Clinical research archive management system and method based on digitization

Abstract

The invention relates to the field of archive management, in particular to a clinical research archive management system and method based on digitization, and the system comprises a target clinical archive marking module, an archive data set generation module, a management link chain analysis module, a data feature analysis module and a self-adaptive matching push module. The target clinical archive marking module is used for marking the clinical archive recording the follow-up requirement from the medical database as a target clinical archive; the archive data set generation module is used for generating archive data sets corresponding to different departments in the medical database; the management link chain analysis module is used for constructing a management link chain corresponding to each department data set; the data feature analysis module is used for analyzing whether a management link chain recording different data features exists in a data set of the same department or not; and the self-adaptive matching and pushing module is used for carrying out self-adaptive matching and pushing on the archive management data based on the analysis result.

Description

Technical Field

[0001] The present invention relates to the technical field of archive management, and in particular to a clinical research archive management system and method based on digitization. Background Art

[0002] The rapid development of information technology, especially the maturity of computer technology, network technology and database technology, has provided strong technical support for the construction of clinical research archive management system. These technologies make it possible to manage archive information digitally, networked and intelligently. And with the continuous advancement of medical technology and the increasing number of clinical research projects, the number and complexity of clinical research archives are also increasing. The traditional paper archive management method can no longer meet the needs of modern clinical research, and has disadvantages such as easy loss, difficult query and limited storage space. Therefore, building a scientific, efficient and secure clinical research archive management system has become an important issue in the medical field. The existing technology for the management of clinical research archives is mostly used for data storage and recording, as well as digital call management. Its benefits to archive management are reflected in all aspects. For example, digital archive records can effectively improve the timeliness of follow-up, so that the use of information technology can achieve all-round optimization of patients and hospitals; but at the same time, for the huge amount of archive data in different departments, it is impossible to effectively guarantee the unified standardization and effectiveness of the timeliness of follow-up. That is, for some archive management, it is still necessary to use data analysis to realize the formulation of follow-up plans and the subsequent monitoring of timeliness. Although the timeliness of follow-up is improved compared with paper archives, in the face of digital diversity, an effective characteristic indicator is still needed to ensure the effectiveness and stability of the timeliness of follow-up. Summary of the invention

[0003] The purpose of the present invention is to provide a digital clinical research archive management system and method to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a clinical research archive management method based on digitization, comprising the following analysis steps:

[0005] Step S100: Mark the clinical files that record the follow-up needs from the medical database as target clinical files, extract all target clinical files stored in the same department into a data set; generate file data sets corresponding to different departments in the medical database;

[0006] Step S200: Based on the archive data set, determine the archive management links related to the follow-up needs in the data set of each department; and connect the archive management links related to the follow-up needs according to the time sequence of the historical archive management links, and build a management link chain corresponding to each department data set;

[0007] Step S300: extracting the follow-up data recorded in the data set corresponding to the management link chain, and analyzing whether there is a management link chain with different data features in the data set of the same department;

[0008] Step S400: Adaptively match and push archive management data based on the analysis results.

[0009] Furthermore, step S200 includes the following specific steps:

[0010] Step S210: The archive management link refers to all links of the archive management event record for operating the clinical archive; each generated target clinical archive corresponds to a archive management event, and archive management events with the same management characteristics in each department data set are extracted to generate a feature event set. The same management characteristics means that all the authorized personnel who generate operations in the archive management event record are the same, and the clinical research direction and follow-up content corresponding to the archive are the same;

[0011] The purpose of analyzing the characteristic event set is to prevent the differences in archive management data from being caused by different link characteristics, so that the variables for subsequent analysis of archive management data differences are unified and independent;

[0012] Step S220: extract the follow-up content in each characteristic event set to determine the archive management link when the clinical data to be called is generated, and output the archive management link as the first target link; generate the target link set U by marking the first target link of each archive management event in the characteristic event set, where U = {u1, u2, ..., u n}, where u1, u2, ..., un represent the 1st, 2nd, ..., nth first target links in the target link set;

[0013] Step S230: Perform intersection calculation on the target link set U of each archive management event in the same feature event set to obtain the homologous target link set Z, Z = U1∩U 2. ..∩U m , where U1, U2, ..., U m Represents the 1st, 2nd, ..., mth archive management events in the characteristic event set; the first target link included in the output homologous target link set Z is the archive management link related to the follow-up needs of the corresponding characteristic event set.

