Big data-based medical artificial intelligence (AI) management method and system, and medium

Abstract

Disclosed in the present invention are a big data-based medical artificial intelligence (AI) management method and system, and a medium. The method comprises: monitoring data of a medical institution, acquiring data storage volume and increment information, and determining an information storage system construction plan; constructing an information storage system for the target medical institution on the basis of the plan; periodically acquiring diagnostic data by means of the system, analyzing the data by means of an AI algorithm, and predicting case progression trends; and performing disease epidemic analysis on the basis of the case progression trends, to assess an epidemic outbreak risk, and determining a response plan. The method effectively improves the management and analysis efficiency of medical data, helps medical institutions identify and respond to disease risks in advance, and improves public health safety.

Description

A big data-based intelligent AI management method, system, and medium for healthcare. Technical Field

[0001] This invention relates to the field of medical management technology, and in particular to a medical intelligent AI management method and system based on big data. Background Technology

[0002] With advancements in medical technology and rapid development in information technology, medical institutions have generated and accumulated vast amounts of medical data. This data includes patient diagnostic information, treatment records, and medical records, characterized by its large scale, diverse types, and rapid growth rate. This medical data is of significant value for disease analysis, disease prediction, and public health monitoring. However, traditional medical data management methods often fail to effectively handle this large-scale and diverse data, resulting in low efficiency in the storage, analysis, and utilization of medical data.

[0003] In current technologies, many medical institutions rely on manual data analysis and processing, which is not only time-consuming and labor-intensive but also prone to errors and omissions. Furthermore, faced with complex and ever-changing disease trends, traditional methods struggle to provide timely early warnings and effective responses to disease outbreaks, making it difficult to predict and control public health risks.

[0004] In recent years, the application of big data and artificial intelligence technologies in the medical field has been gradually increasing. Big data technology can efficiently process and store massive amounts of data, while artificial intelligence algorithms can extract valuable information from this data to predict and analyze disease development trends. By applying big data and artificial intelligence technologies to medical data management, the efficiency of medical data processing and analysis can be significantly improved, enhancing the accuracy and timeliness of disease prediction.

[0005] This invention proposes a big data-based intelligent AI management method for healthcare. By establishing an efficient information storage system and utilizing artificial intelligence algorithms to analyze and predict medical data, it helps medical institutions achieve real-time monitoring and risk warning of disease prevalence, effectively improving public health response capabilities. This method not only improves the efficiency of medical data management but also provides a scientific basis for disease prevention and control, which is of great significance for safeguarding public health. Summary of the Invention

[0006] To address at least one of the aforementioned technical problems, this invention proposes a medical intelligent AI management method and system based on big data.

[0007] The first aspect of this invention provides a medical intelligent AI management method based on big data, comprising:

[0008] Monitor the medical data of the target medical institution, obtain the data storage scale information and data increment information of the target medical institution, and determine the information storage system construction scheme of the target institution based on the data storage scale information and data increment information;

[0009] Construct an information storage system for the target medical institution based on big data technology and the aforementioned information storage system construction scheme;

[0010] The information storage system acquires diagnostic data of patients visiting the target medical institution at a preset time period, and analyzes the diagnostic data using artificial intelligence algorithms to predict the case development trend of the target medical institution.

[0011] Based on the development trend of the cases, an epidemiological analysis of the disease was conducted to determine the risk of disease outbreaks and obtain disease epidemic risk data.

[0012] Based on the aforementioned disease epidemic risk data, determine the disease epidemic response plan for the target medical institution.

[0013] In this solution, the monitoring of medical data of the target medical institution to obtain data storage scale information and data increment information of the target medical institution, and the determination of the information storage system construction scheme of the target institution based on the data storage scale information and data increment information, specifically includes:

[0014] Historical medical data is obtained from the computer of the target medical institution, including electronic health records, laboratory test data, medical imaging data, patient monitoring data, and diagnosis and treatment data.

[0015] The total data volume of the target medical institution is evaluated based on the historical medical data to obtain the data scale information of the target medical institution. The data scale information includes the total data volume, the total data volume of each medical data item, and the data volume ratio of each medical data item.

[0016] Based on the data flow monitoring platform, the medical data of the target medical institution is monitored, and monitoring channels for different medical data items are constructed. Each medical data item is monitored in real time according to the monitoring channels, and the data generation rate and increment of each monitoring channel are recorded to obtain data increment information.

[0017] Based on the data increment information, identify the peak period of data generation and assess the maximum data growth during the peak period;

[0018] Based on the incremental data information and historical medical data, analyze the data growth trend of each medical data item and predict the future data growth.

[0019] Obtain the data access frequency information for each medical data item, set a data access frequency threshold, and divide the medical data of the target medical institution into hot data, warm data, and cold data according to the data access frequency threshold to obtain data access heat information.

[0020] Obtain the required retention time for each medical data item in the target medical institution, and determine the storage device type for each medical data item in the target medical institution based on the data access popularity information. The storage device type includes SSD, HDD, and cloud storage.

[0021] The storage capacity of each type of storage device is determined based on the target medical institution's data scale, data increment, future data growth, and required retention time for medical data.

[0022] The data processor performance requirements of the target medical institution's data storage system are determined based on the maximum data growth and data access frequency information during the peak period.

[0023] The construction scheme of the information storage system of the target medical institution is determined based on the type of storage device, the storage throughput of the storage device type, and the performance requirements of the data processor.

[0024] In this solution, the construction of the target medical institution's information storage system based on big data technology and the aforementioned information storage system construction scheme specifically includes:

[0025] Based on the aforementioned information storage system construction scheme, construct the hardware storage system for the target medical institution;

[0026] A distributed file system for the target medical institution is constructed based on big data technology. Data partitions are constructed in the distributed file system according to medical data items to obtain medical data item storage partitions.

[0027] The storage device type corresponding to each medical data item of the target medical institution is obtained from the information storage system construction plan. Based on the storage device type corresponding to each medical data item, the storage device type corresponding to each medical data item partition is determined. A mapping relationship is constructed between the medical data item storage partition and the corresponding storage device type to obtain the storage partition-device type mapping table.

[0028] Obtain the data update requirements for each medical data item of the target medical institution, and determine the data update cycle for each medical data item based on the data update requirements;

[0029] Based on the storage partition-device type mapping table and the data update cycle, a real-time data acquisition tool is configured. The real-time data acquisition tool collects data for each medical data item in the target medical institution and saves it to the corresponding storage device and storage partition according to the data update cycle, forming a complete information storage system for the target medical institution.

