An adverse drug reaction aggregation monitoring method, system, device and storage medium

Abstract

The embodiment of the application discloses a kind of drug adverse reaction aggregation monitoring method, system, equipment and storage medium, first to drug adverse reaction report is sampled, corresponding adverse reaction report sample set is obtained;Then, based on preset drug early warning rule, early warning grade matching is carried out, corresponding first early warning signal is generated;First early warning signal is sorted again, and second early warning signal is obtained;It is judged whether the sampling time period corresponding to each second early warning signal is crossed;If yes, then the first quantity of sampling time period that exists continuous crossing is counted;If the first quantity is less than or equal to first preset quantity, then the first similarity of corresponding adverse reaction report sample set is compared;If the first similarity is greater than or equal to first threshold, then any one from corresponding second early warning signal is selected and saved as aggregation early warning signal.The embodiment of the application realizes the aggregation monitoring of drug adverse reaction, effectively improves the monitoring efficiency and monitoring early warning accuracy of drug adverse reaction.

Description

A method, system, device and storage medium for monitoring adverse drug reaction clusters. Technical Field

[0001] This invention relates to the field of computer data processing, specifically to a method, system, device, and storage medium for monitoring adverse drug reaction clusters. Background Technology

[0002] In recent years, thanks to the efforts of several generations of pharmaceutical workers, my country has become a major producer of raw materials, pharmaceutical preparations, and vaccines, forming a relatively complete pharmaceutical industrial system and pharmaceutical distribution network, and developing into a world-leading pharmaceutical manufacturing country. However, with the rapid development of the pharmaceutical industry, my country has also entered a period of high incidence of drug safety risks.

[0003] In order to promptly detect adverse drug reaction events, adverse drug reaction monitoring work needs to pay close attention to adverse reaction events that occur in a short period of time for various pharmaceutical companies and products. Such clustering of adverse reactions is usually called clustering signal. By analyzing and evaluating clustering signals, it is determined whether they constitute a group adverse drug reaction event.

[0004] Current monitoring of adverse drug reaction clusters relies primarily on manual statistical analysis. This requires sifting through vast amounts of data to identify specific batches of a particular drug product before statistical analysis is performed to determine the corresponding warning level. Existing technologies require a large number of personnel and significant time investment, resulting in low monitoring efficiency. Furthermore, because current monitoring techniques depend on human experience, the accuracy of monitoring and warnings is relatively low. Summary of the Invention

[0005] To address these issues, embodiments of the present invention provide a method, system, device, and storage medium for monitoring adverse drug reaction clusters, thereby resolving the problems of low monitoring efficiency and low accuracy in early warning of existing adverse drug reaction cluster monitoring technologies.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] According to a first aspect of the present invention, a method for monitoring adverse drug reaction clusters is provided, the method comprising:

[0008] Set the sampling time period and the number of sampling time periods, sample the adverse drug reaction reports of the batch of drugs to be monitored within the time period, and obtain the adverse reaction report sample set corresponding to each sampling time period;

[0009] The adverse reaction report sample sets are classified and statistically analyzed. Based on the preset drug early warning rules, the classification and statistical results are matched to generate the corresponding first early warning signal.

[0010] Based on the corresponding sampling time period, the first warning signals are sorted to obtain the corresponding second warning signals;

[0011] Determine whether the sampling time periods corresponding to each of the second warning signals overlap;

[0012] If the sampling time periods corresponding to each of the second warning signals overlap, then the first number of sampling time periods corresponding to the second warning signals that have consecutive overlaps is counted.

[0013] Determine whether the first quantity is greater than the first preset quantity;

[0014] If the first quantity is less than or equal to the first preset quantity, then compare the first similarity of the corresponding adverse reaction report sample set;

[0015] Determine whether the first similarity is greater than or equal to the first threshold;

[0016] If the first similarity is greater than or equal to the first threshold, then any one of the corresponding second warning signals is selected and saved as a cluster warning signal.

