Method for automatically outputting clinical test report on basis of smart tag, device, and medium

Abstract

The present application discloses a method for automatically outputting a clinical test report on the basis of a smart tag, a device, and a medium. The method comprises: on the basis of clinical test design, constructing a report template to be applied corresponding to automatic output of a clinical test report; identifying, by means of a preset report content identification model, a field to be tagged in the report template to be applied, and determining a tag type corresponding to each field to be tagged, the tag type comprising a table type, a three-section type structure variable tag type, a filter condition type, and an option type; on the basis of the tag type corresponding to each field to be tagged, automatically tagging the report template to be applied, and executing a preset SAS program generation rule to generate a corresponding SAS program on the basis of the tagged report template to be applied; and running the SAS program so as to achieve automatic output of the clinical test report. In the present application, by means of the described method, efficient automatic output of the clinical test report is achieved.

Description

Intelligent marker-based clinical trial report automatic output method, device and medium

[0001] The present application claims priority to the Chinese patent application No. 202410411134.6, filed on April 8, 2024, and entitled "Intelligent marker-based clinical trial report automatic output method, device and medium", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the technical field of medical research and development data analysis, in particular to an intelligent marker-based clinical trial report automatic output method, device and medium. BACKGROUND

[0003] The medical research and development data analysis field is a complex work field across multiple disciplines such as medicine, statistics, computer science, etc. In China, it has been in the ascendant for more than 20 years, and there are few related majors in domestic universities. It needs compound talents, and most of the work still relies on manual work, resulting in a shortage of talents. Medical research and development data analysis has very high quality requirements and very low fault tolerance requirements, and the industry convention usually requires that all calculation results pass through "independent double programming" quality control, i.e., two analysts independently write programs to operate, and the results of the two people must be 100% consistent to pass. Therefore, it is highly dependent on personnel, and a lot of work time is needed to write programs and operate and quality control.

[0004] In terms of clinical trial data submission, with the advent of the electronic submission era, the European Union required pharmaceutical companies to submit in the eCTD (Electronic Common Technical Document) format in 2014, and the US FDA also made a mandatory provision in 2016. CDISC (Clinical Data Interchange Standards Consortium) has developed a number of modules to support clinical data standards over the past 20 years: SEND / SDTM / ADaM / Define.xml. Along with these modules, clinical trial statistical reports based on SAP (Statistical Analysis Plan) are produced. The number of clinical trial reports varies depending on the complexity of the project, ranging from hundreds to thousands. Therefore, the above-mentioned several modules plus clinical trials have become the main and important work tasks of the statistical analysis team of pharmaceutical and CRO companies to meet the submission requirements. Therefore, how to efficiently realize the automatic output of clinical trial reports has become a technical problem to be solved. SUMMARY

[0005] The embodiment of the present application provides a clinical trial report automatic output method, device and medium based on intelligent marking, to solve the following technical problem: how to efficiently realize the automatic output of the clinical trial report.

[0006] In a first aspect, the embodiment of the present application provides a clinical trial report automatic output method based on intelligent marking, and the method comprises the following steps: based on a clinical trial design, a to-be-applied report template corresponding to the clinical trial report automatic output is constructed; through a preset report content recognition model, a to-be-labeled field in the to-be-applied report template is recognized, and a label type corresponding to each to-be-labeled field is determined; wherein the label type comprises a table type, a three-section structure variable label type, a screening condition type and an option type; based on the label type corresponding to each to-be-labeled field, the to-be-applied report template is automatically labeled, and a preset SAS program generation rule is executed to generate a corresponding SAS program based on the labeled to-be-applied report template; and the SAS program is run to realize the automatic output of the clinical trial report.

[0007] In an implementation manner of the present application, through the preset report content recognition model, the to-be-labeled field in the to-be-applied report template is recognized, comprising the following steps: based on a preset field marker pair in the report content recognition model, the to-be-applied report template is matched to determine a plurality of pairs of field markers contained in the to-be-applied report template; and the field in the pair of field markers is determined as the to-be-labeled field.