[0030] In this solution, the step of acquiring diagnostic data of patients visiting the target medical institution according to a preset time period using the information storage system, and analyzing the diagnostic data using artificial intelligence algorithms to predict the case development trend of the target medical institution, specifically involves:

[0031] The information storage system acquires diagnostic data of patients visiting the target medical institution according to a preset time period, and extracts disease type information of the patients based on the diagnostic data.

[0032] Based on the disease type information of the patients, the number of cases of different disease types in the target medical institutions in each time period is statistically analyzed. The number of cases of different disease types in the target medical institutions in each time period is plotted as a case number change curve to obtain a case number change curve dataset. Each curve in the case number change curve dataset is divided into a training set and a test set according to the preset time length proportion.

[0033] A case number change prediction model was constructed based on the ARIMA algorithm. The case number change curve dataset was analyzed by the autocorrelation function of the time series to determine the autoregression order, difference order, and moving average order of the prediction model.

[0034] Configure the parameters of the case number change prediction model according to the autoregression order, difference order, and moving average order. Import the training set into the case number change prediction model for fitting and training. Import the test set into the prediction model for prediction effect evaluation. When the prediction effect is less than the preset effect, adjust the model parameters until the prediction effect is not less than the preset effect.

[0035] The number of cases changing over a preset time period is obtained and imported into the case number change prediction model to predict the number of cases of different disease types in the target medical institution in the future preset time period, and the prediction results are obtained.

[0036] The prediction results are plotted as a dataset of predicted case number change curves, and the case development trend of different disease types is determined based on the dataset of predicted case number change curves.

[0037] In this plan, the step of conducting disease epidemiology analysis based on the development trend of the cases to determine the risk of disease outbreaks and obtain disease epidemiology risk data specifically involves:

[0038] Obtain data on the rate of increase in cases to assess the prevalence of disease, and determine the rate of increase in cases of different disease types at each point in time in the target medical institution in the future based on the case development trend, thereby obtaining case growth rate data;

[0039] By comparing the case growth rate data with the case growth rate index data, the Euclidean distance between the case growth rate data and the case growth rate index data is calculated, and the risk of the epidemic occurrence of different disease types at each time point in the future is assessed based on the Euclidean distance.

[0040] A first risk threshold and a second risk threshold are preset. Diseases with an epidemic occurrence risk greater than the first risk threshold are marked as high-risk epidemic diseases, diseases with an epidemic occurrence risk between the first and second risk thresholds are marked as medium-risk epidemic diseases, and diseases with an epidemic occurrence risk less than the second risk threshold are marked as low-risk epidemic diseases, thus obtaining disease epidemic risk data.

[0041] In this plan, determining the disease epidemic response plan for the target medical institution based on the disease epidemic risk data specifically includes:

[0042] Based on the disease epidemic risk data, identify high-risk epidemic disease types, and obtain the drugs and medical equipment required for the treatment of the high-risk epidemic disease types to obtain treatment material information;

[0043] The number of cases of the high-risk epidemic disease type is determined based on the case development trend, and the required amount of treatment materials is determined based on the number of cases.

[0044] Based on the information on treatment supplies and the demand for treatment supplies, the target medical institution is stockpiled of treatment supplies in advance, thereby obtaining a disease outbreak response plan for the target medical institution.

[0045] A second aspect of the present invention also provides a medical intelligent AI management system based on big data. The system includes a memory and a processor. The memory includes a medical intelligent AI management method program based on big data. When the processor executes the medical intelligent AI management method program based on big data, it performs the following steps:

[0046] Monitor the medical data of the target medical institution, obtain the data storage scale information and data increment information of the target medical institution, and determine the information storage system construction scheme of the target institution based on the data storage scale information and data increment information;

[0047] Construct an information storage system for the target medical institution based on big data technology and the aforementioned information storage system construction scheme;

[0048] The information storage system acquires diagnostic data of patients visiting the target medical institution at a preset time period, and analyzes the diagnostic data using artificial intelligence algorithms to predict the case development trend of the target medical institution.

[0049] Based on the development trend of the cases, an epidemiological analysis of the disease was conducted to determine the risk of disease outbreaks and obtain disease epidemic risk data.

[0050] Based on the aforementioned disease epidemic risk data, determine the disease epidemic response plan for the target medical institution.

[0051] In this plan, the step of conducting disease epidemiology analysis based on the development trend of the cases to determine the risk of disease outbreaks and obtain disease epidemiology risk data specifically involves:

[0052] Obtain data on the rate of increase in cases to assess the prevalence of disease, and determine the rate of increase in cases of different disease types at each point in time in the target medical institution in the future based on the case development trend, thereby obtaining case growth rate data;

[0053] By comparing the case growth rate data with the case growth rate index data, the Euclidean distance between the case growth rate data and the case growth rate index data is calculated, and the risk of the epidemic occurrence of different disease types at each time point in the future is assessed based on the Euclidean distance.

[0054] A first risk threshold and a second risk threshold are preset. Diseases with an epidemic occurrence risk greater than the first risk threshold are marked as high-risk epidemic diseases, diseases with an epidemic occurrence risk between the first and second risk thresholds are marked as medium-risk epidemic diseases, and diseases with an epidemic occurrence risk less than the second risk threshold are marked as low-risk epidemic diseases, thus obtaining disease epidemic risk data.

[0055] In this plan, determining the disease epidemic response plan for the target medical institution based on the disease epidemic risk data specifically includes:

[0056] Based on the disease epidemic risk data, identify high-risk epidemic disease types, and obtain the drugs and medical equipment required for the treatment of the high-risk epidemic disease types to obtain treatment material information;

[0057] The number of cases of the high-risk epidemic disease type is determined based on the case development trend, and the required amount of treatment materials is determined based on the number of cases.

[0058] Based on the information on treatment supplies and the demand for treatment supplies, the target medical institution is stockpiled of treatment supplies in advance, thereby obtaining a disease outbreak response plan for the target medical institution.

[0059] A third aspect of the present invention also provides a computer-readable storage medium comprising a big data-based medical intelligent AI management program, wherein when the big data-based medical intelligent AI management program is executed by a processor, it implements the steps of the big data-based medical intelligent AI management method as described in any of the preceding claims.

