation of the present application, marking the maternal and infant medical data in the maternal and infant medical insurance product development subject database includes: Based on the production-related codes and production-related operation codes, the data of pregnant women are determined in the subject database of the development of maternal and child medical insurance products, and the corresponding production date is determined according to the hospitalization date in the data of pregnant women; The maternal delivery date is used as the maternal index date, and the newborn's birth date is used as the newborn's index date to mark the index date in maternal and child medical data.
[0010] In one implementation of the present application, marking the maternal and infant medical data in the maternal and infant medical insurance product development subject database includes: In the subject database of maternal and infant medical insurance product development, risk factors related to maternal and infant health are queried, and risk factors in maternal and infant medical data are marked; wherein the risk factors at least include: pre-existing hypertension and gestational hypertension, preeclampsia and eclampsia, threatened abortion and hyperemesis gravidarum; Obtain historical maternal and infant medical data within a preset time period, and determine the risk frequency corresponding to each historical maternal and infant medical data based on the historical maternal and infant medical data; wherein the risk frequency is used to indicate the number of occurrences of a specified disease or a specified event corresponding to each risk factor in the maternal and infant group; Based on the mapping relationship between historical maternal and infant medical data and accident frequency, the accident frequency corresponding to each maternal and infant medical data in the maternal and infant medical insurance product development subject database is determined respectively, and the accident frequency of the maternal and infant medical data is marked.
[0011] In one implementation of the present application, data cleaning is performed on the marked maternal and child medical data, including: Count the frequency of missing variables in maternal and child medical data, and delete the maternal and child medical data with missing variables; Identify abnormal maternal and child medical data whose age is not within the specified age range, and abnormal maternal and child medical data whose total cost is not within the specified cost range; Delete maternal and infant medical data with abnormal age and cost, and count the corresponding proportion distribution of the deleted maternal and infant medical data; Determine the maternal and child medical data with abnormal self-payment ratios where the self-payment ratio between the self-payment and the total cost is not within the specified ratio range, so as to determine that the maternal and child medical data with abnormal self-payment ratios are missing self-payment, and calculate the missing ratio distribution; Based on the maternal and infant medical insurance product development subject database, the mean value of out-of-pocket expenses is calculated to fill in the missing values of out-of-pocket expenses according to the mean value of out-of-pocket expenses.
[0012] In one implementation of the present application, data analysis is performed on the marked and cleaned maternal and infant medical data to evaluate the risk cost index of the maternal and infant medical insurance product corresponding to the maternal and infant medical data, including: Based on the marked and cleaned maternal and child medical data, determine the claims-related data in the vertical dimension and the claims-related data in the horizontal dimension; wherein the claims-related data in the vertical dimension include: user type, year, city, age group and medical insurance type, and the claims-related data in the horizontal dimension include: the number of cases, hospitalization expenses and out-of-pocket expenses for each case; Determine personal data in the vertical dimension and personal data in the horizontal dimension; among them, the personal data in the vertical dimension are the same as the claims-related data in the vertical dimension, and the personal data in the horizontal dimension include: number of people, average number of hospitalizations per person, average hospitalization expenses per person, average out-of-pocket expenses per person, and incidence of maternal risk factors.
[0013] In one implementation of the present application, a corresponding cost analysis report is generated based on the data analysis results, including: Based on the data analysis results, the risk cost indicators of maternal and infant medical insurance products are summarized, and an evaluation is performed based on the summarized risk cost indicators; wherein the risk cost indicators include total expenses, out-of-pocket expenses and compensation ratio; According to the risk cost assessment results, determine the user information corresponding to the high risk cost and determine the corresponding cost distribution; wherein the user information includes user group, region and disease type; Generate a corresponding cost analysis report, and based on the cost distribution, adjust the development of maternal and child medical insurance products to reduce the corresponding risk costs.
[0014] On the other hand, the embodiment of the present application also provides a data analysis device for developing maternal and infant medical insurance products, the device comprising: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data analysis method for the development of maternal and child medical insurance products as described above.
[0015] On the other hand, an embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, which, when executed, implement the data analysis method for developing maternal and child medical insurance products as described above.
