Vaccine safety follow-up visit monitoring system and monitoring method

Abstract

The invention relates to the technical field of vaccine follow-up visit monitoring, and particularly discloses a vaccine safety follow-up visit monitoring system, which comprises a data acquisition module used for acquiring monitoring table vaccination data of a recipient group in a monitoring task period; the data analysis module is used for analyzing the monitoring task progress and the historical inoculation problem information of the current inoculation point based on the monitoring table vaccination data, calculating and determining the follow-up visit completion rate of the current inoculation point based on the monitoring task progress and the historical inoculation problem information, and generating early warning information according to the follow-up visit completion rate; the data processing module is used for constructing an AEFI system, analyzing AEFI basic data according to the early warning information, and extracting the AEFI basic data to calculate an abnormal information occurrence rate; performing correlation degree calculation on the monitoring task information and the vaccination file obtained in the AEFI system, and updating the monitoring table according to a correlation degree calculation result; and the auditing module is used for generating graded reminding information according to the occurrence rate of the abnormal information and synchronously pushing the graded reminding information to a corresponding disease control center.

Description

Technical Field

[0001] This invention relates to the field of vaccine follow-up monitoring technology, specifically to a vaccine safety follow-up monitoring system and method. Background Technology

[0002] With the large-scale rollout of new vaccines (such as mRNA vaccines and recombinant protein vaccines), public concern about vaccine safety has increased significantly. Traditional AEFI monitoring mainly relies on passive reporting mechanisms, which suffer from problems such as delayed reporting, missed reporting, incomplete reporting, and inaccurate information due to the uncontrollability of spontaneous reporting. Existing information systems mostly focus on vaccination record management and lack the ability to trigger proactive follow-up and dynamic risk assessment models.

[0003] To compensate for the shortcomings of passive surveillance, various methods can be used to actively identify adverse events affecting individuals (AEFIs). By setting up electronic programs, information can be automatically pushed to vaccine recipients after vaccination, and recipients can actively fill in the AEFIs that occurred after vaccination. This active surveillance method is a good supplement to passive AEFI surveillance. It can timely and comprehensively identify cases and collect information, and combined with passive surveillance, it can more comprehensively evaluate the safety of vaccines administered to large populations after they are marketed.

[0004] Although some provinces and cities have established electronic follow-up form filling systems, they generally have some shortcomings. For example, the task generation during the follow-up process is relatively passive and lacks a dynamic adjustment process. Moreover, it is difficult to combine the follow-up form filling process with abnormal signals for timely identification. This results in a lack of correlation analysis between the AEFI system and the immunization record information, leading to inaccurate and untimely judgment of abnormal information. Summary of the Invention

[0005] The purpose of this invention is to provide a vaccine safety follow-up monitoring system and method, solving the following technical problems:

[0006] How to improve the initiative, accuracy, and real-time nature of the vaccine safety follow-up monitoring system, and enhance the intelligence and informatization of the follow-up system.

[0007] The objective of this invention can be achieved through the following technical solutions:

[0008] A vaccine safety follow-up monitoring system, comprising:

[0009] The data acquisition module is used to collect vaccination data of the target population in the monitoring form during the monitoring task period. The vaccination data in the monitoring form includes the vaccination date, vaccine type, and duration of the monitoring task period.

[0010] The data analysis module is used to analyze the current vaccination site's monitoring task progress and historical vaccination problem information based on the vaccination data in the monitoring form, calculate and determine the current vaccination site's follow-up completion rate based on the monitoring task progress and historical vaccination problem information, and generate early warning information based on the follow-up completion rate.

[0011] The data processing module is used to build the AEFI system, parse the AEFI basic data based on the early warning information, extract the AEFI basic data to calculate the occurrence rate of abnormal information, and perform correlation calculation on the monitoring task information and immunization records obtained from the AEFI system, and update the monitoring table based on the correlation calculation results.

[0012] The review module is used to generate tiered alerts based on the frequency of abnormal information and push them to the corresponding disease control centers simultaneously.

[0013] Preferably, the data acquisition module includes an intelligent form generation unit, which is used to select eligible vaccine recipients from the immunization program information database based on vaccine type, vaccination date, monitoring task cycle duration, and a preset "vaccination-dose-time window" three-dimensional bitmap index, and dynamically adjust the fields of the monitoring table.

[0014] Preferably, the data analysis module includes a task progress analysis unit, which is used to perform the following steps:

[0015] S1, Monitoring Task Cycle The total number of theoretical follow-ups within the period was ,in, To monitor the total number of times, For the first The number of people to be monitored should be secondary; To monitor the duration of the task cycle, This refers to the follow-up time interval;

[0016] S2. Collect the number of historical monitoring tables that have been uploaded. And identify the number of historical monitoring forms that have been approved. ;

[0017] S3. Calculate the follow-up completion rate. and effective completion rate ;

[0018] S4. Compare the effective completion rate and follow-up completion rate :

[0019] Judgment when < Furthermore, the current time has exceeded the monitoring task cycle. When the level reaches 50%, a level-two warning message is generated;

[0020] Judgment when < At that time, a Level 1 warning message is generated;

[0021] S5. Write the Level 2 and Level 1 early warning information into the vaccine safety big data database and add a timestamp, then push it to the data processing module simultaneously.