[0008] In an implementation manner of the present application, the label type corresponding to each to-be-labeled field is determined, comprising the following steps: the field type corresponding to the to-be-labeled field is determined; wherein the field type comprises a table description field, a data input field, a screening condition selection field and an option content field; and based on the field type, the label type corresponding to the to-be-labeled field is determined.

[0009] In an implementation manner of the present application, based on the label type corresponding to each to-be-labeled field, the to-be-applied report template is automatically labeled, comprising the following steps: the field content of the to-be-labeled field is parsed to determine the data type required by the to-be-labeled field based on the field content; based on the data type, the corresponding data storage location information is determined, and the to-be-labeled field is automatically labeled based on the data storage location information and the label rule corresponding to the label type.

[0010] In an implementation form of the present application, the automatic marking of the to-be-marked field based on the marking rule corresponding to the marking type of the data storage location information comprises: in the case that the field type is a table type, defining the data range and table grouping information of the table based on the data storage location information, and defining the calculation rule of the table based on the preset table marking rule, to generate the marking of the table; in the case that the field type is a data input field, defining the three-segment parameter passing structure of the data input field by the preset three-segment naming rule based on the data storage location information, to generate the marking of the data input field; in the case that the field type is a filtering condition selection field, inputting the data storage location information into the preset filtering rule to generate the marking of the filtering condition selection field; in the case that the field type is an option content field, reading the to-be-option information in the data storage location information, and inputting the to-be-option information into the preset option rule to generate the marking of the option content field.

[0011] In an implementation form of the present application, before the preset SAS program generation rule is executed to generate the corresponding SAS program based on the marked to-be-applied report template, the method further comprises: parsing the marked to-be-applied report template to determine the library name and global macro variable required for automatically outputting the clinical trial report corresponding to the to-be-applied report template; loading the running environment based on the required library name and global macro variable.

[0012] In an implementation form of the present application, the execution of the preset SAS program generation rule to generate the corresponding SAS program based on the marked to-be-applied report template comprises: reading the marked to-be-applied report template by using a cross-platform computer programming language to convert the marked to-be-applied report template into a SAS dataset; structuring the SAS dataset, and performing relationship matching between the structured SAS dataset and the macro programs in the preset SAS macro program set, so that the to-be-filled parameters in the structured SAS dataset can be automatically filled; generating the corresponding SAS program of the marked to-be-applied report template based on the relationship matching result.

[0013] In an implementation form of the present application, the method further comprises: defining a marking detection rule to automatically detect the marking after the automatic marking of the to-be-applied report template based on the marking type corresponding to each to-be-marked field; and defining a SAS program detection rule to automatically detect the SAS program after the generation of the corresponding SAS program based on the marked to-be-applied report template.

[0014] In a second aspect, the embodiments of the present application also provide a device for automatically outputting a clinical trial report based on intelligent marking, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: based on a clinical trial design, construct a corresponding to-be-applied report template for automatic output of a clinical trial report; identify to-be-marked fields in the to-be-applied report template by using a preset report content recognition model, and determine a marking type corresponding to each to-be-marked field; wherein the marking type comprises: a table type, a three-part structure variable marking type, a screening condition type, and an option type; based on the marking type corresponding to each to-be-marked field, automatically mark the to-be-applied report template, and execute a preset SAS program generation rule to generate a corresponding SAS program based on the marked to-be-applied report template; and run the SAS program to realize automatic output of the clinical trial report.