[0016] The present application provides a data analysis method, device and medium for developing maternal and infant medical insurance products, which at least have the following beneficial effects: Acquiring multidimensional maternal and infant medical data from multiple data sources can more comprehensively cover all aspects of the maternal and infant medical field and improve the richness and diversity of data; through the data extraction process, key information related to the development of maternal and infant medical insurance products can be screened out to form a special subject database to provide an accurate data basis for subsequent analysis; tagging maternal and infant medical subject data based on keywords helps to quickly locate and analyze related data and improve data processing efficiency; by cleaning the labeled data, redundant, erroneous or inconsistent information can be removed, data quality can be improved, and the accuracy of analysis can be ensured; in-depth analysis of the cleaned data can accurately evaluate the risk cost indicators of maternal and infant medical insurance products; the cost analysis report generated based on the data analysis results can provide a scientific basis for decision-making, thereby formulating more reasonable insurance products and rates. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flow chart of a data analysis method for developing maternal and infant medical insurance products provided in an embodiment of the present application; Figure 2 A schematic diagram of the internal structure of a data analysis device for developing maternal and child medical insurance products provided in an embodiment of the present application. DETAILED DESCRIPTION
[0018] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0019] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0020] Figure 1 A flow chart of a data analysis method for developing maternal and infant medical insurance products provided in an embodiment of the present application.
[0021] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.
[0022] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.
[0023] like Figure 1 As shown, the data analysis method for developing maternal and infant medical insurance products provided in the embodiment of the present application includes: Step 101: Acquire multidimensional medical data through multiple data sources, and extract data from the multidimensional medical data to form a subject database for maternal and child medical insurance product development.
[0024] Specifically, the server obtains multi-dimensional medical data through multiple data sources, including: Identify multiple data sources for health and medical data collection, and build secure data transmission channels between the multiple data sources; Through secure data transmission channels, multi-dimensional medical data is obtained from multiple data sources, and based on database underlying aggregation technology and image file aggregation technology, structured and unstructured multi-dimensional medical data is stored in the data lake; It should be noted that the multidimensional medical data in the embodiment of the present application at least includes: physiological indicators of pregnant women, prenatal examination results, delivery records, and health conditions and test data of newborns.
[0025] In one embodiment, multiple data sources for health and medical data collection are determined, and a secure data transmission channel is established. Through the secure data channel, various health and medical data of pregnant women from pregnancy to delivery, as well as the growth of newborns are collected, sorted, stored and analyzed. In this embodiment, the National Health and Medical Big Data Center (North) is used as the data source, and the National Health and Medical Big Data Center (North) synchronously obtains data from the National Health Information Platform.
[0026] These data include but are not limited to pregnant women's physiological indicators (such as blood pressure, blood sugar, weight, etc.), prenatal examination results, delivery records, newborn health conditions (such as birth weight, jaundice, asphyxia, etc.) and subsequent infant health monitoring data. Then, the database underlying aggregation technology and image file aggregation technology are used to aggregate structured and unstructured multidimensional medical data into the data lake. Based on HDFS, MPP database and object storage, the massive data storage is completed, and the multidimensional medical data is encrypted through the data encryption system to realize the encrypted storage of sensitive data and prevent data leakage caused by de-database attacks and other methods.
[0027] In one embodiment of the present application, the server extracts data from the multi-dimensional medical data to form a maternal and child medical insurance product development subject database, including: Based on the specified diagnosis code, the maternal and infant data are obtained from the multidimensional medical data; wherein the specified diagnosis code is used to indicate the diagnosis code whose first digit is a specified value; Determine the difference between the admission date and the discharge date of each medical data, and compare the difference with the specified time period; When the difference is less than the specified time length, determining that the user type corresponding to the medical data is a newborn, so as to obtain corresponding newborn data in the multi-dimensional medical data; Determine the maternal and infant medical data corresponding to the pregnant and lying-in data and the newborn data, and form a thematic database for the development of maternal and infant medical insurance products corresponding to the maternal and infant medical data.
[0028] In one embodiment, all inpatient medical visit data of all patients with any ICD10 diagnosis code starting with "O" are obtained, that is, the maternal data are obtained. All inpatient medical visit data with a difference of less than 1 year between the admission date and the birth date are obtained, that is, the newborn data are obtained.
[0029] Table 1 is a table of key data variables for data extraction. The key data variables are shown in Table 1 below: Table 1
[0030] It should be noted that the key data variables in the embodiment of the present application include patient ID, hospitalization ID, hospital ID, hospital name, city where the hospital is located, date of birth, admission date, discharge date, age_year, age_month, social security type, total cost, personal out-of-pocket expenses, personal out-of-pocket expenses, diagnosis name, diagnosis category, ICD9 CM3 surgery code and surgery name.