[0022] Preferably, the data analysis module further includes a problem correction unit, which is used for:

[0023] Regarding the past Each monitoring task cycle The late reporting rate, return rate, and abnormality rate of the same vaccination site within the same period were normalized to obtain the historical vaccination problem index. ;

[0024] Using historical vaccination issues Dynamically adjust follow-up completion rate threshold Corrected threshold , To preset the adjustment weight coefficient, and ∈ The effective completion rate With the corrected threshold Compare:

[0025] Judgment if < The warning will be triggered one time step in advance.

[0026] Preferably, the data processing module includes:

[0027] The early warning analysis unit is used to extract raw monitoring records that match the current vaccine type and vaccination date window from the AEFI system after receiving secondary or primary early warning information, and to construct a temporary analysis dataset.

[0028] The anomaly information determination unit is used to determine the risk of temporary analysis datasets, specifically as follows:

[0029] Through formula Calculate the occurrence rate of abnormal information ,in, Add the number of outliers to the organ classification field of the MedDRA system; The total number of follow-up participants. For the first Number of daily follow-ups per follow-up person The actual number of follow-up days; through Determine the total risk between the individual follow-up and the time frame;

[0030] Obtain the occurrence rate of abnormal information Compared with the national baseline incidence rate The ratio of the two values ​​is used to calculate the relative risk rate. ,when A signal is marked as significant when the value is greater than 2 and the lower limit of the 95% confidence interval is greater than 1.

[0031] Preferably, the data processing module further includes a correlation calculation unit:

[0032] Through calculation formula Calculate the correlation degree ;

[0033] in, For the first The occurrence rate of abnormal information in each monitoring session. This represents the average occurrence rate of abnormal information. For the first Symptom association matching degree of the second monitoring, This represents the mean of the symptom-related match. To monitor the total number of times;

[0034] correlation With preset correlation threshold range Compare:

[0035] like ≥ If a high correlation is determined, the corresponding abnormal record in the AEFI system will be automatically written back to the "Correlation Evidence" field of the monitoring table;

[0036] like ≤ < If the correlation is determined to be moderate, it will be marked as pending manual review;

[0037] like < If the correlation is determined to be low, a temporary file will be created and a data management prompt will be displayed.

[0038] Preferably, the review module includes a tiered reminder unit, which is used for:

[0039] Received abnormal information occurrence rate and relative risk rate ;

[0040] If 2 < ≤3 and If the rate is less than the preset minimum threshold for abnormal information occurrence, a green alert will be generated and pushed only to this vaccination site;

[0041] If 3 < ≤5 or If the abnormal information occurrence rate falls within the preset threshold range, an orange alert will be generated and simultaneously pushed to the district-level CDC.

[0042] like >5 or If the rate exceeds the preset threshold, a red alert will be generated, immediately sent to the municipal CDC, and an emergency sample expansion and suspension of vaccination instructions will be triggered.

[0043] Preferably, the review module further includes:

[0044] The blockchain writing unit is used to write the alert level, anomaly rate calculation parameters, and original dataset hash into the CDC consortium blockchain in the form of Merkle tree leaf nodes, generating an immutable audit trail;

[0045] The reverse return unit is used to automatically push the list of fields to be supplemented and the data format requirements back to the outpatient department when an orange or red alert is returned by the superior disease control department, and restart the supplementary follow-up sub-process until the abnormality rate is recalculated and qualified.

[0046] Preferably, it also includes a dynamic amplification module for performing dynamic amplification upon receiving a red alert, including:

[0047] Through formula Calculate the number of additional recipient samples needed. ;in This represents the total number of vaccine recipients currently under monitoring. This refers to the relative risk rate.

[0048] By extracting new recipients with the same batch number and similar vaccination dates from the immunization program database, supplementary follow-up tasks are generated and the follow-up frequency is automatically increased until two consecutive cycles are completed. Regular monitoring can be resumed if the number of cases is less than 2.

[0049] A method for vaccine safety follow-up monitoring, the method being executed through a vaccine safety follow-up monitoring system, and comprising the following steps:

[0050] Step 1: Collect vaccination data from the target population in the monitoring form during the monitoring task period. The vaccination data in the monitoring form includes the vaccination date, vaccine type, and duration of the monitoring task period.