[0017] Furthermore, the method also includes:

[0018] If the sampling time periods corresponding to the various second warning signals do not overlap, then the second warning signals are saved as clustered warning signals.

[0019] Furthermore, the method also includes:

[0020] If the first similarity is less than the first threshold, then determine whether the first similarity is greater than or equal to the second threshold;

[0021] If the first similarity is greater than or equal to the second threshold, then any one of the corresponding second warning signals is selected and saved as a cluster warning signal, and the remaining second warning signals are saved as historical versions of the cluster warning signal.

[0022] If the first similarity is less than the second threshold, then the corresponding second warning signals will all be saved as cluster warning signals.

[0023] Furthermore, the method also includes:

[0024] If the first quantity is greater than the first preset quantity, then determine whether the first quantity is less than the second preset quantity;

[0025] If the first quantity is greater than or equal to the second preset quantity, then any one of the corresponding second warning signals is selected and saved as a cluster warning signal;

[0026] If the first quantity is less than the second preset quantity, then at least one third warning signal with the highest warning level is selected from the corresponding second warning signals;

[0027] Determine whether the sampling time periods corresponding to each of the third warning signals overlap;

[0028] If the sampling time periods corresponding to the various third warning signals do not overlap, then the third warning signals will be saved as clustered warning signals.

[0029] Furthermore, the method also includes:

[0030] If the sampling time periods corresponding to each third warning signal overlap, then the second number of sampling time periods corresponding to the third warning signals that have consecutive overlaps is counted.

[0031] Determine whether the second quantity is greater than the first preset quantity;

[0032] If the second quantity is less than or equal to the first preset quantity, then compare the second similarity of the adverse reaction report sample set corresponding to the third warning signal;

[0033] Determine whether the second similarity is greater than or equal to the first threshold;

[0034] If the second similarity is greater than or equal to the first threshold, then any one of the corresponding third warning signals is selected and saved as a cluster warning signal;

[0035] If the second similarity is less than the first threshold, then determine whether the second similarity is greater than or equal to the second threshold;

[0036] If the second similarity is greater than or equal to the second threshold, then any one of the corresponding third warning signals is selected and saved as a cluster warning signal, and the remaining third warning signals are saved as historical versions of the cluster warning signal.

[0037] If the second similarity is less than the second threshold, then the corresponding third warning signals will all be saved as cluster warning signals.

[0038] Furthermore, the method also includes:

[0039] If the second quantity is greater than the first preset quantity, then compare the third similarity of the adverse reaction report sample set corresponding to the third warning signal;

[0040] Determine whether the third similarity is greater than or equal to the first threshold;

[0041] If the third similarity is greater than or equal to the first threshold, then any one of the corresponding third warning signals is selected and saved as a cluster warning signal.

[0042] Furthermore, the method also includes:

[0043] If the third similarity is less than the first threshold, then the fourth similarity of the adverse reaction report sample sets corresponding to the third warning signals in adjacent sampling time periods is compared.

[0044] Determine whether the fourth similarity is greater than or equal to the first threshold;

[0045] If the fourth similarity is greater than or equal to the first threshold, then any one of the corresponding third warning signals is selected and saved as an aggregation warning signal;

[0046] If the fourth similarity is less than the first threshold, then the corresponding third warning signals will all be saved as cluster warning signals.

[0047] According to a second aspect of the present invention, a drug adverse reaction cluster monitoring system is provided, the system comprising:

[0048] The data sampling module is used to set the sampling time period and the number of the sampling time periods, and to sample the adverse drug reaction reports of the batch of drugs to be monitored within the time period to obtain the adverse reaction report sample set corresponding to each sampling time period.

[0049] The early warning matching module is used to classify and statistically analyze each adverse reaction report sample set, match the classification and statistical results based on preset drug early warning rules, and generate a corresponding first early warning signal.