[0031] Step 102: Mark the maternal and infant medical data in the maternal and infant medical insurance product development subject database, and perform data cleaning on the marked maternal and infant medical data.
[0032] Specifically, in one embodiment of the present application, the server marks the maternal and infant medical data in the maternal and infant medical insurance product development subject database, including: Based on the delivery-related codes and delivery-related operation codes, the maternal data are determined in the subject database of maternal and child medical insurance product development, and the corresponding delivery date is determined according to the admission date in the maternal data; The maternal delivery date is used as the maternal index date, and the newborn's birth date is used as the newborn's index date to mark the index date in maternal and child medical data.
[0033] In one embodiment, in the maternal and child health medical data labeling technology module, the index date, risk factors and accident frequency are three key concepts. For pregnant women, the index date is the date of production, and the corresponding date of production for the pregnant woman is determined based on the ICD10 code related to production and the admission date on the first page of the medical record where the ICD9 surgery code is located. For newborns, the index date is the date of birth.
[0034] In one embodiment of the present application, the server marks the maternal and infant medical data in the maternal and infant medical insurance product development subject database, including: In the subject database of maternal and infant medical insurance product development, query the risk factors related to maternal and infant health, and mark the risk factors in maternal and infant medical data; among them, the risk factors at least include: pre-existing hypertension and gestational hypertension, preeclampsia and eclampsia, threatened abortion and hyperemesis gravidarum; Obtain historical maternal and infant medical data within a preset time period, and determine the frequency of accidents corresponding to each historical maternal and infant medical data based on the historical maternal and infant medical data. It should be noted that the frequency of accidents in the embodiment of the present application is used to indicate the number of occurrences of each risk factor in the maternal and infant group corresponding to a specified disease or a specified event.
[0035] Then, based on the mapping relationship between historical maternal and infant medical data and accident frequency, the accident frequency corresponding to each maternal and infant medical data in the maternal and infant medical insurance product development subject database is determined respectively, and the accident frequency of the maternal and infant medical data is marked.
[0036] In one embodiment, Table 2 is a risk factor table, and the risk factors are shown in Table 2 below: Table 2
[0037] It should be noted that the risk factors in the embodiments of the present application include existing hypertension and gestational hypertension, preeclampsia and eclampsia, threatened abortion, hyperemesis gravidarum, genitourinary tract infection, existing diabetes and gestational diabetes, twin / multiple pregnancy, polyhydramnios / oligohydramnios, placenta previa, anemia, history of cesarean section, previous chronic kidney disease, previous gastrointestinal disease, previous heart disease, previous hemorrhagic disease, uterine fibroids, thyrotoxicosis, asthma and assisted reproduction.
[0038] In the field of maternal and child health care, the frequency of accidents usually refers to the number of times or frequency of a specific disease or adverse event in the maternal and child population. Here, "accident" can be understood as the occurrence of a disease, the appearance of symptoms, or the occurrence of an adverse event. The frequency of accidents is usually obtained by statistically analyzing the relevant records in the data set.
[0039] The corresponding accident frequency is determined by counting all DX (diagnosis) from 36 weeks to 2 weeks before the index date, 2 weeks before and after the index date, and 2-46 weeks after the index date for pregnant women, as well as all DX1 (main diagnosis) from the index date to 52 weeks for newborns.
[0040] In one embodiment of the present application, the server performs data cleaning on the marked maternal and child medical data, including: Count the frequency of missing variables in maternal and child medical data, and delete the maternal and child medical data with missing variables; Identify abnormal maternal and child medical data whose age is not within the specified age range, and abnormal maternal and child medical data whose total cost is not within the specified cost range; Delete maternal and infant medical data with abnormal age and cost, and count the corresponding proportion distribution of the deleted maternal and infant medical data; Determine the maternal and child medical data with abnormal self-payment ratios where the self-payment ratio between the self-payment and the total cost is not within the specified ratio range, so as to determine that the maternal and child medical data with abnormal self-payment ratios are missing self-payment, and calculate the missing ratio distribution; Based on the subject database of maternal and child health insurance products, the mean out-of-pocket expenses were calculated to fill in the missing values of out-of-pocket expenses according to the mean out-of-pocket expenses.