[0051] Step 2: Analyze the current vaccination site's monitoring task progress and historical vaccination problem information based on the vaccination data in the monitoring form, calculate and determine the current vaccination site's follow-up completion rate based on the monitoring task progress and historical vaccination problem information, and generate early warning information based on the follow-up completion rate;

[0052] Step 3: Construct an AEFI system. Analyze AEFI basic data based on early warning information and extract AEFI basic data to calculate the occurrence rate of abnormal information; calculate the correlation between the monitoring task information and immunization records obtained from the AEFI system, and update the monitoring table based on the correlation calculation results.

[0053] Step 4: Generate graded alert information based on the incidence rate of abnormal information and push it to the corresponding disease control center simultaneously. Upon receiving a red alert, conduct dynamic sample expansion.

[0054] The beneficial effects of this invention are:

[0055] This invention realizes a process of moving from passive monitoring to proactive early warning and intervention in follow-up. Firstly, it achieves precise screening of vaccination recipients through intelligent form-driven methods. Basic vaccination information of the recipient population is automatically collected when the monitoring task is initiated. Based on the vaccination data in the monitoring form, the progress of the current vaccination site's monitoring task and historical vaccination issues are analyzed. Further calculations are performed to obtain the follow-up completion rate of the current vaccination site, and early warning information is generated based on the follow-up completion rate to ensure that the current vaccination site can provide effective follow-up information and guarantee the smooth implementation and execution of the monitoring task. Secondly, it uses the AEFI system to discover and predict abnormal information and performs correlation analysis on abnormal information to improve early warning decision-making capabilities. The AEFI system is constructed to parse AEFI basic data based on early warning information and extract AEFI basic data to calculate the occurrence rate of abnormal information. The correlation between the monitoring task information and immunization records obtained from the AEFI system is calculated, and the monitoring form is updated based on the correlation calculation results. Finally, an audit module ensures that tiered reminder information is generated based on the occurrence rate of abnormal information and is simultaneously pushed to the corresponding disease control center. This achieves a rapid prediction and reminder process for abnormal follow-up information.

[0056] Of course, any product implementing this invention does not necessarily need to achieve all the advantages described above at the same time. Attached Figure Description

[0057] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a block diagram of a vaccine safety follow-up monitoring system according to the present invention;

[0059] Figure 2 This is a schematic diagram of the unit structure of the data analysis module of the present invention;

[0060] Figure 3 This is a schematic diagram of the unit structure of the data processing module of the present invention;

[0061] Figure 4 This is a schematic diagram of the unit structure of the review module of the present invention;

[0062] Figure 5 This is a flowchart illustrating the steps of a vaccine safety follow-up monitoring method according to the present invention. Detailed Implementation

[0063] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] Currently, there is no electronic program for proactive monitoring of post-vaccination safety. Most proactive monitoring of post-vaccination safety uses telephone follow-up to investigate the occurrence of adverse events following vaccination (AEFI). Specifically, after vaccination, staff at the vaccination clinic conduct telephone follow-ups with recipients at different time points, such as day 0, day 1, day 3, day 7, and day 28, to understand their health status and record any AEFI occurrences. There are also cases where partially electronic methods are used for proactive monitoring of post-vaccination safety.

[0065] In multi-center active surveillance of adverse events following acellular pertussis-diphtheria-tetanus-haemophilus influenzae type b combined vaccination, some relied on the district's health big data platform to extract individual medical and vaccination information, automatically retrieved the recipient's medical records within 7 days after vaccination, and categorized the search results according to the 10th edition of the International Statistical Classification of Diseases and Related Health Problems into types such as fever, febrile seizures, urticaria, respiratory diseases, and allergies, and monitored the occurrence of adverse events following vaccination in real time.

[0066] The most common method is to conduct follow-up calls by vaccination clinic staff, but this is time-consuming, labor-intensive, and increases workload and pressure, making it difficult to implement. Some electronic online login operations are relatively complex and require a certain level of compliance. The APP download process is relatively complex, and its compliance and maintenance are somewhat difficult. For health big data platforms, the completeness and accuracy of information vary depending on the different stages of information technology construction.

[0067] Please see Figure 1 As shown, in order to solve the above-mentioned technical problems, the present invention provides a vaccine safety follow-up monitoring system, comprising:

[0068] The data acquisition module is used to collect vaccination data of the target population in the monitoring form during the monitoring task period. The vaccination data in the monitoring form includes the vaccination date, vaccine type, and duration of the monitoring task period.

[0069] The data analysis module is used to analyze the current vaccination site's monitoring task progress and historical vaccination problem information based on the vaccination data in the monitoring form, calculate and determine the current vaccination site's follow-up completion rate based on the monitoring task progress and historical vaccination problem information, and generate early warning information based on the follow-up completion rate.

[0070] The data processing module is used to build the AEFI system, parse the AEFI basic data based on the early warning information, extract the AEFI basic data to calculate the occurrence rate of abnormal information, and perform correlation calculation on the monitoring task information and immunization records obtained from the AEFI system, and update the monitoring table based on the correlation calculation results.