[0060] This invention discloses a big data-based intelligent AI management method, system, and medium for healthcare. The method includes monitoring data from healthcare institutions, acquiring data storage scale and incremental information, determining an information storage system construction scheme, and constructing an information storage system for the target healthcare institution based on this scheme. The system periodically acquires diagnostic data and analyzes this data using artificial intelligence algorithms to predict case development trends. Furthermore, it performs disease epidemiology analysis based on case development trends, assesses the risk of epidemic occurrence, and determines response strategies. This method effectively improves the efficiency of healthcare data management and analysis, helps healthcare institutions identify and respond to disease risks in advance, and enhances public health security. Attached Figure Description

[0061] Figure 1 shows a flowchart of a medical intelligent AI management method based on big data according to the present invention;

[0062] Figure 2 shows a flowchart of the process for obtaining disease epidemic risk data according to the present invention;

[0063] Figure 3 shows a flowchart of the present invention for determining the disease epidemic response plan of the target medical institution;

[0064] Figure 4 shows a block diagram of a big data-based medical intelligent AI management system according to the present invention. Detailed Implementation

[0065] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0066] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0067] Figure 1 shows a flowchart of a big data-based intelligent AI management method for healthcare according to the present invention.

[0068] As shown in Figure 1, the first aspect of the present invention provides a medical intelligent AI management method based on big data, comprising:

[0069] S102, monitor the medical data of the target medical institution, obtain the data storage scale information and data increment information of the target medical institution, and determine the information storage system construction scheme of the target institution based on the data storage scale information and data increment information;

[0070] S104, Construct an information storage system for the target medical institution based on big data technology and the aforementioned information storage system construction scheme;

[0071] S106, according to the information storage system, the diagnostic data information of patients visiting the target medical institution is obtained according to a preset time period, and the diagnostic data information is analyzed according to the artificial intelligence algorithm to predict the case development trend of the target medical institution;

[0072] S108, Based on the development trend of the cases, conduct disease epidemic analysis to determine the risk of disease epidemic occurrence and obtain disease epidemic risk data;

[0073] S110, Determine the disease epidemic response plan for the target medical institution based on the aforementioned disease epidemic risk data.

[0074] It should be noted that monitoring the medical data of target medical institutions to obtain their data storage scale and incremental information, and determining the construction scheme of the information storage system accordingly, allows for accurate assessment of the data storage needs of medical institutions by monitoring the data storage scale and incremental information, avoiding waste or inadequacy of system resources. Customized storage solutions reduce unnecessary hardware and software investment, lower operating costs, and improve resource utilization. Based on big data technology and the previously determined information storage system construction scheme, the information storage system of the target medical institutions is built. Utilizing big data technology, an efficient information storage system is constructed, improving data processing and query speed and reducing data access time. Disease epidemiology analysis is conducted through artificial algorithms. By predicting disease development trends, potential epidemic risks can be identified in advance, providing early warning information to public health departments. Timely epidemiology analysis and prediction help formulate effective prevention and control measures to reduce the spread and diffusion of diseases. Based on disease epidemiology risk data, disease epidemiology response plans are formulated for target medical institutions. Developing response plans in advance enables medical institutions to react quickly in the event of a disease outbreak, reducing negative social and economic impacts. The target medical institutions include hospitals, clinics, and community health service centers.

[0075] According to an embodiment of the present invention, the step of monitoring the medical data of the target medical institution, obtaining data storage scale information and data increment information of the target medical institution, and determining the information storage system construction scheme of the target institution based on the data storage scale information and data increment information, specifically includes:

[0076] Historical medical data is obtained from the computer of the target medical institution, including electronic health records, laboratory test data, medical imaging data, patient monitoring data, and diagnosis and treatment data.

[0077] The total data volume of the target medical institution is evaluated based on the historical medical data to obtain the data scale information of the target medical institution. The data scale information includes the total data volume, the total data volume of each medical data item, and the data volume ratio of each medical data item.

[0078] Based on the data flow monitoring platform, the medical data of the target medical institution is monitored, and monitoring channels for different medical data items are constructed. Each medical data item is monitored in real time according to the monitoring channels, and the data generation rate and increment of each monitoring channel are recorded to obtain data increment information.

[0079] Based on the data increment information, identify the peak period of data generation and assess the maximum data growth during the peak period;

[0080] Based on the incremental data information and historical medical data, analyze the data growth trend of each medical data item and predict the future data growth.

[0081] Obtain the data access frequency information for each medical data item, set a data access frequency threshold, and divide the medical data of the target medical institution into hot data, warm data, and cold data according to the data access frequency threshold to obtain data access heat information.

[0082] Obtain the required retention time for each medical data item in the target medical institution, and determine the storage device type for each medical data item in the target medical institution based on the data access popularity information. The storage device type includes SSD, HDD, and cloud storage.

[0083] The storage capacity of each type of storage device is determined based on the target medical institution's data scale, data increment, future data growth, and required retention time for medical data.

[0084] The data processor performance requirements of the target medical institution's data storage system are determined based on the maximum data growth and data access frequency information during the peak period.

[0085] The construction scheme of the information storage system of the target medical institution is determined based on the type of storage device, the storage throughput of the storage device type, and the performance requirements of the data processor.

[0086] It should be noted that by analyzing the access frequency of each medical data item in the target medical institution, data access frequency information is determined. Storage devices are then selected based on the access frequency of different data. Hot data is preferentially stored on high-speed storage devices to improve data access speed, while cold data is stored on lower-cost storage media to reduce storage costs and optimize storage resource utilization. Hot data refers to frequently accessed data, such as real-time monitoring data and active electronic health records; warm data refers to data with medium access frequency, such as recent medical images and diagnostic reports; and cold data refers to data with low access frequency, such as historical data and archived files. HDD (Hard Disk Drive) advantages: large capacity, low cost, suitable for warm data storage. Disadvantages: slower access speed, unsuitable for high-frequency access data. SSD (Solid State Drive) advantages: fast read and write speeds, suitable for high-frequency access hot data storage. Disadvantages: higher cost, suitable for data with relatively small storage capacity requirements. Cloud storage advantages: high flexibility, on-demand expansion, suitable for cold data storage, and supports remote access. Disadvantages: Long-term costs may be high, data transmission latency is greater than local storage, and it relies on network connectivity. Based on the type of storage device, storage throughput, and data processor performance requirements of the target medical institution's information storage system, a final information storage system construction plan is determined. A rationally constructed information storage system improves data management capabilities, ensuring efficient data storage, management, and utilization. The plan considers future data growth needs and storage expansion requirements, ensuring the system can flexibly respond to future changes. The data processor performance requirements include data read and write speeds and data access volume processing capabilities. The medical data items include electronic health records, laboratory test data, medical imaging data, patient monitoring data, and diagnostic and treatment data.