[0050] The signal sorting module is used to sort each first warning signal according to the corresponding sampling time period to obtain the corresponding second warning signal;

[0051] The clustered signal monitoring module is used to determine whether the sampling time periods corresponding to each second warning signal overlap; if the sampling time periods corresponding to each second warning signal overlap, the module counts the first number of sampling time periods corresponding to consecutively overlapping second warning signals; determines whether the first number is greater than a first preset number; if the first number is less than or equal to the first preset number, the module compares the first similarity of the corresponding adverse reaction report sample set; determines whether the first similarity is greater than or equal to a first threshold; if the first similarity is greater than or equal to the first threshold, the module selects any one of the corresponding second warning signals and saves it as a clustered warning signal.

[0052] Furthermore, the aggregation signal monitoring module is also used to perform the following steps:

[0053] If the sampling time periods corresponding to the various second warning signals do not overlap, then the second warning signals are saved as clustered warning signals.

[0054] Furthermore, the aggregation signal monitoring module is also used to perform the following steps:

[0055] If the first similarity is less than the first threshold, then determine whether the first similarity is greater than or equal to the second threshold;

[0056] If the first similarity is greater than or equal to the second threshold, then any one of the corresponding second warning signals is selected and saved as a cluster warning signal, and the remaining second warning signals are saved as historical versions of the cluster warning signal.

[0057] If the first similarity is less than the second threshold, then the corresponding second warning signals will all be saved as cluster warning signals.

[0058] Furthermore, the aggregation signal monitoring module is also used to perform the following steps:

[0059] If the first quantity is greater than the first preset quantity, then determine whether the first quantity is less than the second preset quantity;

[0060] If the first quantity is greater than or equal to the second preset quantity, then any one of the corresponding second warning signals is selected and saved as a cluster warning signal;

[0061] If the first quantity is less than the second preset quantity, then at least one third warning signal with the highest warning level is selected from the corresponding second warning signals;

[0062] Determine whether the sampling time periods corresponding to each of the third warning signals overlap;

[0063] If the sampling time periods corresponding to the various third warning signals do not overlap, then the third warning signals will be saved as clustered warning signals.

[0064] Furthermore, the aggregation signal monitoring module is also used to perform the following steps:

[0065] If the sampling time periods corresponding to each third warning signal overlap, then the second number of sampling time periods corresponding to the third warning signals that have consecutive overlaps is counted.

[0066] Determine whether the second quantity is greater than the first preset quantity;

[0067] If the second quantity is less than or equal to the first preset quantity, then compare the second similarity of the adverse reaction report sample set corresponding to the third warning signal;

[0068] Determine whether the second similarity is greater than or equal to the first threshold;

[0069] If the second similarity is greater than or equal to the first threshold, then any one of the corresponding third warning signals is selected and saved as a cluster warning signal;

[0070] If the second similarity is less than the first threshold, then determine whether the second similarity is greater than or equal to the second threshold;

[0071] If the second similarity is greater than or equal to the second threshold, then any one of the corresponding third warning signals is selected and saved as a cluster warning signal, and the remaining third warning signals are saved as historical versions of the cluster warning signal.

[0072] If the second similarity is less than the second threshold, then the corresponding third warning signals will all be saved as cluster warning signals.

[0073] Furthermore, the aggregation signal monitoring module is also used to perform the following steps:

[0074] If the second quantity is greater than the first preset quantity, then compare the third similarity of the adverse reaction report sample set corresponding to the third warning signal;

[0075] Determine whether the third similarity is greater than or equal to the first threshold;

[0076] If the third similarity is greater than or equal to the first threshold, then any one of the corresponding third warning signals is selected and saved as a cluster warning signal.

[0077] Furthermore, the aggregation signal monitoring module is also used to perform the following steps:

[0078] If the third similarity is less than the first threshold, then the fourth similarity of the adverse reaction report sample sets corresponding to the third warning signals in adjacent sampling time periods is compared.

[0079] Determine whether the fourth similarity is greater than or equal to the first threshold;

[0080] If the fourth similarity is greater than or equal to the first threshold, then any one of the corresponding third warning signals is selected and saved as an aggregation warning signal;

[0081] If the fourth similarity is less than the first threshold, then the corresponding third warning signals will all be saved as cluster warning signals.