[0041] In one embodiment, the missing frequencies of all variables are first counted, and the maternal and child medical data with missing variables are deleted. Cases with abnormal age and total cost are deleted, and the proportion distribution of the deleted maternal and child medical data is counted. It should be noted that the abnormal age and total cost in the embodiment of the present application refers to: 20<=age<=45, 500<=hospitalization cost<=3000000.
[0042] Mark the cases with abnormal self-payment ratio, determine the cases with abnormal self-payment ratio as missing self-payment, and calculate the proportion distribution of missing self-payment. It should be noted that the self-payment ratio in the embodiment of the present application = self-payment / total cost, and the abnormal self-payment ratio means: self-payment ratio>0.9 or self-payment ratio<0.1.
[0043] The missing values of out-of-pocket expenses are supplemented with the mean, and the mean calculation method of out-of-pocket expenses is: year + city + age group + medical insurance type + total cost classification. It should be noted that the total cost classification in the embodiment of the present application includes 0-20,000, 20,000-50,000 and 50,000+.
[0044] In addition, maternal expenses are segmented according to the number of weeks of gestation, and the expenses for gestational weeks 4, 8, 12, 16, 20, 24, 28, and 32 are included in prenatal expenses.
[0045] Step 103: perform data analysis on the marked and cleaned maternal and infant medical data to evaluate the risk cost indicators of maternal and infant medical insurance products corresponding to the maternal and infant medical data, and generate a corresponding cost analysis report based on the data analysis results.
[0046] Specifically, the server performs data analysis on the marked and cleaned maternal and infant medical data to evaluate the risk cost indicators of maternal and infant medical insurance products corresponding to the maternal and infant medical data, including: Based on the marked and cleaned maternal and child medical data, the claims-related data in the vertical dimension and the claims-related data in the horizontal dimension are determined. It should be noted that the claims-related data in the vertical dimension in the embodiment of the present application include: user type, year, city, age group and medical insurance type, and the claims-related data in the horizontal dimension include: the number of cases, hospitalization expenses and out-of-pocket expenses for each case.
[0047] The server also needs to determine the personal data of the vertical dimension and the personal data of the horizontal dimension. It should be noted that the personal data of the vertical dimension in the embodiment of the present application is the same as the claim-related data of the vertical dimension, and the personal data of the horizontal dimension includes: number of people, average number of hospitalizations per person, average hospitalization expenses per person, average out-of-pocket expenses per person, and incidence of maternal risk factors.
[0048] In one embodiment of the present application, the server generates a corresponding cost analysis report based on the data analysis results, including: Based on the data analysis results, the risk cost indicators of maternal and infant medical insurance products are summarized, and the risk cost indicators after the summary are evaluated. It should be noted that the risk cost indicators in the embodiment of the present application include total expenses, out-of-pocket expenses and compensation ratio.
[0049] According to the risk cost assessment result, the user information corresponding to the high risk cost is determined, and the corresponding cost distribution is determined. It should be noted that the user information in the embodiment of the present application includes user groups, regions and disease types.
[0050] Then, a corresponding cost analysis report is generated, and based on the cost distribution, adjustments are made to the development of maternal and child medical insurance products to reduce the corresponding risk costs.
[0051] In one embodiment, the calculation of the net value of maternal and child health insurance is a comprehensive process involving multiple factors, mainly including the pricing of insurance products, compensation forecasts, cost estimation, market adjustments, etc. Table 3 is a cost statistical analysis report.
[0052] Table 3
[0053] It should be noted that the embodiments of the present application include age range, pregnancy type, social security type, number of people, number of 0 deductible accidents, number of 5000 deductible accidents, number of 10000 deductible accidents, total cost, 0 deductible out-of-pocket expenses, 5000 deductible out-of-pocket expenses and 10000 deductible out-of-pocket expenses.
[0054] Through big data aggregation and analysis technology, this application can collect and process massive amounts of medical data, personal health information, and historical diagnosis and treatment data, and analyze factors such as the disease incidence rate and medical expenses of patients with different diseases, so as to more accurately assess the health status and risk level of pregnant women and newborns. It can significantly improve the accuracy and reliability of risk assessment, and solve the difficulties and defects in areas such as imbalanced health insurance product structure, single product, design and pricing.
[0055] Maternal and infant medical insurance products focus on the health risks of pregnant women and newborns, and provide targeted protection. This targeted design makes the insurance products more accurate in covering risks and can better meet the needs of specific groups of people. In addition, it covers multiple stages from pregnancy to birth, including pregnancy complications, delivery risks, congenital diseases of newborns, and hospitalization. This comprehensive coverage design provides more comprehensive protection for the insured and reduces the worries caused by risks not being covered.