[0087] According to an embodiment of the present invention, the construction of the information storage system for the target medical institution based on big data technology and the information storage system construction scheme specifically includes:

[0088] Based on the aforementioned information storage system construction scheme, construct the hardware storage system for the target medical institution;

[0089] A distributed file system for the target medical institution is constructed based on big data technology. Data partitions are constructed in the distributed file system according to medical data items to obtain medical data item storage partitions.

[0090] The storage device type corresponding to each medical data item of the target medical institution is obtained from the information storage system construction plan. Based on the storage device type corresponding to each medical data item, the storage device type corresponding to each medical data item partition is determined. A mapping relationship is constructed between the medical data item storage partition and the corresponding storage device type to obtain the storage partition-device type mapping table.

[0091] Obtain the data update requirements for each medical data item of the target medical institution, and determine the data update cycle for each medical data item based on the data update requirements;

[0092] Based on the storage partition-device type mapping table and the data update cycle, a real-time data acquisition tool is configured. The real-time data acquisition tool collects data for each medical data item in the target medical institution and saves it to the corresponding storage device and storage partition according to the data update cycle, forming a complete information storage system for the target medical institution.

[0093] It should be noted that, according to the information storage system construction scheme, an efficient and stable hardware storage system is built to ensure the secure storage and rapid access of medical data; the distributed file system supports the storage and management of large-scale data, improving data management efficiency and reliability; by partitioning the data, the orderliness and manageability of data storage are ensured, facilitating rapid data retrieval and access; the distributed system can effectively allocate and balance data load, improving the overall performance and stability of the system; the mapping relationship allows data to be flexibly stored on different devices according to access frequency and importance, reducing waste of high-performance devices and lowering overall storage costs; by reasonably setting the data update cycle, system resource consumption is reduced, improving the operating efficiency and data processing capabilities of the storage system; by configuring acquisition tools, automatic data acquisition and storage are achieved, reducing manual operation, reducing human error, and improving data management efficiency; the data partitioning according to medical data items enables medical data items to be stored in the corresponding partitions; the storage partition-device type mapping table can accurately store different medical data items of the target medical institution in the corresponding storage devices; the real-time data acquisition tools include Flume and Kafka.

[0094] According to an embodiment of the present invention, the step of acquiring diagnostic data information of patients visiting the target medical institution according to the information storage system at a preset time period, and analyzing the diagnostic data information according to an artificial intelligence algorithm to predict the case development trend of the target medical institution specifically includes:

[0095] The information storage system acquires diagnostic data of patients visiting the target medical institution according to a preset time period, and extracts disease type information of the patients based on the diagnostic data.

[0096] Based on the disease type information of the patients, the number of cases of different disease types in the target medical institutions in each time period is statistically analyzed. The number of cases of different disease types in the target medical institutions in each time period is plotted as a case number change curve to obtain a case number change curve dataset. Each curve in the case number change curve dataset is divided into a training set and a test set according to the preset time length proportion.

[0097] A case number change prediction model was constructed based on the ARIMA algorithm. The case number change curve dataset was analyzed by the autocorrelation function of the time series to determine the autoregression order, difference order, and moving average order of the prediction model.

[0098] Configure the parameters of the case number change prediction model according to the autoregression order, difference order, and moving average order. Import the training set into the case number change prediction model for fitting and training. Import the test set into the prediction model for prediction effect evaluation. When the prediction effect is less than the preset effect, adjust the model parameters until the prediction effect is not less than the preset effect.

[0099] The number of cases changing over a preset time period is obtained and imported into the case number change prediction model to predict the number of cases of different disease types in the target medical institution in the future preset time period, and the prediction results are obtained.

[0100] The prediction results are plotted as a dataset of predicted case number change curves, and the case development trend of different disease types is determined based on the dataset of predicted case number change curves.

[0101] It should be noted that by comprehensively acquiring and analyzing medical data through big data technology and artificial intelligence algorithms, an effective model for predicting changes in the number of cases has been constructed. By periodically statistically analyzing and predicting the number of cases of different disease types, a precise grasp of future case development trends has been achieved. The preset time period is days. The ARIMA (Autoregressive Integral Moving Average) model is an artificial intelligence algorithm used for time series data analysis and statistics. It performs data modeling and prediction by capturing data trends.

[0102] Figure 2 shows a flowchart of the process for obtaining disease epidemic risk data according to the present invention.

[0103] According to an embodiment of the present invention, the step of performing disease epidemiology analysis based on the case development trend to determine the risk of disease epidemic occurrence and obtain disease epidemiology risk data specifically includes:

[0104] S202, Obtain case growth rate index data to assess the prevalence of disease, and determine the case growth rate of different disease types in the target medical institution at each time point in the future period based on the case development trend, and obtain case growth rate data;

[0105] S204, Based on the comparison between the case growth rate data and the case growth rate index data, calculate the Euclidean distance between the case growth rate data and the case growth rate index data, and assess the risk of the epidemic occurrence of different disease types at each time point in the future preset time based on the Euclidean distance.

[0106] S206, preset a first risk threshold and a second risk threshold, mark diseases with an epidemic occurrence risk greater than the first risk threshold as high-risk epidemic diseases, mark diseases with an epidemic occurrence risk between the first and second risk thresholds as medium-risk epidemic diseases, and mark diseases with an epidemic occurrence risk less than the second risk threshold as low-risk epidemic diseases, thereby obtaining disease epidemic risk data.

[0107] It should be noted that by calculating the distance between the rate of increase in cases and the indicator data, the epidemic risk of different diseases in the future can be accurately assessed. Based on the preset risk threshold, the epidemic risk of diseases can be clearly classified, which helps health departments and medical institutions to formulate targeted prevention and control measures, rationally allocate medical resources according to the risk level of the disease, ensure that high-risk diseases are given priority treatment, and improve the utilization efficiency of medical resources.