[0014] Furthermore, step S300 includes the following specific steps:

[0015] Extract the follow-up data recorded in each characteristic event set. The follow-up data includes the follow-up frequency and the follow-up method. Based on the follow-up frequency, calculate the fluctuation coefficient K, K = (Fmax-Fmin) / N, where Fmax represents the maximum value of the follow-up frequency recorded in the characteristic event set of the same department, and Fmin represents the minimum value of the follow-up frequency recorded in the characteristic event set of the same department; N represents the number of types of follow-up frequencies recorded in the characteristic event set of the same department; follow-up frequencies with the same value represent the same type;

[0016] The follow-up frequencies of each archive management event in different characteristic event sets recorded in the same department are sorted in ascending order to generate a follow-up sequence, and the frequency characteristics are divided with the first follow-up frequency in the follow-up sequence as the starting point and the interval fluctuation coefficient K; if the follow-up sequence is divided into d frequency characteristics, d ≥ 2, then the response signal whose corresponding characteristic event set frequency characteristics are not unique is output; otherwise, the response signal whose characteristic event set frequency characteristics are unique is output;

[0017] And one type of follow-up method corresponds to one type of method feature. When the number of method feature types of each archive management event recorded in the same department with different feature event sets is one, a response signal with a unique method feature is output, otherwise a response signal with a non-unique method feature is output;

[0018] When there are response signals in which the existence mode characteristics or frequency characteristics of each characteristic event set recorded in the same department are not unique, a management link chain recording different data characteristics exists in the characteristic event set of the same department; otherwise, it does not exist.

[0019] Furthermore, step S400 includes the following specific steps:

[0020] When there is no management link chain recording different data characteristics in the same department data set, the corresponding department extracts the corresponding follow-up data for matching response when adding new clinical files;

[0021] When there is a chain of management links that record different data characteristics in the same department data set, use the formula:

[0022] Y=max{[Q1 / Q0] (F,H)};

[0023] Calculate the optimal follow-up index Y of the management link chain corresponding to each characteristic event set; [Q1 / Q0] (F,H) It indicates the follow-up timeliness rate corresponding to the follow-up data under each combination of follow-up frequency F and follow-up mode H, where Q1 indicates the number of feedback records provided by the user within the preset period after the follow-up, and Q0 indicates the total number of follow-ups;

[0024] Extract the follow-up data corresponding to the output optimal follow-up index Y as the adaptive push data of the management link chain;

[0025] When a new clinical file is added to the corresponding department, the historical file management links that have been recorded in the new clinical file are extracted, and the historical file management links are matched with the management link chain in the corresponding department for similarity. The management link chain corresponding to the maximum similarity is extracted as the control link chain, and the adaptive push data recorded in the control link chain is matched and pushed.

[0026] Analyzing adaptive push data can not only save the system time in analyzing users, but also effectively utilize the archive management system to improve the follow-up timeliness rate of similar user archives, so that the digital clinical archive management system can play a greater use value and practical application effect; saving system analysis of follow-up timeliness rate and how to improve the follow-up timeliness rate, effectively saving system analysis resources on the premise of increasing the efficiency of follow-up management in the clinical archive generation stage with huge data volume and the archive management stage.

[0027] A clinical research archive management system based on digitization, including a target clinical archive marking module, an archive data set generation module, a management link chain analysis module, a data feature analysis module and an adaptive matching push module;

[0028] The target clinical file marking module is used to mark the clinical files recording the follow-up requirements from the medical database as target clinical files;

[0029] The archive data set generation module is used to generate archive data sets corresponding to different departments in the medical database;

[0030] The management link chain analysis module is used to construct the management link chain corresponding to each department data set;

[0031] The data feature analysis module is used to analyze whether there is a management link chain that records different data features in the same department data set;

[0032] The adaptive matching and pushing module is used to adaptively match and push archive management data based on the analysis results.