[0056] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, this embodiment of the application also provides a data analysis device for the development of maternal and child medical insurance products, and its structure is as follows: Figure 2 shown.
[0057] Figure 2 This is a schematic diagram of the internal structure of a data analysis device for developing maternal and child medical insurance products provided in an embodiment of the present application. Figure 2 As shown, the device includes: at least one processor 201; and a memory 202 communicatively connected to the at least one processor 201; The memory 202 stores instructions that can be executed by at least one processor 201, and the instructions are executed by at least one processor 201 to enable at least one processor 201 to: Acquire multidimensional medical data through multiple data sources and extract data from the multidimensional medical data to form a subject database for maternal and child medical insurance product development; Mark the maternal and infant medical data in the subject database of maternal and infant medical insurance product development, and clean the marked maternal and infant medical data; Data analysis is performed on the marked and cleaned maternal and infant medical data to evaluate the risk cost indicators of maternal and infant medical insurance products corresponding to the maternal and infant medical data, and based on the data analysis results, a corresponding cost analysis report is generated.
[0058] The present application also provides a non-volatile computer storage medium storing computer executable instructions. When the computer executable instructions are executed, they can: Acquire multidimensional medical data through multiple data sources and extract data from the multidimensional medical data to form a subject database for maternal and child medical insurance product development; Mark the maternal and infant medical data in the subject database of maternal and infant medical insurance product development, and clean the marked maternal and infant medical data; Data analysis is performed on the marked and cleaned maternal and infant medical data to evaluate the risk cost indicators of maternal and infant medical insurance products corresponding to the maternal and infant medical data, and based on the data analysis results, a corresponding cost analysis report is generated.
[0059] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0060] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0061] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.
[0062] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0063] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0064] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0067] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
[0068] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0069] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0070] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. Data analysis methods for the development of maternal and child health insurance products, It is characterized in that The method comprises: Acquire multidimensional medical data through multiple data sources, and extract data from the multidimensional medical data to form a subject database for maternal and child medical insurance product development; Marking the maternal and infant medical data in the maternal and infant medical insurance product development subject database, and performing data cleaning on the marked maternal and infant medical data; Data analysis is performed on the marked and cleaned maternal and infant medical data to evaluate the risk cost indicators of maternal and infant medical insurance products corresponding to the maternal and infant medical data, and a corresponding cost analysis report is generated based on the data analysis results.
2. The data analysis method for developing maternal and infant medical insurance products according to claim 1, It is characterized in that Acquire multi-dimensional medical data through multiple data sources, including: Determine multiple data sources for health and medical data collection, and respectively establish secure data transmission channels between the multiple data sources; Acquire multidimensional medical data from the multiple data sources through the secure data transmission channel, and store the structured and unstructured multidimensional medical data in the data lake based on database underlying aggregation technology and image file aggregation technology; The multi-dimensional medical data at least includes: physiological indicators of pregnant women, prenatal examination results, delivery records, and health conditions and test data of newborns.
3. The data analysis method for developing maternal and infant medical insurance products according to claim 1, It is characterized in that Data is extracted from the multidimensional medical data to form a subject database for maternal and child medical insurance product development, including: Based on a designated diagnosis code, obtaining maternal and child data from the multidimensional medical data; wherein the designated diagnosis code is used to indicate a diagnosis code whose first digit is a designated value; Determine the difference between the admission date and the discharge date of each medical data, and compare the difference with the specified time period; When the difference is less than the specified time length, determining that the user type corresponding to the medical data is a newborn, so as to obtain corresponding newborn data in the multidimensional medical data; The maternal and infant medical data corresponding to the maternal data and the newborn data are determined, and a maternal and infant medical insurance product development subject database corresponding to the maternal and infant medical data is formed.
4. The data analysis method for developing maternal and infant medical insurance products according to claim 1, It is characterized in that Marking the maternal and infant medical data in the maternal and infant medical insurance product development subject database includes: Based on the production-related codes and production-related operation codes, the data of pregnant women are determined in the subject database of the development of maternal and child medical insurance products, and the corresponding production date is determined according to the hospitalization date in the data of pregnant women; The maternal delivery date is used as the maternal index date, and the newborn's birth date is used as the newborn's index date to mark the index date in maternal and child medical data.