[0108] Figure 3 shows a flowchart of the present invention for determining the disease epidemic response plan for target medical institutions.

[0109] According to an embodiment of the present invention, determining the disease epidemic response plan for the target medical institution based on the disease epidemic risk data specifically includes:

[0110] S302, based on the disease epidemic risk data, obtain the types of high-risk epidemic diseases, and obtain the drugs and medical equipment required for the treatment of the high-risk epidemic diseases, thereby obtaining treatment material information;

[0111] S304, determine the number of cases of the high-risk epidemic disease type based on the case development trend, and determine the demand for treatment materials based on the number of cases.

[0112] S306, Based on the information on treatment supplies and the demand for treatment supplies, advance reserves of treatment supplies are made for the target medical institution to obtain a disease outbreak response plan for the target medical institution.

[0113] It should be noted that accurately identifying the types of high-risk infectious diseases faced by medical institutions helps to focus on and prepare corresponding response measures; by predicting demand, optimizing the supply chain management of medical supplies can ensure that sufficient treatment materials can be supplied in a timely manner when needed, thereby improving the ability to respond to sudden outbreaks or disease outbreaks; and by stockpiling treatment materials in advance, it can ensure a rapid response and the implementation of emergency treatment work during the peak of disease epidemics.

[0114] According to embodiments of the invention, it also includes:

[0115] Real-time monitoring of the usage data of treatment supplies in the disease epidemic response plan; and determination of the consumption rate of supplies based on the usage data.

[0116] Establish a dynamic inventory management system for the target medical institution to monitor the inventory level of treatment supplies in the target medical institution in real time, and determine the replenishment cycle of each treatment supply based on the consumption rate and the inventory level of treatment supplies.

[0117] Acquire data on the urgency, frequency of use, and supply time of each type of treatment material. Perform linear programming analysis on the urgency, frequency of use, supply time, and replenishment cycle of the treatment materials to determine the procurement time of each type of treatment material.

[0118] The allocation of each type of treatment material to the target medical institution is based on the aforementioned delivery time.

[0119] It is important to note that in medical institutions, the demand for treatment supplies increases dramatically during disease outbreaks, making the rapid consumption and replenishment of these supplies a critical issue in responding to epidemics. However, traditional supply management methods often lack the ability to monitor and dynamically adjust in real time, leading to instability in the supply supply chain and potential shortages or overstocking. Therefore, establishing a dynamic inventory management system for target medical institutions is crucial. This system determines the replenishment cycle of treatment supplies and uses linear programming algorithms to plan based on the urgency, usage frequency, and supply time data of each treatment supply. This determines the turnover time for each supply and ultimately identifies the optimal time for procurement in advance. Through scientific optimization of procurement time and resource allocation, emergency response time can be shortened, ensuring that supplies reach where they are needed in a timely manner. By integrating supply time data and optimizing procurement plans, the stability and continuity of the supply supply chain can be ensured.

[0120] Figure 4 shows a block diagram of a big data-based medical intelligent AI management system according to the present invention.

[0121] A second aspect of the present invention also provides a medical intelligent AI management system 4 based on big data. The system includes a memory 41 and a processor 42. The memory includes a medical intelligent AI management method program based on big data. When the processor executes the medical intelligent AI management method program based on big data, it performs the following steps:

[0122] Monitor the medical data of the target medical institution, obtain the data storage scale information and data increment information of the target medical institution, and determine the information storage system construction scheme of the target institution based on the data storage scale information and data increment information;

[0123] Construct an information storage system for the target medical institution based on big data technology and the aforementioned information storage system construction scheme;

[0124] The information storage system acquires diagnostic data of patients visiting the target medical institution at a preset time period, and analyzes the diagnostic data using artificial intelligence algorithms to predict the case development trend of the target medical institution.

[0125] Based on the development trend of the cases, an epidemiological analysis of the disease was conducted to determine the risk of disease outbreaks and obtain disease epidemic risk data.

[0126] Based on the aforementioned disease epidemic risk data, determine the disease epidemic response plan for the target medical institution.

[0127] According to an embodiment of the present invention, the step of monitoring the medical data of the target medical institution, obtaining data storage scale information and data increment information of the target medical institution, and determining the information storage system construction scheme of the target institution based on the data storage scale information and data increment information, specifically includes:

[0128] Historical medical data is obtained from the computer of the target medical institution, including electronic health records, laboratory test data, medical imaging data, patient monitoring data, and diagnosis and treatment data.

[0129] The total data volume of the target medical institution is evaluated based on the historical medical data to obtain the data scale information of the target medical institution. The data scale information includes the total data volume, the total data volume of each medical data item, and the data volume ratio of each medical data item.

[0130] Based on the data flow monitoring platform, the medical data of the target medical institution is monitored, and monitoring channels for different medical data items are constructed. Each medical data item is monitored in real time according to the monitoring channels, and the data generation rate and increment of each monitoring channel are recorded to obtain data increment information.

[0131] Based on the data increment information, identify the peak period of data generation and assess the maximum data growth during the peak period;

[0132] Based on the incremental data information and historical medical data, analyze the data growth trend of each medical data item and predict the future data growth.

[0133] Obtain the data access frequency information for each medical data item, set a data access frequency threshold, and divide the medical data of the target medical institution into hot data, warm data, and cold data according to the data access frequency threshold to obtain data access heat information.

[0134] Obtain the required retention time for each medical data item in the target medical institution, and determine the storage device type for each medical data item in the target medical institution based on the data access popularity information. The storage device type includes SSD, HDD, and cloud storage.

[0135] The storage capacity of each type of storage device is determined based on the target medical institution's data scale, data increment, future data growth, and required retention time for medical data.

[0136] The data processor performance requirements of the target medical institution's data storage system are determined based on the maximum data growth and data access frequency information during the peak period.

[0137] The construction scheme of the information storage system of the target medical institution is determined based on the type of storage device, the storage throughput of the storage device type, and the performance requirements of the data processor.

[0138] According to an embodiment of the present invention, the construction of the information storage system for the target medical institution based on big data technology and the information storage system construction scheme specifically includes:

[0139] Based on the aforementioned information storage system construction scheme, construct the hardware storage system for the target medical institution;

[0140] A distributed file system for the target medical institution is constructed based on big data technology. Data partitions are constructed in the distributed file system according to medical data items to obtain medical data item storage partitions.