[0033] Further, the management link chain analysis module includes a characteristic event set generation unit, a first target link marking unit, and a homologous target link set calculation unit;

[0034] The characteristic event set generating unit is used to extract the archive management events with the same management characteristics in each department data set to generate a characteristic event set.

[0035] The first target link marking unit is used to extract the follow-up content in each characteristic event set to determine the archive management link when the clinical data to be called is generated, and output the archive management link as the first target link;

[0036] The homologous target link set calculation unit is used to perform intersection calculation on the target link sets of each archive management event in the same feature event set to obtain a homologous target link set, and output the first target link contained in the homologous target link set as the archive management link related to the follow-up needs of the corresponding feature event set.

[0037] Further, the data feature analysis module includes a fluctuation system calculation unit, a follow-up sequence generation unit, a response signal output unit and a data feature classification unit;

[0038] The fluctuation coefficient calculation unit is used to extract the follow-up data recorded in each characteristic event set, the follow-up data includes the follow-up frequency and the follow-up method, and calculate the fluctuation coefficient based on the follow-up frequency;

[0039] The follow-up sequence generation unit is used to sort the follow-up frequencies of various archive management events in the set of different characteristic events recorded in the same department in ascending order to generate a follow-up sequence;

[0040] The response signal output unit is used to output a corresponding response signal based on the frequency characteristics and the mode characteristics;

[0041] The data feature classification unit is used to output a management link chain that records different data features in the feature event set of the same department when there is a response signal that the existence mode features or frequency features of each feature event set recorded in the same department are not unique; otherwise, it does not exist.

[0042] Furthermore, the adaptive matching push module includes an optimal follow-up index calculation unit, a follow-up data extraction unit, and a control link chain push unit;

[0043] The optimal follow-up index calculation unit is used to calculate the optimal follow-up index of the management link chain corresponding to each characteristic event set;

[0044] The follow-up data extraction unit is used to extract the follow-up data corresponding to the output optimal follow-up index as adaptive push data for the management link chain;

[0045] The control link chain push unit is used to extract the historical file management links that have been recorded in the newly added clinical files when the corresponding department adds new clinical files, match the historical file management links with the management link chains in the corresponding department for similarity, extract the corresponding management link chain when the similarity is the largest as the control link chain, and match and push the adaptive push data recorded in the control link chain.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention analyzes the archive management events of different departments, extracts the archive management links that need to be analyzed, and clarifies the optimal follow-up data under each characteristic event set, so as to ensure the efficiency and stability of the timely follow-up rate in a directional manner when facing a large amount of newly added archive data; and the analysis of adaptive push data can not only save the time of system analysis users, but also effectively utilize the archive management system to improve the timely follow-up rate of similar user archives, so that the digital clinical archive management system can play a greater use value and practical application effect; save the problem of system analysis of the timely follow-up rate and how to improve the timely follow-up rate, and effectively save system analysis resources on the premise of increasing the efficiency of follow-up management in the clinical archive generation stage with huge data volume and the archive management stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 It is a structural schematic diagram of a digital clinical research archive management system of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] See also Figure 1 The present invention provides a technical solution: a clinical research archive management method based on digitization, comprising the following analysis steps:

[0051] Step S100: Mark the clinical files that record the follow-up needs from the medical database as target clinical files, extract all target clinical files stored in the same department into a data set; generate file data sets corresponding to different departments in the medical database;

[0052] Step S200: Based on the archive data set, determine the archive management links related to the follow-up needs in the data set of each department; and connect the archive management links related to the follow-up needs according to the time sequence of the historical archive management links, and build a management link chain corresponding to each department data set;

[0053] Step S300: extracting the follow-up data recorded in the data set corresponding to the management link chain, and analyzing whether there is a management link chain with different data features in the data set of the same department;

[0054] Step S400: Adaptively match and push archive management data based on the analysis results.