[0015] In a third aspect, the embodiments of the present application also provide a nonvolatile computer storage medium for automatically outputting a clinical trial report based on intelligent marking, which stores computer executable instructions, and the computer executable instructions are configured to: based on a clinical trial design, construct a corresponding to-be-applied report template for automatic output of a clinical trial report; identify to-be-marked fields in the to-be-applied report template by using a preset report content recognition model, and determine a marking type corresponding to each to-be-marked field; wherein the marking type comprises: a table type, a three-part structure variable marking type, a screening condition type, and an option type; based on the marking type corresponding to each to-be-marked field, automatically mark the to-be-applied report template, and execute a preset SAS program generation rule to generate a corresponding SAS program based on the marked to-be-applied report template; and run the SAS program to realize automatic output of the clinical trial report.

[0016] The method, device and medium for automatically outputting a clinical trial report based on intelligent marking provided by the embodiments of the present application eliminate the cognitive difference between reviewers and programmers by using the WYSIWYG innovative method, and ensure that the finally generated clinical trial report is consistent with the to-be-applied report template style seen by the reviewers. The machine is used to replace the traditional manual production of SAS programs, which improves the efficiency, strengthens the detail control (including format and layout), reduces the risk of rework or revision, reduces the repetitive work, and ensures the consistency and quality. The method has wide versatility, and any report or report based on document production can be applied. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate certain illustrative embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0018] Figure 1 is a flow chart of a method for automatically generating a clinical trial report based on intelligent marking according to an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of the internal structure of a device for automatically generating a clinical trial report based on intelligent marking according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be described below in detail with reference to the embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0021] The embodiments of the present application provide a method, a device, and a medium for automatically generating a clinical trial report based on intelligent marking, to solve the technical problem of how to efficiently realize automatic generation of a clinical trial report.

[0022] The technical solutions of the embodiments of the present application will be described in detail below with reference to the drawings.

[0023] Figure 1 is a flow chart of a method for automatically generating a clinical trial report based on intelligent marking according to an embodiment of the present application. As shown in Figure 1, the method for automatically generating a clinical trial report based on intelligent marking according to an embodiment of the present application specifically includes the following steps:

[0024] Step 101: Based on a clinical trial design, a to-be-applied report template corresponding to automatic generation of a clinical trial report is constructed.

[0025] In an embodiment of the present application, to realize automatic generation of a clinical trial report based on intelligent marking, a to-be-applied report template corresponding to the automatic generation needs to be constructed first. If a report template that can be directly applied exists in a report template library, a corresponding template can be selected for application. If not, a to-be-applied report template corresponding to the requirements can be constructed according to the clinical trial design.

[0026] Step 102: A to-be-labeled field in the to-be-applied report template is identified by a preset report content recognition model, and a marking type corresponding to each to-be-labeled field is determined.

[0027] In an embodiment of the present application, after constructing a to-be-applied report template corresponding to automatic generation of a clinical trial report based on a clinical trial design, a to-be-labeled field in the to-be-applied report template is identified by a preset report content recognition model.

[0028] The report content recognition model is matched with the to-be-applied report template based on the preset field marker pairs to determine a plurality of field marker pairs contained in the to-be-applied report template; and the fields in the field marker pairs are determined as to-be-labeled fields.

[0029] In one embodiment, the style of the field marker pair can be "[ ]".

[0030] Further, a label type corresponding to each to-be-labeled field is determined. It should be noted that the label type includes a table type, a three-part structure variable label type, a filtering condition type, and an option type.

[0031] A field type corresponding to the to-be-labeled field is determined; and the field type includes a table description field, a data input field, a filtering condition selection field, and an option content field. Based on the field type, the label type corresponding to the to-be-labeled field is determined.

[0032] In step 103, the to-be-applied report template is automatically labeled based on the label type corresponding to each to-be-labeled field, and a preset SAS program generation rule is executed to generate a corresponding SAS program based on the labeled to-be-applied report template.

[0033] In one embodiment of the present application, after the label type corresponding to each to-be-labeled field is determined, the to-be-applied report template is automatically labeled based on the label type corresponding to each to-be-labeled field.