[0141] The storage device type corresponding to each medical data item of the target medical institution is obtained from the information storage system construction plan. Based on the storage device type corresponding to each medical data item, the storage device type corresponding to each medical data item partition is determined. A mapping relationship is constructed between the medical data item storage partition and the corresponding storage device type to obtain the storage partition-device type mapping table.

[0142] Obtain the data update requirements for each medical data item of the target medical institution, and determine the data update cycle for each medical data item based on the data update requirements;

[0143] Based on the storage partition-device type mapping table and the data update cycle, a real-time data acquisition tool is configured. The real-time data acquisition tool collects data for each medical data item in the target medical institution and saves it to the corresponding storage device and storage partition according to the data update cycle, forming a complete information storage system for the target medical institution.

[0144] According to an embodiment of the present invention, the step of acquiring diagnostic data information of patients visiting the target medical institution according to the information storage system at a preset time period, and analyzing the diagnostic data information according to an artificial intelligence algorithm to predict the case development trend of the target medical institution specifically includes:

[0145] The information storage system acquires diagnostic data of patients visiting the target medical institution according to a preset time period, and extracts disease type information of the patients based on the diagnostic data.

[0146] Based on the disease type information of the patients, the number of cases of different disease types in the target medical institutions in each time period is statistically analyzed. The number of cases of different disease types in the target medical institutions in each time period is plotted as a case number change curve to obtain a case number change curve dataset. Each curve in the case number change curve dataset is divided into a training set and a test set according to the preset time length proportion.

[0147] A case number change prediction model was constructed based on the ARIMA algorithm. The case number change curve dataset was analyzed by the autocorrelation function of the time series to determine the autoregression order, difference order, and moving average order of the prediction model.

[0148] Configure the parameters of the case number change prediction model according to the autoregression order, difference order, and moving average order. Import the training set into the case number change prediction model for fitting and training. Import the test set into the prediction model for prediction effect evaluation. When the prediction effect is less than the preset effect, adjust the model parameters until the prediction effect is not less than the preset effect.

[0149] The number of cases changing over a preset time period is obtained and imported into the case number change prediction model to predict the number of cases of different disease types in the target medical institution in the future preset time period, and the prediction results are obtained.

[0150] The prediction results are plotted as a dataset of predicted case number change curves, and the case development trend of different disease types is determined based on the dataset of predicted case number change curves.

[0151] According to an embodiment of the present invention, the step of performing disease epidemiology analysis based on the case development trend to determine the risk of disease epidemic occurrence and obtain disease epidemiology risk data specifically includes:

[0152] Obtain data on the rate of increase in cases to assess the prevalence of disease, and determine the rate of increase in cases of different disease types at each point in time in the target medical institution in the future based on the case development trend, thereby obtaining case growth rate data;

[0153] By comparing the case growth rate data with the case growth rate index data, the Euclidean distance between the case growth rate data and the case growth rate index data is calculated, and the risk of the epidemic occurrence of different disease types at each time point in the future is assessed based on the Euclidean distance.

[0154] A first risk threshold and a second risk threshold are preset. Diseases with an epidemic occurrence risk greater than the first risk threshold are marked as high-risk epidemic diseases, diseases with an epidemic occurrence risk between the first and second risk thresholds are marked as medium-risk epidemic diseases, and diseases with an epidemic occurrence risk less than the second risk threshold are marked as low-risk epidemic diseases, thus obtaining disease epidemic risk data.

[0155] According to an embodiment of the present invention, determining the disease epidemic response plan for the target medical institution based on the disease epidemic risk data specifically includes:

[0156] Based on the disease epidemic risk data, identify high-risk epidemic disease types, and obtain the drugs and medical equipment required for the treatment of the high-risk epidemic disease types to obtain treatment material information;

[0157] The number of cases of the high-risk epidemic disease type is determined based on the case development trend, and the required amount of treatment materials is determined based on the number of cases.

[0158] Based on the information on treatment supplies and the demand for treatment supplies, the target medical institution is stockpiled of treatment supplies in advance, thereby obtaining a disease outbreak response plan for the target medical institution.

[0159] A third aspect of the present invention also provides a computer-readable storage medium comprising a big data-based medical intelligent AI management program, wherein when the big data-based medical intelligent AI management program is executed by a processor, it implements the steps of the big data-based medical intelligent AI management method as described in any of the preceding claims.

[0160] This invention discloses a big data-based intelligent AI management method, system, and medium for healthcare. The method includes monitoring data from healthcare institutions, acquiring data storage scale and incremental information, determining an information storage system construction scheme, and constructing an information storage system for the target healthcare institution based on this scheme. The system periodically acquires diagnostic data and analyzes this data using artificial intelligence algorithms to predict case development trends. Furthermore, it performs disease epidemiology analysis based on case development trends, assesses the risk of epidemic occurrence, and determines response strategies. This method effectively improves the efficiency of healthcare data management and analysis, helps healthcare institutions identify and respond to disease risks in advance, and enhances public health security.

[0161] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0162] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0163] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, 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.