[0055] Step S200 includes the following specific steps:

[0056] Step S210: The archive management link refers to all links of the archive management event record for operating the clinical archive; each generated target clinical archive corresponds to a archive management event, and archive management events with the same management characteristics in each department data set are extracted to generate a feature event set. The same management characteristics means that all the authorized personnel who generate operations in the archive management event record are the same, and the clinical research direction and follow-up content corresponding to the archive are the same;

[0057] The purpose of analyzing the characteristic event set is to prevent the differences in archive management data from being caused by different link characteristics, so that the variables for subsequent analysis of archive management data differences are unified and independent;

[0058] Step S220: extract the follow-up content in each characteristic event set to determine the archive management link when the clinical data to be called is generated, and output the archive management link as the first target link; generate the target link set U by marking the first target link of each archive management event in the characteristic event set, where U = {u1, u2, ..., u n}, where u1, u2, ..., un represent the 1st, 2nd, ..., nth first target links in the target link set;

[0059] As shown in the embodiment: the determination of the follow-up content needs to be combined with the data recorded in the historical archives, such as the user health data when the file is created, the user monitoring data during treatment, etc., and belongs to the archive management links of different periods; and what is extracted in this application is the archive management link rather than the data;

[0060] Step S230: Perform intersection calculation on the target link set U of each archive management event in the same feature event set to obtain the homologous target link set Z, Z = U1∩U 2. ..∩U m , where U1, U2, ..., U m Represents the 1st, 2nd, ..., mth archive management events in the characteristic event set; the first target link included in the output homologous target link set Z is the archive management link related to the follow-up needs of the corresponding characteristic event set.

[0061] Step S300 includes the following specific steps:

[0062] Extract the follow-up data recorded in each characteristic event set. The follow-up data includes the follow-up frequency and the follow-up method. Based on the follow-up frequency, calculate the fluctuation coefficient K, K = (Fmax-Fmin) / N, where Fmax represents the maximum value of the follow-up frequency recorded in the characteristic event set of the same department, and Fmin represents the minimum value of the follow-up frequency recorded in the characteristic event set of the same department; N represents the number of types of follow-up frequencies recorded in the characteristic event set of the same department; follow-up frequencies with the same numerical value represent the same type; one type of characteristic event set corresponds to one management link chain;

[0063] The follow-up frequencies of each archive management event in different characteristic event sets recorded in the same department are sorted in ascending order to generate a follow-up sequence, and the frequency characteristics are divided with the first follow-up frequency in the follow-up sequence as the starting point and the interval fluctuation coefficient K; if the follow-up sequence is divided into d frequency characteristics, d ≥ 2, then the response signal whose corresponding characteristic event set frequency characteristics are not unique is output; otherwise, the response signal whose characteristic event set frequency characteristics are unique is output;

[0064] As shown in the embodiment: if the interval fluctuation coefficient K is 0.13, the follow-up sequence records the follow-up frequencies as 0.6, 0.75, and 0.8;

[0065] The above follow-up sequence can be divided into two frequency features, one is [0.6, 0.73], the other is (0.73, 0.86], and 0.6 belongs to [0.6, 0.73], 0.75 and 0.8 belong to (0.73, 0.86].

[0066] And one type of follow-up method corresponds to one type of method feature. When the number of method feature types of each archive management event recorded in the same department with different feature event sets is one, a response signal with a unique method feature is output, otherwise a response signal with a non-unique method feature is output;

[0067] When there are response signals in which the existence mode characteristics or frequency characteristics of each characteristic event set recorded in the same department are not unique, a management link chain recording different data characteristics exists in the characteristic event set of the same department; otherwise, it does not exist.