[0082] According to a third aspect of the present invention, a drug adverse reaction cluster monitoring device is provided, the device comprising: a processor and a memory;

[0083] The memory is used to store one or more program instructions;

[0084] The processor is configured to run one or more program instructions to perform the steps of a method for monitoring adverse drug reaction clusters as described in any of the preceding claims.

[0085] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program, when executed by a processor, implements the steps of the adverse drug reaction cluster monitoring method as described in any of the preceding claims.

[0086] The embodiments of the present invention have the following advantages:

[0087] This invention discloses a method, system, device, and storage medium for clustered monitoring of adverse drug reactions. First, adverse drug reaction reports are sampled to obtain a corresponding adverse reaction report sample set. Then, warning levels are matched based on preset drug warning rules to generate a corresponding first warning signal. The first warning signals are then sorted to obtain second warning signals. It is determined whether the sampling time periods corresponding to each second warning signal overlap. If so, a first number of consecutively overlapping sampling time periods is counted. If the first number is less than or equal to a first preset number, a first similarity is compared with the corresponding adverse reaction report sample sets. If the first similarity is greater than or equal to a first threshold, any one of the corresponding second warning signals is selected and saved as a clustered warning signal. This invention achieves clustered monitoring of adverse drug reactions, effectively improving the monitoring efficiency and accuracy of adverse drug reaction warnings. Attached Figure Description

[0088] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0089] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0090] Figure 1 is a schematic diagram of the logical structure of a drug adverse reaction cluster monitoring system provided in an embodiment of the present invention;

[0091] Figure 2 is one of the schematic diagrams of the aggregation signal monitoring process provided in an embodiment of the present invention;

[0092] Figure 3 is a second schematic diagram of the aggregation signal monitoring process provided in an embodiment of the present invention. Detailed Implementation

[0093] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. 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.

[0094] Referring to Figure 1, this embodiment of the invention provides a drug adverse reaction cluster monitoring system, which specifically includes: a data sampling module 1, an early warning matching module 2, a signal sorting module 3, and a cluster signal monitoring module 4.

[0095] Furthermore, the data sampling module 1 is used to set the sampling time period and the number of sampling time periods, and to sample the adverse drug reaction reports of the batch of drugs to be monitored within the time period to obtain the adverse reaction report sample set corresponding to each sampling time period.

[0096] Furthermore, the early warning matching module 2 is used to classify and statistically analyze each adverse reaction report sample set, and based on the preset drug early warning rules, match the classification and statistical results to generate the corresponding first early warning signal.

[0097] Furthermore, the signal sorting module 3 is used to sort each of the first warning signals according to the corresponding sampling time period to obtain the corresponding second warning signal.

[0098] Furthermore, the aggregation signal monitoring module 4 is used to determine whether the sampling time periods corresponding to each second warning signal overlap; if the sampling time periods corresponding to the second warning signals overlap, then the first number of sampling time periods corresponding to the second warning signals with consecutive overlap is counted; it is determined whether the first number is greater than a first preset number; if the first number is less than or equal to the first preset number, then the first similarity of the corresponding adverse reaction report sample set is compared; it is determined whether the first similarity is greater than or equal to a first threshold; if the first similarity is greater than or equal to the first threshold, then any one of the corresponding second warning signals is selected and saved as an aggregation warning signal.

[0099] This invention discloses a drug adverse reaction cluster monitoring system. First, drug adverse reaction reports are sampled to obtain a corresponding adverse reaction report sample set. Then, based on preset drug warning rules, warning levels are matched to generate a corresponding first warning signal. Next, the first warning signals are sorted to obtain second warning signals. It is determined whether the sampling time periods corresponding to each second warning signal overlap. If so, a first number of consecutively overlapping sampling time periods is counted. If the first number is less than or equal to a first preset number, a first similarity is compared with the corresponding adverse reaction report sample sets. If the first similarity is greater than or equal to a first threshold, any one of the corresponding second warning signals is selected and saved as a cluster warning signal. This invention achieves cluster monitoring of drug adverse reactions, effectively improving the monitoring efficiency and accuracy of monitoring and warning.