[0034] The field content of the to-be-labeled field is parsed to determine a data type required by the to-be-labeled field based on the field content; a corresponding data storage location information is determined based on the data type; and the to-be-labeled field is automatically labeled based on a labeling rule corresponding to the label type and the data storage location information.

[0035] In one embodiment of the present application, the to-be-labeled field is automatically labeled based on the labeling rule corresponding to the data storage location information and the label type, including: in the case where the field type is a table type, defining a data range and table grouping information of the table based on the data storage location information, and defining a calculation rule of the table based on a preset table labeling rule to generate a label of the table; in the case where the field type is a data input field, defining a three-part parameter passing structure of the data input field by a preset three-part naming rule based on the data storage location information to generate a label of the data input field; in the case where the field type is a filtering condition selection field, inputting the data storage location information into a preset filtering rule to generate a label of the filtering condition selection field; and in the case where the field type is an option content field, reading to-be-option information in the data storage location information and inputting the to-be-option information into a preset option rule to generate a label of the option content field.

[0036] In one embodiment, the table type can define the data range and grouping information of the table after determining the required data storage location information; that is, which variable of which database / dataset is required to define the data range (such as the safety analysis set, marked as ADaM.ADSL.SAFFL{Y}, it is known that the record of the variable SAFFL of the dataset ADSL in the database ADAM should be equal to Y), which variable of which database / dataset is required to define the grouping (such as the trial drug, marked as ADaM.ADSL.TRT01AN, it is known that the value of the variable TRT01AN of the dataset ADSL in the database ADAM should be used for column classification). Further, the calculation content of the table is marked in the table content, that is, which variable of which database / dataset is required for calculation (such as the number of subjects with adverse events during the treatment period related to the study drug, marked as ADAM.ADAE.AEBODSYS|ADAM.ADAE.AEDECOD[SP], it is known that the values of the variables AEBODSYS and AEDECOD of the dataset ADAE in the database ADAM should be used for value calculation).

[0037] It should be further noted that the calculation type of the table includes frequency calculation, classification summary, general statistical quantity calculation, confidence interval and P value statistical analysis, legend (such as survival curve graph, swim plot, spider plot, forest plot, etc.), list, etc. These types almost cover all clinical trial table calculation types required in the clinical research report, for example, [SH] represents a cross analysis table.

[0038] In one embodiment, the naming rule of the three-part structure, that is, <library.dataset.variable>, for example, ADAM.ADSL.RANDFL, indicates that the RANDFL variable of the ADSL dataset in the ADAM database is used.

[0039] In one embodiment, the screening condition type is increased according to the required screening condition, for example, ADaM.ADSL.DCSREAS~=”, which indicates that the record of the DCSREAS variable of the ADSL dataset in the ADaM database is not empty.

[0040] In one embodiment of the present application, after the to-be-applied report template is automatically marked, a preset SAS program generation rule is executed to generate a corresponding SAS program based on the marked to-be-applied report template.

[0041] It should be noted that in application, R language or cross-platform computer programming language can be used instead of SAS to perform core operation related to statistical analysis, that is, a preset R language program or cross-platform computer programming language program is executed to generate rules based on the marked report template to be applied to generate corresponding R language program or cross-platform computer programming language program.

[0042] Step 104, running the SAS program to realize automatic output of the clinical trial report.

[0043] In an embodiment of the present application, after the corresponding SAS program is generated, the SAS program is run to realize automatic output of the clinical trial report.

[0044] In an embodiment of the present application, the method further comprises: defining a marking detection rule to automatically detect the marking after automatically marking the report template to be applied based on the marking type corresponding to each field to be marked; and defining a SAS program detection rule to automatically detect the SAS program after generating the corresponding SAS program based on the marked report template to be applied.

[0045] The above is the method embodiment of the present application. Based on the same inventive concept, the present application embodiment also provides an intelligent marking-based clinical trial report automatic output device, the structure of which is shown in FIG. 2.

