Our experts simplify the data transformation process, standardize data goals, ensure consistency of attributes, define files and programming specifications, and avoid wastage of time and resources. Our tool also supports SDTM conversion and meets the requirements described in its Implementation Guide and internal standards.
The SDTM (Study Data Tabulation Model) and ADaM (Analysis Data Model) are standards for human clinical trials (research) data tables and non-clinical data tables submitted by researchers to health authorities. The Federation of Clinical data Exchange Standards (CDISC) developed this specification.
ApoGI is AI and meta-data driven solution designed for automation of the end-to-end drug development process. Its data transformation feature automates the generation of datasets in various standard structures like SDTM+/-, SDTM, ADaM, or any other data standard as defined by regulatory authorities.
Our experts simplify the process of converting from SDTM/ADaM to NDA electronic submission, standardize data goals, ensure consistency of attributes for each variable between data sets, define files and programming specifications, and avoid wasting time and resources to verify late consistency.
The programming specification document is a key part of the SDTM conversion process because of its programming and verification capabilities, writing definition PDFs, and defining the generation of the main parts of the XML. There is a great need for a cost-effective way to ensure SDTM conversion meets the requirements described in the SDTM Implementation Guide and internal standards, and to ensure consistency between SDTM data sets, programming specifications, and definition files.
Mapping datasets, e.g., raw to SDTM (or SDTM to ADaM), is a time-consuming task supported by this automation platform. With AI-enabled technology, automapping (or automated generation of dataset specifications to get from source to target) is possible. Additionally, it also becomes increasingly intelligent via guided, supervised learning with use over time, reducing time to generation as well as the QC cycles required. The platform has considered functionalities to automate the process of generating both ADaM and TFLs platform macros and transformational metadata to support ETL-like conversion