[0100] Corresponding to the adverse drug reaction cluster monitoring system disclosed above, this invention also discloses a method for monitoring adverse drug reaction clusters. The following details a method for monitoring adverse drug reaction clusters disclosed in this invention, in conjunction with the adverse drug reaction cluster monitoring system described above.

[0101] Referring to Figure 2, the specific steps of a method for monitoring adverse drug reaction clusters provided by an embodiment of the present invention will be described below.

[0102] The data sampling module 1 sets the sampling time period and the number of sampling time periods, and samples the adverse drug reaction reports of the batch of drugs to be monitored within the time period to obtain the adverse reaction report sample set corresponding to each sampling time period.

[0103] The above steps specifically include: first, obtaining adverse drug reaction reports for the batch to be monitored within the specified time period; then, setting the sampling time period and the number of sampling time periods; and finally, sampling the adverse drug reaction reports for the batch to be monitored within the specified time period to obtain the adverse reaction report sample set corresponding to each sampling time period.

[0104] For example: If the time period for the batch to be monitored is from January 1, 2022 to March 30, 2022, and the sampling period is set to 30 days with 90 sampling periods, then the sampling periods obtained after sampling are as follows: January 1, 2022 to January 30, 2022; January 2, 2022 to January 31, 2022; January 3, 2022 to February 1, 2022; January 4, 2022 to February 2, 2022; ...; March 31, 2022 to April 29, 2022. Adverse drug reaction reports are collected within each of these sampling periods to obtain the sample set of adverse reaction reports for each sampling period.

[0105] The embodiments of the present invention obtain the sampling time period through the above steps. The start time of adjacent sampling time periods differs by only one day, which can realize comprehensive sampling of all time periods within the time period of the batch to be monitored. Thus, the most accurate cluster signal time period can be found by using the adverse reaction report sample set corresponding to each sampling time period, effectively improving the accuracy of adverse drug reaction monitoring.

[0106] The early warning matching module 2 classifies and statistically analyzes each adverse reaction report sample set, and matches the classification and statistical results based on preset drug early warning rules to generate the corresponding first early warning signal.

[0107] In this embodiment of the invention, the aforementioned preset drug warning rules are specifically shown in Table 1:

[0108] Table 1: Pre-set Drug Early Warning Rules

[0109]

[0110] As shown in Table 1 above, in this embodiment of the invention, the preset drug warning rules specifically include various warning levels and corresponding conditions. The classification statistics specifically include: the number of adverse reaction reports in each sampling time period, the number of adverse reaction reports with serious cases in the sampling time period, and the number of adverse reaction reports with deaths in the sampling time period. By matching the classification statistics with the above preset drug warning rules, the first warning signal can be obtained.

[0111] In this embodiment of the invention, the above-mentioned preset drug early warning rules are used to quantify and statistically classify the adverse reaction report sample sets of each sampling time period, so as to use the corresponding early warning level to screen out the clustered early warning signals in subsequent steps.

[0112] The signal sorting module 3 sorts each first warning signal according to the corresponding sampling time period to obtain the corresponding second warning signal.

[0113] The aggregation signal monitoring module 4 determines whether the sampling time periods corresponding to each second warning signal overlap. If the sampling time periods corresponding to each second warning signal overlap, the first number of sampling time periods corresponding to consecutively overlapping second warning signals is counted. It is then determined whether the first number is greater than a first preset number. If the first number is less than or equal to the first preset number, the first similarity of the corresponding adverse reaction report sample set is compared. It is then determined whether the first similarity is greater than or equal to a first threshold. If the first similarity is greater than or equal to the first threshold, any one of the corresponding second warning signals is selected and saved as an aggregation warning signal.