[0071] The review module is used to generate tiered alerts based on the frequency of abnormal information and push them to the corresponding disease control centers simultaneously.

[0072] The above technical solution constructs a vaccine safety follow-up monitoring system through a data acquisition module, a data analysis module, a data processing module, and an auditing module, realizing a process from passive monitoring to proactive early warning and intervention. Specifically, the data acquisition module achieves accurate screening of vaccine recipients through intelligent form-driven methods, automatically collecting basic vaccination information of the recipient population when the monitoring task is initiated. The data analysis module analyzes the current vaccination site's monitoring task progress and historical vaccination problem information based on the vaccination data in the monitoring form, further calculates the current vaccination site's monitoring task progress and historical vaccination problem information to obtain the current vaccination site's follow-up completion rate, and generates early warning information based on the follow-up completion rate to ensure the current vaccination... The system provides effective follow-up information to ensure the smooth implementation and execution of monitoring tasks. The data processing module is used to discover and predict abnormal information based on the AEFI system, and to perform correlation analysis on abnormal information to improve early warning decision-making capabilities. Specifically, it constructs the AEFI system to parse AEFI basic data based on early warning information and extracts AEFI basic data to calculate the incidence rate of abnormal information. It also calculates the correlation between monitoring task information and immunization records obtained from the AEFI system and updates the monitoring table based on the correlation calculation results. The review module ensures that graded reminder information is generated based on the incidence rate of abnormal information and is simultaneously pushed to the corresponding disease control center, realizing a rapid prediction and reminder process for follow-up abnormal information.

[0073] The AEFI system framework is described below:

[0074] 1. AEFI Basic Data Management

[0075] AEFI basic data management includes AEFI monitoring issue maintenance, AEFI monitoring table maintenance, and AEFI monitoring task configuration. It can create various types of monitoring issues, customize monitoring survey form templates based on monitoring issues, and flexibly adjust the question order, layout, and set logical rules such as mandatory and optional items to meet diverse data collection requirements. At the same time, it can adapt to monitoring work with different urgency levels and data collection needs by setting different monitoring tasks through the system.

[0076] 2. AEFI Monitoring and Management

[0077] AEFI monitoring management includes AEFI monitoring form completion and review. During the monitoring process, the system can conduct detailed queries for specific monitoring groups, and also provides convenient functions for outpatient doctors, allowing them to query cases that have not yet been completed and to implement follow-up actions accordingly. For monitoring group data that has been completed, the management system supports hierarchical reporting and review according to established procedures to ensure the accuracy and completeness of the data, achieving standardized and refined management of AEFI monitoring work.

[0078] 3. Public Service WeChat Functions

[0079] The WeChat public service platform serves as a crucial data collection function within the AEFI monitoring system. Vaccine recipients or their parents, as core data providers, conveniently complete the monitoring survey form via WeChat. The system can track and provide real-time feedback on the completion status; for recipients or their parents who have not yet completed the form, the system can send reminder messages via WeChat to improve the timeliness of completion.

[0080] 4. Third-party integration

[0081] The system can interface with the AEFI active monitoring system and hospital treatment systems. By using key identifiers in the basic information, the system can accurately match the medical records of the monitored population from the hospital's treatment system data, enabling full-process tracing of the monitored population from the start of vaccination to hospital treatment. This data is then used for analysis; by analyzing the correlation between vaccination time and subsequent medical treatment, the system can quickly determine whether there are potential adverse reaction trends after a specific vaccine. Simultaneously, the system establishes dynamic health records based on the traceability data, providing detailed and reliable data support for public health decision-making.

[0082] As one embodiment of the present invention, the data acquisition module includes an intelligent form generation unit. The intelligent form generation unit is used to select eligible vaccine recipients from the immunization program information database based on vaccine type, vaccination date, monitoring task cycle duration, and a preset "vaccination-dose-time window" three-dimensional bitmap index, and dynamically adjust the fields of the monitoring table.

[0083] In the above technical solution, the input parameters of the intelligent form generation unit include vaccine type, vaccination date, and monitoring task cycle duration. These parameters are indexed by a preset "vaccination-dose-time window" three-dimensional bitmap and stored in the immunization program information database. The working process is as follows: First, the recommended follow-up plan for the current vaccine type is analyzed, such as three follow-ups at 7, 14, and 28 days after the second dose of the vaccine. Then, a list of recipients meeting the vaccination time window is matched in the immunization program database. Next, an electronic monitoring form containing necessary fields (such as fever, local redness and swelling, allergy history, etc.) and optional fields (expanded by age / underlying disease) is dynamically generated. Finally, multiple data collection methods are supported, including mobile terminal filling, OCR recognition of paper form upload, and HIS system integration. The intelligent form generation unit enables the setting of corresponding forms for different vaccines and population information, thereby avoiding interference from irrelevant fields in the normal filling experience and improving data integrity.