5. The data analysis method for developing maternal and infant medical insurance products according to claim 1, It is characterized in that Marking the maternal and infant medical data in the maternal and infant medical insurance product development subject database includes: In the subject database of maternal and infant medical insurance product development, risk factors related to maternal and infant health are queried, and risk factors in maternal and infant medical data are marked; wherein the risk factors at least include: pre-existing hypertension and gestational hypertension, preeclampsia and eclampsia, threatened abortion and hyperemesis gravidarum; Obtain historical maternal and infant medical data within a preset time period, and determine the risk frequency corresponding to each historical maternal and infant medical data based on the historical maternal and infant medical data; wherein the risk frequency is used to indicate the number of occurrences of a specified disease or a specified event corresponding to each risk factor in the maternal and infant group; Based on the mapping relationship between historical maternal and infant medical data and accident frequency, the accident frequency corresponding to each maternal and infant medical data in the maternal and infant medical insurance product development subject database is determined respectively, and the accident frequency of the maternal and infant medical data is marked.
6. The data analysis method for developing maternal and infant medical insurance products according to claim 1, It is characterized in that The marked maternal and infant medical data is cleaned, including: Count the frequency of missing variables in maternal and child medical data, and delete the maternal and child medical data with missing variables; Identify abnormal maternal and child medical data whose age is not within the specified age range, and abnormal maternal and child medical data whose total cost is not within the specified cost range; Delete maternal and infant medical data with abnormal age and cost, and count the corresponding proportion distribution of the deleted maternal and infant medical data; Determine the maternal and child medical data with abnormal self-payment ratios where the self-payment ratio between the self-payment and the total cost is not within the specified ratio range, so as to determine that the maternal and child medical data with abnormal self-payment ratios are missing self-payment, and calculate the missing ratio distribution; Based on the maternal and infant medical insurance product development subject database, the mean value of out-of-pocket expenses is calculated to fill in the missing values of out-of-pocket expenses according to the mean value of out-of-pocket expenses.
7. The data analysis method for developing maternal and infant medical insurance products according to claim 1, It is characterized in that Performing data analysis on the marked and cleaned maternal and infant medical data to evaluate the risk cost index of the maternal and infant medical insurance product corresponding to the maternal and infant medical data, including: Based on the marked and cleaned maternal and child medical data, determine the claims-related data in the vertical dimension and the claims-related data in the horizontal dimension; wherein the claims-related data in the vertical dimension include: user type, year, city, age group and medical insurance type, and the claims-related data in the horizontal dimension include: the number of cases, hospitalization expenses and out-of-pocket expenses for each case; Determine personal data in the vertical dimension and personal data in the horizontal dimension; among them, the personal data in the vertical dimension are the same as the claims-related data in the vertical dimension, and the personal data in the horizontal dimension include: number of people, average number of hospitalizations per person, average hospitalization expenses per person, average out-of-pocket expenses per person, and incidence of maternal risk factors.
8. The data analysis method for developing maternal and infant medical insurance products according to claim 1, It is characterized in that Based on the data analysis results, generate the corresponding cost analysis report, including: Based on the data analysis results, the risk cost indicators of maternal and infant medical insurance products are summarized, and an evaluation is performed based on the summarized risk cost indicators; wherein the risk cost indicators include total expenses, out-of-pocket expenses and compensation ratio; According to the risk cost assessment results, determine the user information corresponding to the high risk cost and determine the corresponding cost distribution; wherein the user information includes user group, region and disease type; Generate a corresponding cost analysis report, and based on the cost distribution, adjust the development of maternal and child medical insurance products to reduce the corresponding risk costs.
9. Data analysis equipment for the development of maternal and child health insurance products, It is characterized in that The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data analysis method for developing maternal and child medical insurance products as described in any one of claims 1-8.
10. A non-volatile computer storage medium storing computer executable instructions, It is characterized in that When the computer executable instructions are executed, the data analysis method for developing maternal and child medical insurance products as described in any one of claims 1 to 8 is implemented.
Citation Information
Patent Citations
Mother-and-baby all-life-cycle health medical service system based on artificial intelligence
CN110136794A
Insurance user evaluation method and device, electronic equipment and computer readable medium
CN111180065A
Intelligent accurate maternal and infant health management information platform
CN113948194A
Insurance pricing method based on electronic medical record data feature selection
CN114612255A
Medical insurance premium analysis method and device, equipment and storage medium
CN116894735A