[0068] Step S400 includes the following specific steps:

[0069] When there is no management link chain recording different data characteristics in the same department data set, the corresponding department extracts the corresponding follow-up data for matching response when adding new clinical files;

[0070] The data set of the same department may contain several characteristic event sets, and each characteristic event set contains several archive management events. The different data features to be analyzed in this application are analyzed under the same characteristic event;

[0071] When there is a chain of management links that record different data characteristics in the same department data set, use the formula:

[0072] Y=max{[Q1 / Q0] (F,H)};

[0073] Calculate the optimal follow-up index Y of the management link chain corresponding to each characteristic event set; [Q1 / Q0] (F,H) It indicates the follow-up timeliness rate corresponding to the follow-up data under each combination of follow-up frequency F and follow-up mode H, where Q1 indicates the number of feedback records provided by the user within the preset period after the follow-up, and Q0 indicates the total number of follow-ups;

[0074] Extract the follow-up data corresponding to the output optimal follow-up index Y as the adaptive push data of the management link chain;

[0075] When a new clinical file is added to the corresponding department, the historical file management links that have been recorded in the new clinical file are extracted, and the historical file management links are matched with the management link chain in the corresponding department for similarity. The management link chain corresponding to the maximum similarity is extracted as the control link chain, and the adaptive push data recorded in the control link chain is matched and pushed.

[0076] Analyzing adaptive push data can not only save the system time in analyzing users, but also effectively utilize the archive management system to improve the follow-up timeliness rate of similar user archives, so that the digital clinical archive management system can play a greater use value and practical application effect; saving system analysis of follow-up timeliness rate and how to improve the follow-up timeliness rate, effectively saving system analysis resources on the premise of increasing the efficiency of follow-up management in the clinical archive generation stage with huge data volume and the archive management stage.

[0077] A clinical research archive management system based on digitization, including a target clinical archive marking module, an archive data set generation module, a management link chain analysis module, a data feature analysis module and an adaptive matching push module;

[0078] The target clinical file marking module is used to mark the clinical files recording the follow-up requirements from the medical database as target clinical files;

[0079] The archive data set generation module is used to generate archive data sets corresponding to different departments in the medical database;

[0080] The management link chain analysis module is used to construct the management link chain corresponding to each department data set;

[0081] The data feature analysis module is used to analyze whether there is a management link chain that records different data features in the same department data set;

[0082] The adaptive matching and pushing module is used to adaptively match and push archive management data based on the analysis results.

[0083] The management link chain analysis module includes a characteristic event set generation unit, a first target link marking unit, and a homologous target link set calculation unit;

[0084] The characteristic event set generating unit is used to extract the archive management events with the same management characteristics in each department data set to generate a characteristic event set.

[0085] The first target link marking unit is used to extract the follow-up content in each characteristic event set to determine the archive management link when the clinical data to be called is generated, and output the archive management link as the first target link;

[0086] The homologous target link set calculation unit is used to perform intersection calculation on the target link sets of each archive management event in the same feature event set to obtain a homologous target link set, and output the first target link contained in the homologous target link set as the archive management link related to the follow-up needs of the corresponding feature event set.

[0087] The data feature analysis module includes a fluctuation system calculation unit, a follow-up sequence generation unit, a response signal output unit and a data feature classification unit;

[0088] The fluctuation coefficient calculation unit is used to extract the follow-up data recorded in each characteristic event set, the follow-up data includes the follow-up frequency and the follow-up method, and calculate the fluctuation coefficient based on the follow-up frequency;

[0089] The follow-up sequence generation unit is used to sort the follow-up frequencies of various archive management events in the set of different characteristic events recorded in the same department in ascending order to generate a follow-up sequence;

[0090] The response signal output unit is used to output a corresponding response signal based on the frequency characteristics and the mode characteristics;

[0091] The data feature classification unit is used to output a management link chain that records different data features in the feature event set of the same department when there is a response signal that the existence mode features or frequency features of each feature event set recorded in the same department are not unique; otherwise, it does not exist.