[0084] As one embodiment of the present invention, please refer to Figure 2 As shown, the data analysis module includes a task progress analysis unit, which is used to perform the following steps:

[0085] S1, Monitoring Task Cycle The total number of theoretical follow-ups within the period was ,in, To monitor the total number of times, For the first The number of people to be monitored should be secondary; To monitor the duration of the task cycle, This refers to the follow-up time interval;

[0086] S2. Collect the number of historical monitoring tables that have been uploaded. And identify the number of historical monitoring forms that have been approved. ;

[0087] S3. Calculate the follow-up completion rate. and effective completion rate ;

[0088] S4. Compare the effective completion rate and follow-up completion rate :

[0089] Judgment when < Furthermore, the current time has exceeded the monitoring task cycle. When the level reaches 50%, a level-two warning message is generated;

[0090] Judgment when < At that time, a Level 1 warning message is generated;

[0091] S5. Write the Level 2 and Level 1 early warning information into the vaccine safety big data database and add a timestamp, then push it to the data processing module simultaneously.

[0092] In the above technical solution, the data analysis module obtains follow-up information data through the task progress analysis unit, namely, the effective completion rate, which is used to determine and record the progress of the follow-up task; through Obtain the theoretical total number of follow-up visits, and collect the number of monitoring forms that have already been uploaded. To determine the number of uploads for follow-up visits, and the number of historical monitoring forms that have passed review. To further determine and calculate, that is, through Determine the follow-up completion rate However, this follow-up completion rate is not definitively valid and needs to be calculated. Get As the effective completion rate, the current follow-up task completion progress is determined by comparing the effective completion rate with the follow-up completion rate. Based on the comparison results, the current follow-up completion information is determined, and whether an alert is needed is issued. Specifically, it is determined that when... < Furthermore, the current time has exceeded the monitoring task cycle. When it reaches 50%, a level-two warning message is generated; it is determined that when < At that time, a Level 1 warning message is generated; based on the acquired Level 2 and Level 1 warning messages, the information is written into the vaccine safety big data database and timestamped, and then pushed synchronously to the data processing module; further problem confirmation is performed on the task progress warning information, and further analysis is conducted through the problem correction unit of the data analysis module.

[0093] As one embodiment of the present invention, please refer to Figure 2 As shown, the data analysis module also includes a problem correction unit, which is used for:

[0094] Regarding the past Each monitoring task cycle The late reporting rate, return rate, and abnormality rate of the same vaccination site within the same period were normalized to obtain the historical vaccination problem index. ;

[0095] Using historical vaccination issues Dynamically adjust follow-up completion rate threshold Corrected threshold , To preset the adjustment weight coefficient, and ∈ The effective completion rate With the corrected threshold Compare:

[0096] Judgment if < The warning will be triggered one time step in advance.

[0097] In the above technical solution, a historical vaccination problem index is introduced through a problem correction unit to dynamically adjust the threshold, thereby providing early warning of problems and reducing the escalation of vaccination follow-up issues. Specifically, this is achieved by extracting past... Each monitoring task cycle Three indicators at the same vaccination site—late reporting rate, return rate, and abnormality rate—were calculated, and Z-score normalization was applied to each indicator to obtain the results. , , To calculate the comprehensive historical issues index: The calculation method for dynamically correcting the early warning threshold is as follows: By assessing whether the current vaccination site has a high rate of delayed or returned vaccinations, even if the current effective completion rate is low... Higher than the follow-up completion rate threshold It can also trigger a yellow alert in advance; the problem correction unit can ensure the follow-up rate while preventing low-quality data from masking the real risk, and ensure the construction process of promoting vaccination sites to attach importance to data quality.

[0098] As one embodiment of the present invention, please refer to Figure 3 As shown, the data processing module includes:

[0099] The early warning analysis unit is used to extract raw monitoring records that match the current vaccine type and vaccination date window from the AEFI system after receiving secondary or primary early warning information, and to construct a temporary analysis dataset.

[0100] The anomaly information determination unit is used to determine the risk of temporary analysis datasets, specifically as follows:

[0101] Through formula Calculate the occurrence rate of abnormal information ,in, Add the number of outliers to the organ classification field of the MedDRA system; The total number of follow-up participants. For the first Number of daily follow-ups per follow-up person The actual number of follow-up days; through Determine the total risk between the individual follow-up and the time frame;

[0102] Obtain the occurrence rate of abnormal information Compared with the national baseline incidence rate The ratio of the two values ​​is used to calculate the relative risk rate. ,when A signal is marked as significant when the value is greater than 2 and the lower limit of the 95% confidence interval is greater than 1.

[0103] In the above technical solution, the early warning analysis unit of the data processing module automatically calls the AEFI system to receive secondary or primary early warning information, ensuring that a dataset matching the current information conditions is extracted from the AEFI system, including all original AEFI records of the same vaccine type and vaccination date within a few days, such as about 7 days, and a temporary analysis dataset is constructed to facilitate subsequent in-depth analysis.