[0046] FIG. 2 is a schematic diagram of the internal structure of an intelligent marking-based clinical trial report automatic output device according to an embodiment of the present application. As shown in FIG. 2, the device comprises:

[0047] at least one processor 201;

[0048] and a memory 202 in communication connection with the at least one processor;

[0049] The memory 202 stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor 201 to enable the at least one processor 201 to:

[0050] construct a report template to be applied corresponding to the automatic output of the clinical trial report based on the clinical trial design;

[0051] identify the fields to be marked in the report template to be applied and determine the marking type corresponding to each field to be marked through a preset report content recognition model; wherein the marking type comprises: table type, three-part structure variable marking type, screening condition type, and option type;

[0052] automatically mark the to-be-applied report template based on the mark types corresponding to the to-be-marked fields, and execute preset SAS program generation rules to generate a corresponding SAS program based on the marked to-be-applied report template;

[0053] Run the SAS program to realize automatic output of the clinical trial report.

[0054] Some embodiments of the present application provide a non-volatile computer storage medium corresponding to the intelligent marking-based automatic output of the clinical trial report of FIG. 1, which stores computer executable instructions, and the computer executable instructions are configured to:

[0055] Based on the clinical trial design, a to-be-applied report template corresponding to the automatic output of the clinical trial report is constructed;

[0056] By using a preset report content recognition model, to-be-marked fields in the to-be-applied report template are recognized, and mark types corresponding to each to-be-marked field are determined; wherein the mark types include: a table type, a three-part structure variable mark type, a screening condition type, and an option type;

[0057] Automatically mark the to-be-applied report template based on the mark types corresponding to the to-be-marked fields, and execute preset SAS program generation rules to generate a corresponding SAS program based on the marked to-be-applied report template;

[0058] Run the SAS program to realize automatic output of the clinical trial report.

[0059] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts of each of the embodiments can be referred to each other. Each of the embodiments focuses on the differences from other embodiments. In particular, for the Internet of Things device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0060] The system and medium provided by the embodiments of the present application are one-to-one corresponding to the method, and therefore, the system and medium also have similar beneficial technical effects to the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system and medium will not be described here.

[0061] Those skilled in the art will appreciate that embodiments of the present application can be readily used as software, hardware, or a combination of software and hardware. In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0062] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks or in conjunction with the flowcharts described above.

[0063] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks or in conjunction with the flowcharts described above.

[0064] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks or in conjunction with the flowcharts described above.

[0065] In one typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0066] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, etc. in the form of a computer-readable medium. The memory is an example of computer-readable media.

[0067] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0068] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0069] The above only describes the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for automatically generating clinical trial reports based on intelligent marking, wherein: The method comprises: Based on the clinical trial design, build the corresponding report template to be used for automatic output of clinical trial reports; Identify the fields to be marked in the report template to be applied through a preset report content recognition model, and determine the marking type corresponding to each field to be marked; wherein the marking type includes: table type, three-segment structure variable marking type, filter condition type, and option type; Automatically marking the report template to be applied based on the marking type corresponding to each to-be-marked field, and executing a preset SAS program generation rule to generate a corresponding SAS program based on the marked report template to be applied; Run the SAS program to automatically generate clinical trial reports.

2. A method for automatically generating clinical trial reports based on intelligent marking according to claim 1, wherein: Identifying the fields to be marked in the report template to be applied using a preset report content recognition model includes: Matching the report template to be applied based on the field marker pairs preset in the report content recognition model to determine a number of field marker pairs included in the report template to be applied; The fields in the field marker pair are determined to be fields to be marked.

3. The method for automatically generating clinical trial reports based on intelligent marking according to claim 1, wherein: Determine the tag type corresponding to each field to be tagged, including: Determine the field type corresponding to the field to be marked; wherein the field type includes: form description field, data input field, screening condition selection field, option content field; Based on the field type, a marking type corresponding to the field to be marked is determined.