[0092] The adaptive matching push module includes an optimal follow-up index calculation unit, a follow-up data extraction unit and a control link chain push unit;

[0093] The optimal follow-up index calculation unit is used to calculate the optimal follow-up index of the management link chain corresponding to each characteristic event set;

[0094] The follow-up data extraction unit is used to extract the follow-up data corresponding to the output optimal follow-up index as adaptive push data for the management link chain;

[0095] The control link chain push unit is used to extract the historical file management links that have been recorded in the newly added clinical files when the corresponding department adds new clinical files, match the historical file management links with the management link chains in the corresponding department for similarity, extract the corresponding management link chain when the similarity is the largest as the control link chain, and match and push the adaptive push data recorded in the control link chain.

[0096] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0097] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A clinical research archive management method based on digitization, characterized in that: The analysis steps include: Step S100: Mark the clinical files recording the follow-up needs from the medical database as target clinical files, and extract all target clinical files stored in the same department into a data set; Generate a collection of archival data corresponding to different departments in the medical database; Step S200: Based on the archive data set, determine the archive management link related to the follow-up needs in the data set of each department; The archive management links related to follow-up needs are linked in the chronological order of the historical archive management links, and the management link chain corresponding to each department data set is constructed; Step S300: extracting the follow-up data recorded in the data set corresponding to the management link chain, and analyzing whether there is a management link chain with different data features in the data set of the same department; Step S400: Adaptively match and push archive management data based on the analysis results.

2. A digital clinical research archive management method according to claim 1, characterized in that: The step S200 includes the following specific steps: Step S210: The file management link refers to all links of the file management event record for operating the clinical file; each generated target clinical file corresponds to a file management event, and the file management events with the same management characteristics in each department data set are extracted to generate a feature event set, and the same management characteristics refer to the same personnel with the same authority to generate operations in the file management event record and the same clinical research direction and follow-up content corresponding to the file; Step S220: extracting the follow-up content in each characteristic event set to determine the archive management link when the clinical data to be called is generated, and outputting the archive management link as the first target link; The first target link of each archive management event mark in the feature event set is used to generate a target link set U, where U = {u1, u2, ..., u n }, where u1, u2, ..., un represent the 1st, 2nd, ..., nth first target links in the target link set; Step S230: Perform intersection calculation on the target link set U of each archive management event in the same feature event set to obtain the homologous target link set Z, Z = U1∩U 2. ..∩U m , where U1, U2, ..., U m Represents the 1st, 2nd, ..., mth archive management events in the characteristic event set; the first target link included in the output homologous target link set Z is the archive management link related to the follow-up needs of the corresponding characteristic event set.

3. A digital clinical research archive management method according to claim 2, characterized in that: The step S300 includes the following specific steps: Extract the follow-up data recorded in each characteristic event set, the follow-up data includes the follow-up frequency and the follow-up method, and calculate the fluctuation coefficient K based on the follow-up frequency, K = (Fmax-Fmin) / N, where Fmax represents the maximum value of the follow-up frequency recorded in the characteristic event set of the same department, and Fmin represents the minimum value of the follow-up frequency recorded in the characteristic event set of the same department; N represents the number of types of follow-up frequencies recorded in the characteristic event set of the same department; follow-up frequencies with the same value represent the same type; The follow-up frequencies of each archive management event in different characteristic event sets recorded in the same department are sorted in ascending order to generate a follow-up sequence, and the frequency characteristics are divided with the first follow-up frequency in the follow-up sequence as the starting point and the interval fluctuation coefficient K; if the follow-up sequence is divided into d frequency characteristics, d ≥ 2, then the response signal whose corresponding characteristic event set frequency characteristics are not unique is output; otherwise, the response signal whose characteristic event set frequency characteristics are unique is output; And one type of follow-up method corresponds to one type of method feature. When the number of method feature types of each archive management event recorded in the same department with different feature event sets is one, a response signal with a unique method feature is output, otherwise a response signal with a non-unique method feature is output; When there are response signals in which the existence mode characteristics or frequency characteristics of each characteristic event set recorded in the same department are not unique, a management link chain recording different data characteristics exists in the characteristic event set of the same department; otherwise, it does not exist.