[0104] Subsequent analysis uses an anomaly information determination unit to assess the risk of this temporary analysis dataset, through a calculation formula. Determine the occurrence rate of abnormal information, conduct comparative analysis based on the occurrence rate to identify abnormal signals, and further compare it with the national baseline occurrence rate. The ratio is used to calculate the relative risk rate. ; Judge when A value greater than 2 and with the lower limit of the 95% confidence interval greater than 1 is marked as a significant signal. Based on this significant signal marking, potential safety signals are determined, and the signal is used to ensure entry into the review module for verification. National basic incidence rate. It was confirmed through screening from a large historical database.

[0105] As one embodiment of the present invention, please refer to Figure 3 As shown, the data processing module also includes a correlation calculation unit:

[0106] Through calculation formula Calculate the correlation degree ;

[0107] in, For the first The occurrence rate of abnormal information in each monitoring session. This represents the average occurrence rate of abnormal information. For the first Symptom association matching degree of the second monitoring, This represents the mean of the symptom-related match. To monitor the total number of times;

[0108] correlation With preset correlation threshold range Compare:

[0109] like ≥ If a high correlation is determined, the corresponding abnormal record in the AEFI system will be automatically written back to the "Correlation Evidence" field of the monitoring table;

[0110] like ≤ < If the correlation is determined to be moderate, it will be marked as pending manual review;

[0111] like < If the correlation is determined to be low, a temporary file will be created and a data management prompt will be displayed.

[0112] In the above technical solution, correlation analysis is achieved through a correlation calculation unit, and the Pearson correlation coefficient is used to measure the trend consistency between the "abnormal information occurrence rate" and the "symptom association matching degree"; the specific calculation formula is as follows: The semantic matching scores between symptoms determined by an NLP engine and known clinical manifestations of AEFI were used. And through correlation With preset correlation threshold range The comparison is used to determine the correlation. ≥ If a high correlation is determined, the corresponding abnormal record in the AEFI system will be automatically written back to the "Correlation Evidence" field of the monitoring table; if... ≤ < If the correlation is determined to be moderate, it is marked as requiring manual review; if the correlation is determined to be moderate... < If the correlation is determined to be low, a temporary file is created and a data governance prompt is displayed; this process enables the risk to be associated with vaccination based on the correlation degree, thereby reducing the false alarm rate.

[0113] Furthermore, in practical use, the correlation calculation unit also deduplicates the data based on the "vaccine-dose-time window" three-dimensional bitmap when the same recipient receives multiple vaccines or multiple doses of the same vaccine within the monitoring task period, ensuring that only one monitoring task is generated and avoiding dilution of the vaccination signal.

[0114] As one embodiment of the present invention, please refer to Figure 4 As shown, the review module includes a tiered reminder unit, which is used for:

[0115] Received abnormal information occurrence rate and relative risk rate ;

[0116] If 2 < ≤3 and If the rate is less than the preset minimum threshold for abnormal information occurrence, a green alert will be generated and pushed only to this vaccination site;

[0117] If 3 < ≤5 or If the abnormal information occurrence rate falls within the preset threshold range, an orange alert will be generated and simultaneously pushed to the district-level CDC.

[0118] like >5 or If the rate exceeds the preset threshold, a red alert will be generated, immediately sent to the municipal CDC, and an emergency sample expansion and suspension of vaccination instructions will be triggered.

[0119] In the above technical solution, the occurrence rate of abnormal information received by the audit module from the data processing module is... and relative risk rate Further feedback is provided, with the feedback content using color-coded alerts based on the magnitude of the two values; darker colors indicate a stronger alert. Specifically, if 2 < 0.05, the alert is triggered. ≤3 and If the incidence rate is less than the preset minimum threshold for abnormal information, a green alert is generated and pushed only to this vaccination site, indicating that the situation is within the normal follow-up adjustment range and continued observation is sufficient. However, if 3 < ≤5 or When the incidence of abnormal information falls within the preset threshold range, it requires attention from a higher level, escalating to an orange alert, and needs to be simultaneously pushed to the district-level CDC; if >5 or If the abnormality rate exceeds the preset threshold, a red alert is generated, immediately pushed to the municipal CDC, and triggers emergency sample expansion and suspension of vaccination instructions. All color-coded alerts include the abnormality rate confidence interval, sample size, and blockchain-based evidence hash to ensure that higher-level units can verify data integrity with a single click.

[0120] As one embodiment of the present invention, please refer to Figure 4 As shown, the review module also includes:

[0121] The blockchain writing unit is used to write the alert level, anomaly rate calculation parameters, and original dataset hash into the CDC consortium blockchain in the form of Merkle tree leaf nodes, generating an immutable audit trail;

[0122] The reverse return unit is used to automatically push the list of fields to be supplemented and the data format requirements back to the outpatient department when an orange or red alert is returned by the superior disease control department, and restart the supplementary follow-up sub-process until the abnormality rate is recalculated and qualified.

