Tables, Listings, and Figures (TLFs) help to analyse and summarize datasets of a clinical study into an easily readable format. Statistical programmers along with inputs from biostatisticians create these TLFs. Once Lead statistician review/validate them, medical writers use the TLFs to create documents like clinical study reports (CSRs). Some TLFs are straight forward and easy to interpret, while others may require writing an extensive discussion to explain them. In addition to their value in CSRs, TLFs are used to answer regulatory questions and support publications based on the clinical data contained in them.
Creating TLFs is a tiresome process that involves frequent quality checks to verify the validity of the included information. In addition to that, medical writers could request changes in the outputs, which requires additional time to rewrite the code that produced the TLF documents. This means new rounds of validation and quality checks to confirm the correctness of the new outcome. All these processes lead to delays in delivering the final CSR to health authorities. The outcome is a considerable lag phase in providing life-saving medications and treatments to those needing them the most. There is a need to speed up this process and here automation can play a crucial role in creating and managing “Table, Listings and Figures” in clinical trials.
Here are several reasons highlighting the importance of TLFs automation:
- Efficiency and Time savings:
Automation significantly reduces the time and effort required to create and update the TFLs. This is especially important in research and technical writing, where large datasets and numerous visuals are common.
- Consistency
Automated process contributes to the standardization of data preparation. Table and Figures generated through automation adhere to predefines templates and formatting standards. The consistency is crucial for ensuring that data is presented uniformly across different stages of TLF generation such mock shells, outputs and supporting documents.
- Accuracy
Automation reduces the risk of human error in data entry, calculation, and analysis. This is a critical in clinical trials where data accuracy and integrity are paramount. Automation can minimize the chances of transcription error or miscalculation, ensuring the reliability of TLFs generation
- Data Integrity
It encompasses the maintenance and assurance of the accuracy and consistency of data over its entire TLFs generation process. In the realm of automation testing, ensuring data integrity translates to guaranteeing the quality and credibility of testing processes.
- Reduced Workload and Resource optimization
By automating repetitive and time-consuming tasks in TLF generation such as generating mock shells, aligning the layouts, writing code for displaying the analysed results, data extraction and other similar tasks, researchers can optimize their workload. This not only enhances overall productivity but also allows researchers to allocate their time and resources more strategically to focus on critical aspects of the interpreting the results.
- Regulatory Compliance
Clinical trials are subject to strict regulatory requirements. Automation helps in maintaining compliance by ensuring that data is handled consistently and transparently. Automated tools can generate audit trails and documentation necessary for regulatory submissions.
- Facilitation and Collaboration
Automation enables seamless collaboration among members of the research team. With standardized and readily accessible TLF’s, researchers can collaborate more effectively, share insights, and make informed decisions collectively.
Let see, At GenInvo how we are using automation to generate Table, Listing and Figures. GenInvo has leveraged use of Machine Learning to develop tool (ApoGI™) which offer a robust TLF Module to generate mock shell and associated TLFs. This tool is one of the best automation tools out there in market these days. This tool utilizes artificial intelligence with the technologies to go through thousands of layers of inputs and data to create TLFs.
ApoGI™ – Table, Listing and Figures (TLF) Module
The ApoGI™ – TLF module comprises of two sub modules.
Mock Shell Generator – This sub-module supports generation of mock shells with automation directly by scraping Protocol and SAP documents automatically. Below mentioned are few steps to explain How mock shells generation works in the tool.
- One can choose the type of TLFs from different available options such as, Summary Table, Vital Sign Table, Demographics Table, AE Laboratory listings, Laboratory Listings, Box Plot Figures and many more.
- Then select the required Protocol and SAP documents.
- TLF Module then runs a smart AI/ML algorithm over the documents to capture the necessary matching details based on TLF type selected in first step to generate the shells. This reduces most of the manual effort of designing the shells.
- Tool support mock shell repository to maintains the generated shell with versioning feature.
TLF Report Generator – This sub-module plays a vital role in TLFs output generation. Below mentioned are few steps to explain how TLF generation works.
- Choose the generated ADaM dataset (GenInvo has an innovative solution to generate ADaM dataset. See ApoGI-DT™ as input data to use in TLF output generation.
- Tools allows to choose the requested TLF from wide variety of repository.
- Tools allows to set up general and standard settings for proper display of layout with their relevant mock shells.
- Finally, tool will run the automation algorithm to generate the requested TLFs.
- The generated TLFs can be exported individually or as single combined file in multiple format (i.e. PDF, RTF, MS-Word) along with their source programming codes, log files etc.
Benefits of using ApoGI™ – Table, Listing and Figures (TLF) Module
- Generate TLFs in click of button that are compliant with regulations
- No programming experience needed
- Update titles and footnotes and other general display text with ease
- Reduce/eliminate bottle-neck processes like frequent changes and quality checks when coding, creating, updating, and validating TLFs
- Accelerate regulatory submission to health authorities
By Amit Gupta, Technical Lead- Software Development