[0114] For example: the sampling period for the first second warning signal is from January 1, 2022 to January 30, 2022; the sampling period for the second second warning signal is from January 20, 2022 to February 13, 2022; the sampling period for the third second warning signal is from February 1, 2022 to March 2, 2022; and the sampling period for the fourth second warning signal is from March 10, 2022 to April 9, 2022. The sampling periods for the first and second second warning signals overlap between January 20, 2022 and January 30, 2022; the sampling periods for the second and third second warning signals overlap between February 1, 2022 and February 13, 2022; and the sampling periods for the third and fourth second warning signals do not overlap. Furthermore, the three second warning signals overlap consecutively, therefore the first quantity is 3.

[0115] In this embodiment of the invention, the first preset quantity is 2 and the first threshold is 80%.

[0116] Referring to Figures 2 and 3, the above steps specifically include: first, determining whether the sampling time periods corresponding to each second warning signal overlap; if the sampling time periods corresponding to each second warning signal do not overlap, then saving the second warning signal as a clustered warning signal; if the sampling time periods corresponding to each second warning signal overlap, then counting the first number of sampling time periods corresponding to the second warning signals that have consecutive overlap.

[0117] Determine if the first quantity is greater than 2; if the first quantity is less than or equal to 2, compare the first similarity of the corresponding adverse reaction report sample set; determine if the first similarity is greater than or equal to 80%; if the first similarity is greater than or equal to 80%, it indicates that the similarity of the corresponding adverse reaction report sample set is too high, and any one of the corresponding second warning signals can be selected and saved as a cluster warning signal; if the first similarity is less than 80%, determine if the first similarity is greater than or equal to the second threshold, which is 50%; if the first similarity is greater than or equal to 50%, select any one of the corresponding second warning signals and save it as a cluster warning signal, and save the remaining second warning signals as historical versions of the cluster warning signal; if the first similarity is less than 50%, save all the corresponding second warning signals as cluster warning signals; if the first quantity is greater than 2, execute multiple consecutive cross-processing steps.

[0118] The above-mentioned multiple consecutive cross-processing process specifically includes: determining whether the first quantity is less than the second preset quantity, wherein the second preset quantity is 30; if the first quantity is greater than or equal to 30, then selecting any one of the corresponding second warning signals and saving it as a clustered warning signal; if the first quantity is less than 30, then filtering at least one third warning signal with the highest warning level from the corresponding second warning signals.

[0119] Determine whether the sampling time periods corresponding to each third warning signal overlap; if the sampling time periods corresponding to each third warning signal do not overlap, save each third warning signal as a clustered warning signal; if the sampling time periods corresponding to each third warning signal overlap, count the second number of sampling time periods corresponding to the third warning signals that have consecutive overlap.

[0120] Determine if the second quantity is greater than 2; if the second quantity is less than or equal to 2, compare the second similarity of the adverse reaction report sample set corresponding to the third warning signal; determine if the second similarity is greater than or equal to 80%; if the second similarity is greater than or equal to 80%, select any one of the corresponding third warning signals and save it as a clustered warning signal; if the second similarity is less than 80%, determine if the second similarity is greater than or equal to 50%; if the second similarity is greater than or equal to 50%, select any one of the corresponding third warning signals and save it as a clustered warning signal, and save the remaining third warning signals as historical versions of the clustered warning signal; if the second similarity is less than 50%, save all the corresponding third warning signals as clustered warning signals.

[0121] If the second number is greater than 2, then compare the third similarity of the adverse reaction report sample set corresponding to the third warning signal; determine whether the third similarity is greater than or equal to 80%; if the third similarity is greater than or equal to 80%, then select any one of the corresponding third warning signals and save it as a clustered warning signal; if the third similarity is less than 80%, then compare the fourth similarity of the adverse reaction report sample set corresponding to the third warning signals in adjacent sampling time periods.

[0122] Determine if the fourth similarity is greater than or equal to 80%; if the fourth similarity is greater than or equal to 80%, select any one of the corresponding third warning signals and save it as a cluster warning signal; if the fourth similarity is less than 80%, save all the corresponding third warning signals as cluster warning signals.