[0123] As one embodiment of the present invention, please refer to Figure 1 As shown, it also includes a dynamic amplification module, used to perform dynamic amplification upon receiving a red alert, including:

[0124] Through formula Calculate the number of additional recipient samples needed. ;in This represents the total number of vaccine recipients currently under monitoring. This refers to the relative risk rate.

[0125] By extracting new recipients with the same batch number and similar vaccination dates from the immunization program database, supplementary follow-up tasks are generated and the follow-up frequency is automatically increased until two consecutive cycles are completed. Regular monitoring can be resumed if the number of cases is less than 2.

[0126] In the above technical solution, the dynamic sample expansion module is activated upon receiving a red alert, which expands the range of recipient samples to ensure that the current follow-up tasks can be supplemented. Furthermore, by increasing the follow-up sampling frequency and extending the monitoring cycle, the system can quickly verify and eliminate potential safety hazards, thereby significantly improving the efficiency of risk elimination for safety follow-up issues.

[0127] For a method of vaccine safety follow-up monitoring, please refer to [link / reference]. Figure 5 As shown, the method, implemented using a vaccine safety follow-up monitoring system, includes the following steps:

[0128] Step 1: Collect vaccination data from the target population in the monitoring form during the monitoring task period. The vaccination data in the monitoring form includes the vaccination date, vaccine type, and duration of the monitoring task period.

[0129] Step 2: Analyze the current vaccination site's monitoring task progress and historical vaccination problem information based on the vaccination data in the monitoring form, calculate and determine the current vaccination site's follow-up completion rate based on the monitoring task progress and historical vaccination problem information, and generate early warning information based on the follow-up completion rate;

[0130] Step 3: Construct an AEFI system. Analyze AEFI basic data based on early warning information and extract AEFI basic data to calculate the occurrence rate of abnormal information; calculate the correlation between the monitoring task information and immunization records obtained from the AEFI system, and update the monitoring table based on the correlation calculation results.

[0131] Step 4: Generate graded alert information based on the incidence rate of abnormal information and push it to the corresponding disease control center simultaneously. Upon receiving a red alert, conduct dynamic sample expansion.

[0132] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0133] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended documents. In some cases, the actions or steps described in this application may be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0134] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they should all fall within the protection scope of the present invention.

Claims

1. A vaccine safety follow-up monitoring system, characterized in that, include: The data acquisition module is used to collect vaccination data of the target population in the monitoring table during the monitoring task period. The vaccination data in the monitoring table includes the vaccination date, vaccine type, and duration of the monitoring task period. The data analysis module is used to analyze the current vaccination site's monitoring task progress and historical vaccination problem information based on the vaccination data in the monitoring form, calculate and determine the current vaccination site's follow-up completion rate based on the monitoring task progress and historical vaccination problem information, and generate early warning information based on the follow-up completion rate. The data processing module is used to build the AEFI system, which parses the AEFI basic data based on the early warning information and extracts the AEFI basic data to calculate the occurrence rate of abnormal information. And calculate the correlation between the monitoring task information and immunization records obtained from the AEFI system, and update the monitoring table based on the correlation calculation results; The review module is used to generate tiered alerts based on the frequency of abnormal information and push them to the corresponding disease control centers simultaneously.

2. The vaccine safety follow-up monitoring system according to claim 1, characterized in that, The data acquisition module includes an intelligent form generation unit, which is used to select eligible vaccine recipients from the immunization program information database based on vaccine type, vaccination date, monitoring task cycle duration, and a preset "vaccination-dose-time window" three-dimensional bitmap index, and dynamically adjust the fields of the monitoring table.

3. The vaccine safety follow-up monitoring system according to claim 1, characterized in that, The data analysis module includes a task progress analysis unit, which is used to perform the following steps: S1, Monitoring Task Cycle The total number of theoretical follow-ups within the period was ,in, To monitor the total number of times, For the first The number of people to be monitored should be secondary; To monitor the duration of the task cycle, This refers to the follow-up time interval; S2. Collect the number of historical monitoring tables that have been uploaded. And identify the number of historical monitoring forms that have been approved. ; S3. Calculate the follow-up completion rate. and effective completion rate ; S4. Compare the effective completion rate and follow-up completion rate : Judgment when < Furthermore, the current time has exceeded the monitoring task cycle. When the level reaches 50%, a level-two warning message is generated; Judgment when < At that time, a Level 1 warning message is generated; S5. Write the Level 2 and Level 1 early warning information into the vaccine safety big data database and add a timestamp, then push it to the data processing module simultaneously.