[0164] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0165] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0166] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A medical intelligent AI management method based on big data, characterized in that, Includes the following steps: Monitor the medical data of the target medical institution, obtain the data storage scale information and data increment information of the target medical institution, and determine the information storage system construction scheme of the target institution based on the data storage scale information and data increment information; Construct an information storage system for the target medical institution based on big data technology and the aforementioned information storage system construction scheme; The information storage system acquires diagnostic data of patients visiting the target medical institution at a preset time period, and analyzes the diagnostic data using artificial intelligence algorithms to predict the case development trend of the target medical institution. Based on the development trend of the cases, an epidemiological analysis of the disease was conducted to determine the risk of disease outbreaks and obtain disease epidemic risk data. Based on the aforementioned disease epidemic risk data, determine the disease epidemic response plan for the target medical institution; The monitoring of medical data from the target medical institution, obtaining information on the data storage scale and data increment of the target medical institution, and determining the information storage system construction scheme of the target institution based on the data storage scale and data increment information, specifically involves: Historical medical data is obtained from the computer of the target medical institution, including electronic health records, laboratory test data, medical imaging data, patient monitoring data, and diagnosis and treatment data. The total data volume of the target medical institution is evaluated based on the historical medical data to obtain the data scale information of the target medical institution. The data scale information includes the total data volume, the total data volume of each medical data item, and the data volume ratio of each medical data item. Based on the data flow monitoring platform, the medical data of the target medical institution is monitored, and monitoring channels for different medical data items are constructed. Each medical data item is monitored in real time according to the monitoring channels, and the data generation rate and increment of each monitoring channel are recorded to obtain data increment information. Based on the data increment information, identify the peak period of data generation and assess the maximum data growth during the peak period; Based on the incremental data information and historical medical data, analyze the data growth trend of each medical data item and predict the future data growth. Obtain the data access frequency information for each medical data item, set a data access frequency threshold, and divide the medical data of the target medical institution into hot data, warm data, and cold data according to the data access frequency threshold to obtain data access heat information. Obtain the required retention time for each medical data item in the target medical institution, and determine the storage device type for each medical data item in the target medical institution based on the data access popularity information. The storage device type includes SSD, HDD, and cloud storage. The storage capacity of each type of storage device is determined based on the target medical institution's data scale, data increment, future data growth, and required retention time for medical data. The data processor performance requirements of the target medical institution's data storage system are determined based on the maximum data growth and data access frequency information during the peak period. The construction scheme for the information storage system of the target medical institution is determined based on the type of storage device, the storage throughput of the storage device type, and the performance requirements of the data processor. The construction of the information storage system for the target medical institution based on big data technology and the aforementioned information storage system construction scheme specifically includes: Based on the aforementioned information storage system construction scheme, construct the hardware storage system for the target medical institution; A distributed file system for the target medical institution is constructed based on big data technology. Data partitions are constructed in the distributed file system according to medical data items to obtain medical data item storage partitions. The storage device type corresponding to each medical data item of the target medical institution is obtained from the information storage system construction plan. Based on the storage device type corresponding to each medical data item, the storage device type corresponding to each medical data item partition is determined. A mapping relationship is constructed between the medical data item storage partition and the corresponding storage device type to obtain the storage partition-device type mapping table. Obtain the data update requirements for each medical data item of the target medical institution, and determine the data update cycle for each medical data item based on the data update requirements; Based on the storage partition-device type mapping table and data update cycle, a real-time data acquisition tool is configured. The real-time data acquisition tool collects data for each medical data item in the target medical institution and saves it to the corresponding storage device and storage partition according to the data update time cycle, forming a complete information storage system for the target medical institution. The step of acquiring diagnostic data of patients visiting the target medical institution according to a preset time period using the information storage system, and analyzing the diagnostic data using artificial intelligence algorithms to predict the case development trend of the target medical institution, specifically involves: The information storage system acquires diagnostic data of patients visiting the target medical institution according to a preset time period, and extracts disease type information of the patients based on the diagnostic data. Based on the disease type information of the patients, the number of cases of different disease types in the target medical institutions in each time period is statistically analyzed. The number of cases of different disease types in the target medical institutions in each time period is plotted as a case number change curve to obtain a case number change curve dataset. Each curve in the case number change curve dataset is divided into a training set and a test set according to the preset time length proportion. A case number change prediction model was constructed based on the ARIMA algorithm. The case number change curve dataset was analyzed by the autocorrelation function of the time series to determine the autoregression order, difference order, and moving average order of the prediction model. Configure the parameters of the case number change prediction model according to the autoregression order, difference order, and moving average order. Import the training set into the case number change prediction model for fitting and training. Import the test set into the prediction model for prediction effect evaluation. When the prediction effect is less than the preset effect, adjust the model parameters until the prediction effect is not less than the preset effect. The number of cases changing over a preset time period is obtained and imported into the case number change prediction model to predict the number of cases of different disease types in the target medical institution in the future preset time period, and the prediction results are obtained. The prediction results are plotted as a dataset of predicted case number change curves, and the case development trend of different disease types is determined based on the dataset of predicted case number change curves.

2. The medical intelligent AI management method based on big data according to claim 1, characterized in that, The process of conducting disease epidemiology analysis based on the development trend of the cases to determine the risk of disease outbreaks and obtain disease epidemiology risk data specifically includes: Obtain data on the rate of increase in cases to assess the prevalence of disease, and determine the rate of increase in cases of different disease types at each point in time in the target medical institution in the future based on the case development trend, thereby obtaining case growth rate data; By comparing the case growth rate data with the case growth rate index data, the Euclidean distance between the case growth rate data and the case growth rate index data is calculated, and the risk of the epidemic occurrence of different disease types at each time point in the future is assessed based on the Euclidean distance. A first risk threshold and a second risk threshold are preset. Diseases with an epidemic occurrence risk greater than the first risk threshold are marked as high-risk epidemic diseases, diseases with an epidemic occurrence risk between the first and second risk thresholds are marked as medium-risk epidemic diseases, and diseases with an epidemic occurrence risk less than the second risk threshold are marked as low-risk epidemic diseases, thus obtaining disease epidemic risk data.

3. The medical intelligent AI management method based on big data according to claim 1, characterized in that, The step of determining the disease epidemic response plan for the target medical institution based on the disease epidemic risk data specifically includes: Based on the disease epidemic risk data, identify high-risk epidemic disease types, and obtain the drugs and medical equipment required for the treatment of the high-risk epidemic disease types to obtain treatment material information; The number of cases of the high-risk epidemic disease type is determined based on the case development trend, and the required amount of treatment materials is determined based on the number of cases. Based on the information on treatment supplies and the demand for treatment supplies, the target medical institution is stockpiled of treatment supplies in advance, thereby obtaining a disease outbreak response plan for the target medical institution.