[0123] In this embodiment of the invention, by utilizing the overlap of the sampling time periods corresponding to each second warning signal, clustered warning signals in which adverse drug reactions occur are screened out from all the second warning signals. This can effectively remove signals with excessively high similarity in the adverse reaction report sample set, thereby ensuring the accuracy of the clustered warning signals.

[0124] This invention discloses a method for clustered monitoring of adverse drug reactions. First, adverse drug reaction reports are sampled to obtain a corresponding adverse reaction report sample set. Then, warning levels are matched based on preset drug warning rules to generate a corresponding first warning signal. Next, the first warning signals are sorted to obtain second warning signals. It is then determined whether the sampling time periods corresponding to each second warning signal overlap. If so, a first number of consecutively overlapping sampling time periods is counted. If the first number is less than or equal to a first preset number, a first similarity is compared with the corresponding adverse reaction report sample sets. If the first similarity is greater than or equal to a first threshold, any one of the corresponding second warning signals is selected and saved as a clustered warning signal. This invention achieves clustered monitoring of adverse drug reactions, effectively improving the monitoring efficiency and accuracy of adverse drug reaction warnings.

[0125] In addition, embodiments of the present invention also provide a drug adverse reaction cluster monitoring device, the device comprising: a processor and a memory; the memory for storing one or more program instructions; the processor for running one or more program instructions to perform the steps of a drug adverse reaction cluster monitoring method as described in any of the preceding embodiments.

[0126] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the adverse drug reaction cluster monitoring method described in any of the preceding embodiments.

[0127] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0128] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0129] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0130] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0131] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0132] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0133] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0134] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A method for monitoring adverse drug reaction clusters, characterized in that, The method includes: setting a sampling time period and the number of sampling time periods; sampling adverse drug reaction reports of the batch of drugs to be monitored within the time period to obtain a sample set of adverse reaction reports corresponding to each sampling time period; classifying and statistically analyzing each sample set of adverse reaction reports; matching the classification and statistical results based on preset drug early warning rules to generate a corresponding first early warning signal; sorting each first early warning signal according to the corresponding sampling time period to obtain a corresponding second early warning signal; determining whether the sampling time periods corresponding to each second early warning signal overlap; if the sampling time periods corresponding to each second early warning signal overlap, counting a first number of sampling time periods corresponding to consecutively overlapping second early warning signals; determining whether the first number is greater than a first preset number; if the first number is less than or equal to the first preset number, then... The method further includes: comparing the first similarity of the corresponding adverse reaction report sample sets; determining whether the first similarity is greater than or equal to a first threshold; if the first similarity is greater than or equal to the first threshold, selecting any one of the corresponding second warning signals and saving it as a clustered warning signal; the method also includes: if the sampling time periods corresponding to each second warning signal do not overlap, saving the second warning signal as a clustered warning signal; if the first similarity is less than the first threshold, determining whether the first similarity is greater than or equal to a second threshold; if the first similarity is greater than or equal to the second threshold, selecting any one of the corresponding second warning signals and saving it as a clustered warning signal, and saving the remaining second warning signals as historical versions of the clustered warning signal; if the first similarity is less than the second threshold, saving all the corresponding second warning signals as clustered warning signals.

2. The method for monitoring adverse drug reaction clusters as described in claim 1, characterized in that, The method further includes: if the first quantity is greater than a first preset quantity, then determining whether the first quantity is less than a second preset quantity; if the first quantity is greater than or equal to the second preset quantity, then selecting any one of the corresponding second warning signals and saving it as a clustered warning signal; if the first quantity is less than the second preset quantity, then filtering at least one third warning signal with the highest warning level from the corresponding second warning signals; determining whether the sampling time periods corresponding to each third warning signal overlap; if the sampling time periods corresponding to each third warning signal do not overlap, then saving the third warning signal as a clustered warning signal.