4. A digital clinical research archive management method according to claim 3, characterized in that: The step S400 includes the following specific steps: When there is no management link chain recording different data features in the same department data set, the corresponding follow-up data is extracted for matching response when the corresponding department adds a new clinical file; When there is a chain of management links that record different data characteristics in the same department data set, use the formula: Y=max{[Q1 / Q0] (F,H) }; Calculate the optimal follow-up index Y of the management link chain corresponding to each characteristic event set; [Q1 / Q0] (F,H) It indicates the follow-up timeliness rate corresponding to the follow-up data under each combination of follow-up frequency F and follow-up mode H, where Q1 indicates the number of feedback records provided by the user within the preset period after the follow-up, and Q0 indicates the total number of follow-ups; Extract the follow-up data corresponding to the output optimal follow-up index Y as the adaptive push data of the management link chain; When a new clinical file is added to the corresponding department, the historical file management links that have been recorded in the new clinical file are extracted, and the historical file management links are matched with the management link chain in the corresponding department for similarity. The management link chain corresponding to the maximum similarity is extracted as the control link chain, and the adaptive push data recorded in the control link chain is matched and pushed.

5. A clinical research archive management system based on digitization, such as a clinical research archive method based on digitization according to any one of claims 1 to 4, characterized in that: It includes a target clinical archive marking module, an archive data set generation module, a management link chain analysis module, a data feature analysis module and an adaptive matching push module; The target clinical file marking module is used to mark the clinical files recording the follow-up requirements from the medical database as target clinical files; The archive data set generation module is used to generate archive data sets corresponding to different departments in the medical database; The management link chain analysis module is used to construct the management link chain corresponding to each department data set; The data feature analysis module is used to analyze whether there is a management link chain recording different data features in the same department data set; The adaptive matching and pushing module is used to adaptively match and push the archive management data based on the analysis results.

6. A digital clinical research archive management system according to claim 5, characterized in that: The management link chain analysis module includes a characteristic event set generation unit, a first target link marking unit, and a homologous target link set calculation unit; The characteristic event set generating unit is used to extract the archive management events with the same management characteristics in each department data set to generate a characteristic event set. The first target link marking unit is used to extract the archive management link when the clinical data required for the follow-up content determination in each characteristic event set is generated, and output the archive management link as the first target link; The homologous target link set calculation unit is used to perform intersection calculation on the target link sets of each archive management event in the same feature event set to obtain a homologous target link set, and output the first target link contained in the homologous target link set as the archive management link related to the follow-up requirements of the corresponding feature event set.

7. A digital clinical research archive management system according to claim 6, characterized in that: The data feature analysis module includes a fluctuation system calculation unit, a follow-up sequence generation unit, a response signal output unit and a data feature classification unit; The fluctuation coefficient calculation unit is used to extract the follow-up data recorded in each characteristic event set, wherein the follow-up data includes the follow-up frequency and the follow-up method, and calculate the fluctuation coefficient based on the follow-up frequency; The follow-up sequence generating unit is used to sort the follow-up frequencies of each archive management event in the set of different characteristic events recorded in the same department in ascending order to generate a follow-up sequence; The response signal output unit is used to output a corresponding response signal based on the frequency characteristics and the mode characteristics; The data feature classification unit is used to output a management link chain that records different data features in the feature event set of the same department when there is a response signal that the existence mode features or frequency features of each feature event set recorded in the same department are not unique; otherwise, it does not exist.

8. A digital clinical research archive management system according to claim 7, characterized in that: The adaptive matching push module includes an optimal follow-up index calculation unit, a follow-up data extraction unit and a control link chain push unit; The optimal follow-up index calculation unit is used to calculate the optimal follow-up index of the management link chain corresponding to each characteristic event set; The follow-up data extraction unit is used to extract the follow-up data corresponding to the output optimal follow-up index as adaptive push data for the management link chain; The control link chain push unit is used to extract the historical file management links that have been recorded in the newly added clinical files when the corresponding department adds a new clinical file, match the historical file management links with the management link chains in the corresponding department for similarity, extract the corresponding management link chain when the similarity is the largest as the control link chain, and match and push the adaptive push data recorded in the control link chain.

Images