4. A medical intelligent AI management system based on big data, characterized in that, The big data-based medical intelligent AI management system includes a storage device and a processor. The storage device includes a big data-based medical intelligent AI management method program. When the big data-based medical intelligent AI management method program is executed by the processor, it performs the following steps: Monitor the medical data of the target medical institution, obtain the data storage scale information and data increment information of the target medical institution, and determine the information storage system construction scheme of the target institution based on the data storage scale information and data increment information; Construct an information storage system for the target medical institution based on big data technology and the aforementioned information storage system construction scheme; The information storage system acquires diagnostic data of patients visiting the target medical institution at a preset time period, and analyzes the diagnostic data using artificial intelligence algorithms to predict the case development trend of the target medical institution. Based on the development trend of the cases, an epidemiological analysis of the disease was conducted to determine the risk of disease outbreaks and obtain disease epidemic risk data. Based on the aforementioned disease epidemic risk data, determine the disease epidemic response plan for the target medical institution; The monitoring of medical data from the target medical institution, obtaining information on the data storage scale and data increment of the target medical institution, and determining the information storage system construction scheme of the target institution based on the data storage scale and data increment information, specifically involves: Historical medical data is obtained from the computer of the target medical institution, including electronic health records, laboratory test data, medical imaging data, patient monitoring data, and diagnosis and treatment data. The total data volume of the target medical institution is evaluated based on the historical medical data to obtain the data scale information of the target medical institution. The data scale information includes the total data volume, the total data volume of each medical data item, and the data volume ratio of each medical data item. Based on the data flow monitoring platform, the medical data of the target medical institution is monitored, and monitoring channels for different medical data items are constructed. Each medical data item is monitored in real time according to the monitoring channels, and the data generation rate and increment of each monitoring channel are recorded to obtain data increment information. Based on the data increment information, identify the peak period of data generation and assess the maximum data growth during the peak period; Based on the incremental data information and historical medical data, analyze the data growth trend of each medical data item and predict the future data growth. Obtain the data access frequency information for each medical data item, set a data access frequency threshold, and divide the medical data of the target medical institution into hot data, warm data, and cold data according to the data access frequency threshold to obtain data access heat information. Obtain the required retention time for each medical data item in the target medical institution, and determine the storage device type for each medical data item in the target medical institution based on the data access popularity information. The storage device type includes SSD, HDD, and cloud storage. The storage capacity of each type of storage device is determined based on the target medical institution's data scale, data increment, future data growth, and required retention time for medical data. The data processor performance requirements of the target medical institution's data storage system are determined based on the maximum data growth and data access frequency information during the peak period. The construction scheme for the information storage system of the target medical institution is determined based on the type of storage device, the storage throughput of the storage device type, and the performance requirements of the data processor. The construction of the information storage system for the target medical institution based on big data technology and the aforementioned information storage system construction scheme specifically includes: Based on the aforementioned information storage system construction scheme, construct the hardware storage system for the target medical institution; A distributed file system for the target medical institution is constructed based on big data technology. Data partitions are constructed in the distributed file system according to medical data items to obtain medical data item storage partitions. The storage device type corresponding to each medical data item of the target medical institution is obtained from the information storage system construction plan. Based on the storage device type corresponding to each medical data item, the storage device type corresponding to each medical data item partition is determined. A mapping relationship is constructed between the medical data item storage partition and the corresponding storage device type to obtain the storage partition-device type mapping table. Obtain the data update requirements for each medical data item of the target medical institution, and determine the data update cycle for each medical data item based on the data update requirements; Based on the storage partition-device type mapping table and data update cycle, a real-time data acquisition tool is configured. The real-time data acquisition tool collects data for each medical data item in the target medical institution and saves it to the corresponding storage device and storage partition according to the data update time cycle, forming a complete information storage system for the target medical institution. The step of acquiring diagnostic data of patients visiting the target medical institution according to a preset time period using the information storage system, and analyzing the diagnostic data using artificial intelligence algorithms to predict the case development trend of the target medical institution, specifically involves: The information storage system acquires diagnostic data of patients visiting the target medical institution according to a preset time period, and extracts disease type information of the patients based on the diagnostic data. Based on the disease type information of the patients, the number of cases of different disease types in the target medical institutions in each time period is statistically analyzed. The number of cases of different disease types in the target medical institutions in each time period is plotted as a case number change curve to obtain a case number change curve dataset. Each curve in the case number change curve dataset is divided into a training set and a test set according to the preset time length proportion. A case number change prediction model was constructed based on the ARIMA algorithm. The case number change curve dataset was analyzed by the autocorrelation function of the time series to determine the autoregression order, difference order, and moving average order of the prediction model. Configure the parameters of the case number change prediction model according to the autoregression order, difference order, and moving average order. Import the training set into the case number change prediction model for fitting and training. Import the test set into the prediction model for prediction effect evaluation. When the prediction effect is less than the preset effect, adjust the model parameters until the prediction effect is not less than the preset effect. The number of cases changing over a preset time period is obtained and imported into the case number change prediction model to predict the number of cases of different disease types in the target medical institution in the future preset time period, and the prediction results are obtained. The prediction results are plotted as a dataset of predicted case number change curves, and the case development trend of different disease types is determined based on the dataset of predicted case number change curves.

5. A medical intelligent AI management system based on big data according to claim 4, characterized in that, The process of conducting disease epidemiology analysis based on the development trend of the cases to determine the risk of disease outbreaks and obtain disease epidemiology risk data specifically includes: Obtain data on the rate of increase in cases to assess the prevalence of disease, and determine the rate of increase in cases of different disease types at each point in time in the target medical institution in the future based on the case development trend, thereby obtaining case growth rate data; By comparing the case growth rate data with the case growth rate index data, the Euclidean distance between the case growth rate data and the case growth rate index data is calculated, and the risk of the epidemic occurrence of different disease types at each time point in the future is assessed based on the Euclidean distance. A first risk threshold and a second risk threshold are preset. Diseases with an epidemic occurrence risk greater than the first risk threshold are marked as high-risk epidemic diseases, diseases with an epidemic occurrence risk between the first and second risk thresholds are marked as medium-risk epidemic diseases, and diseases with an epidemic occurrence risk less than the second risk threshold are marked as low-risk epidemic diseases, thus obtaining disease epidemic risk data.

6. A medical intelligent AI management system based on big data according to claim 4, characterized in that, The step of determining the disease epidemic response plan for the target medical institution based on the disease epidemic risk data specifically includes: Based on the disease epidemic risk data, identify high-risk epidemic disease types, and obtain the drugs and medical equipment required for the treatment of the high-risk epidemic disease types to obtain treatment material information; The number of cases of the high-risk epidemic disease type is determined based on the case development trend, and the required amount of treatment materials is determined based on the number of cases. Based on the information on treatment supplies and the demand for treatment supplies, the target medical institution is stockpiled of treatment supplies in advance, thereby obtaining a disease outbreak response plan for the target medical institution.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a big data-based medical intelligent AI management program, which, when executed by a processor, implements the steps of the big data-based medical intelligent AI management method as described in any one of claims 1 to 3.

Images