3. The method for monitoring adverse drug reaction clusters as described in claim 2, characterized in that, The method further includes: if the sampling time periods corresponding to each third warning signal overlap, then counting the second number of sampling time periods corresponding to the third warning signals with consecutive overlap; determining whether the second number is greater than a first preset number; if the second number is less than or equal to the first preset number, then comparing the second similarity of the adverse reaction report sample set corresponding to the third warning signal; determining whether the second similarity is greater than or equal to a first threshold; if the second similarity is greater than or equal to the first threshold, then selecting any one of the corresponding third warning signals and saving it as a clustered warning signal; if the second similarity is less than the first threshold, then determining whether the second similarity is greater than or equal to the second threshold; if the second similarity is greater than or equal to the second threshold, then selecting any one of the corresponding third warning signals and saving it as a clustered warning signal, and saving the remaining third warning signals as historical versions of the clustered warning signal; if the second similarity is less than the second threshold, then saving all the corresponding third warning signals as clustered warning signals.

4. The method for monitoring adverse drug reaction clusters as described in claim 3, characterized in that, The method further includes: if the second quantity is greater than the first preset quantity, then comparing the third similarity of the adverse reaction report sample set corresponding to the third warning signal; determining whether the third similarity is greater than or equal to the first threshold; if the third similarity is greater than or equal to the first threshold, then selecting any one of the corresponding third warning signals and saving it as a clustered warning signal.

5. The method for monitoring adverse drug reaction clusters as described in claim 4, characterized in that, The method further includes: if the third similarity is less than the first threshold, comparing the fourth similarity of the adverse reaction report sample sets corresponding to the third warning signals in adjacent sampling time periods; determining whether the fourth similarity is greater than or equal to the first threshold; if the fourth similarity is greater than or equal to the first threshold, selecting any one of the corresponding third warning signals and saving it as a cluster warning signal; if the fourth similarity is less than the first threshold, saving all the corresponding third warning signals as cluster warning signals.

6. A drug adverse reaction cluster monitoring system, characterized in that, The system includes: a data sampling module, used to set a sampling time period and the number of sampling time periods, and to sample adverse drug reaction reports of the drug batch to be monitored within the time period to obtain a sample set of adverse reaction reports corresponding to each sampling time period; an early warning matching module, used to classify and statistically analyze each sample set of adverse reaction reports, and to match the classification and statistical results based on preset drug early warning rules to generate a corresponding first early warning signal; a signal sorting module, used to sort each first early warning signal according to the corresponding sampling time period to obtain a corresponding second early warning signal; and an aggregation signal monitoring module, used to determine whether the sampling time periods corresponding to each second early warning signal overlap; if the sampling time periods corresponding to each second early warning signal overlap, to count a first number of sampling time periods corresponding to consecutively overlapping second early warning signals; and to determine whether the first number is greater than a first preset number. If the first quantity is less than or equal to the first preset quantity, then compare the first similarity of the corresponding adverse reaction report sample set; determine whether the first similarity is greater than or equal to the first threshold; if the first similarity is greater than or equal to the first threshold, then select any one from the corresponding second warning signals and save it as a clustered warning signal; further includes: if the sampling time periods corresponding to each second warning signal do not overlap, then save the second warning signal as a clustered warning signal; if the first similarity is less than the first threshold, then determine whether the first similarity is greater than or equal to the second threshold; if the first similarity is greater than or equal to the second threshold, then select any one from the corresponding second warning signals and save it as a clustered warning signal, and save the remaining second warning signals as historical versions of the clustered warning signal; if the first similarity is less than the second threshold, then save all the corresponding second warning signals as clustered warning signals.

7. A drug adverse reaction aggregation monitoring device, characterized in that, The device includes: a processor and a memory; the memory is used to store one or more program instructions; the processor is used to run one or more program instructions to perform the steps of the adverse drug reaction cluster monitoring method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the adverse drug reaction cluster monitoring method as described in any one of claims 1 to 5.

Images