4. A method for automatically generating clinical trial reports based on intelligent marking according to claim 3, wherein: Automatically marking the report template to be applied based on the marking type corresponding to each field to be marked, including: Parsing the field content of the field to be marked to determine the data type required by the field to be marked based on the field content; Corresponding data storage location information is determined based on the data type, so as to automatically mark the to-be-marked field based on a marking rule corresponding to the data storage location information and the marking type.

5. A method for automatically generating clinical trial reports based on intelligent marking according to claim 4, wherein: Automatically marking the to-be-marked field based on the data storage location information and the marking rule corresponding to the marking type, including: In the case where the field type is a table type, based on the data storage location information, defining the data range and table grouping information of the table, and based on a preset table marking rule, defining a calculation rule of the table to generate a mark for the table; In the case where the field type is a data input field, based on the data storage location information, a three-part parameter passing structure of the data input field is defined by a preset three-part naming rule to generate a tag for the data input field; In the case where the field type is a screening condition selection field, inputting the data storage location information into a preset screening rule to generate a tag of the screening condition selection field; In the case that the field type is an option content field, the candidate option information in the data storage location information is read, and the candidate option information is input into a preset option rule to generate a tag of the option content field.

6. A method for automatically generating clinical trial reports based on intelligent marking according to claim 4, wherein: Before executing a preset SAS program generation rule to generate a corresponding SAS program based on the marked report template to be applied, the method further includes: Parsing the marked report template to be applied to determine the library name and global macro variables required for automatically generating a clinical trial report corresponding to the report template to be applied; Based on the required library names and global macro variables, the runtime environment is loaded.

7. The method for automatically generating clinical trial reports based on intelligent marking according to claim 1, wherein: Executing preset SAS program generation rules to generate a corresponding SAS program based on the marked report template to be applied, specifically including: Reading the marked report template to be applied by using a cross-platform computer programming language to convert the marked report template to be applied into a SAS data set; Structuring the SAS data set, and matching the structured SAS data set with a macro program in a preset SAS macro program set, so that parameters to be filled in the structured SAS data set can be automatically filled in; Based on the relationship matching result, the marked report template to be applied generates a corresponding SAS program.

8. The method for automatically generating clinical trial reports based on intelligent marking according to claim 1, wherein: The method further comprises: defining a tag detection rule to automatically detect the tags after automatically tagging the report template to be applied based on the tag type corresponding to each field to be tagged; and A SAS program detection rule is defined to automatically detect the SAS program after the corresponding SAS program is generated based on the marked report template to be applied.

9. A device for automatically generating clinical trial reports based on intelligent marking, wherein: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Based on the clinical trial design, build the corresponding report template to be used for automatic output of clinical trial reports; Identify the fields to be marked in the report template to be applied through a preset report content recognition model, and determine the marking type corresponding to each field to be marked; wherein the marking type includes: table type, three-segment structure variable marking type, filter condition type, and option type; Automatically marking the report template to be applied based on the marking type corresponding to each to-be-marked field, and executing a preset SAS program generation rule to generate a corresponding SAS program based on the marked report template to be applied; Run the SAS program to automatically generate clinical trial reports.

10. A non-volatile computer storage medium for automatically generating clinical trial reports based on smart tags, storing computer-executable instructions, wherein: The computer executable instructions are configured to: Based on the clinical trial design, build the corresponding report template to be used for automatic output of clinical trial reports; Identify the fields to be marked in the report template to be applied through a preset report content recognition model, and determine the marking type corresponding to each field to be marked; wherein the marking type includes: table type, three-segment structure variable marking type, filter condition type, and option type; Automatically marking the report template to be applied based on the marking type corresponding to each to-be-marked field, and executing a preset SAS program generation rule to generate a corresponding SAS program based on the marked report template to be applied; Run the SAS program to automatically generate clinical trial reports.

Images