4. The vaccine safety follow-up monitoring system according to claim 3, characterized in that, The data analysis module also includes a problem correction unit, which is used for: Regarding the past Each monitoring task cycle The late reporting rate, return rate, and abnormality rate of the same vaccination site within the same period were normalized to obtain the historical vaccination problem index. ; Using historical vaccination issues Dynamically adjust follow-up completion rate threshold Corrected threshold , To preset the adjustment weight coefficient, and ∈ The effective completion rate With the corrected threshold Compare: Judgment if < The warning will be triggered one time step in advance.

5. The vaccine safety follow-up monitoring system according to claim 3, characterized in that, The data processing module includes: The early warning analysis unit is used to extract raw monitoring records that match the current vaccine type and vaccination date window from the AEFI system after receiving secondary or primary early warning information, and to construct a temporary analysis dataset. The anomaly information determination unit is used to determine the risk of temporary analysis datasets, specifically as follows: Through formula Calculate the occurrence rate of abnormal information ,in, Add the number of outliers to the organ classification field of the MedDRA system; The total number of follow-up participants. For the first Number of daily follow-ups per follow-up person The actual number of follow-up days; through Determine the total risk between the individual follow-up and the time frame; Obtain the occurrence rate of abnormal information Compared with the national baseline incidence rate The ratio of the two values ​​is used to calculate the relative risk rate. ,when A signal is marked as significant when the value is greater than 2 and the lower limit of the 95% confidence interval is greater than 1.

6. The vaccine safety follow-up monitoring system according to claim 5, characterized in that, The data processing module also includes a correlation calculation unit: Through calculation formula Calculate the correlation degree ; in, For the first The occurrence rate of abnormal information in each monitoring session. This represents the average occurrence rate of abnormal information. For the first Symptom association matching degree of the second monitoring, This represents the mean of the symptom-related match. To monitor the total number of times; correlation With preset correlation threshold range Compare: like ≥ If a high correlation is determined, the corresponding abnormal record in the AEFI system will be automatically written back to the "correlation evidence" field of the monitoring table. like ≤ < If the correlation is determined to be moderate, it will be marked as requiring manual review. like < If the correlation is determined to be low, a temporary file will be created and a data management prompt will be displayed.

7. The vaccine safety follow-up monitoring system according to claim 5, characterized in that, The review module includes a tiered reminder unit, which is used for: Received abnormal information occurrence rate and relative risk rate ; If 2 < ≤3 and If the rate is less than the preset minimum threshold for abnormal information occurrence, a green alert will be generated and pushed only to this vaccination site; If 3 < ≤5 or If the abnormal information occurrence rate falls within the preset threshold range, an orange alert will be generated and simultaneously pushed to the district-level CDC. like >5 or If the rate exceeds the preset threshold, a red alert will be generated, immediately sent to the municipal CDC, and an emergency sample expansion and suspension of vaccination instructions will be triggered.

8. The vaccine safety follow-up monitoring system according to claim 1, characterized in that, The audit module also includes: The blockchain writing unit is used to write the alert level, anomaly rate calculation parameters, and original dataset hash into the CDC consortium blockchain in the form of Merkle tree leaf nodes, generating an immutable audit trail; The reverse return unit is used to automatically push the list of fields to be supplemented and the data format requirements back to the outpatient department when an orange or red alert is returned by the superior disease control department, and restart the supplementary follow-up sub-process until the abnormality rate is recalculated and qualified.

9. A vaccine safety follow-up monitoring system according to claim 7, characterized in that, It also includes a dynamic amplification module, used to perform dynamic amplification upon receiving a red alert, including: Through formula Calculate the number of additional recipient samples needed. ;in This represents the total number of vaccine recipients currently under monitoring. This refers to the relative risk rate. By extracting new recipients with the same batch number and similar vaccination dates from the immunization program database, supplementary follow-up tasks are generated and the follow-up frequency is automatically increased until two consecutive cycles are completed. Regular monitoring can be resumed if the number of cases is less than 2.

10. A method for vaccine safety follow-up monitoring, wherein the method is performed by a vaccine safety follow-up monitoring system as described in any one of claims 1-9, characterized in that, The method includes the following steps: Step 1: Collect vaccination data from the target population within the monitoring task period. The vaccination data in the monitoring form includes the vaccination date, vaccine type, and duration of the monitoring task period. Step 2: Analyze the current vaccination site's monitoring task progress and historical vaccination problem information based on the vaccination data in the monitoring form, calculate and determine the current vaccination site's follow-up completion rate based on the monitoring task progress and historical vaccination problem information, and generate early warning information based on the follow-up completion rate; Step 3: Construct an AEFI system. Analyze AEFI basic data based on early warning information and extract AEFI basic data to calculate the occurrence rate of abnormal information; calculate the correlation between the monitoring task information and immunization records obtained from the AEFI system, and update the monitoring table based on the correlation calculation results. Step 4: Generate graded alert information based on the incidence rate of abnormal information and push it to the corresponding disease control center simultaneously. Upon receiving a red alert information, conduct dynamic sample expansion.

Images