AI Powered Clinical Data Standards and Submission Platform

Cutting-edge platform to automate clinical data standards and submission process, driven by Artificial Intelligence framework capable of producing high quality and accurate results

Smart aCRF

Smart Mapper

Define R3

Validator

Smart aCRF

SMART Annotation Repository – A growing body of keywords and annotations pairs (learns, stores, and facilitates re-use of annotations) . Keyword, Annotations and Annotation attributes with Location can be added or modified with ease and saved for re-use. Smart learning within the application and repeat usage augments the repository as the application is used. It Comes preloaded with CDISC/Sponsor defined Metadata, the recommended Text and Annotation attributes.

Preloaded with CDISC/sponsor defined metadata & CDISC recommended text and annotation attributes.

Annotation repository – A growing body of keywords annotation pairs – learns, stores, facilitates Re-Use of annotations

Keywords, annotations, and annotations attributes with location can be added or modified with ease and saved for Re-Use.

Reverse Engineer using existing study annotations to augment repository and Re-Use.

Easy integration of customs/sponsors metadata into database.

Integrated ML/NLP solution for keyword detection and prediction.

Smart Mapper

Smart Mapper module produces mapping specification & SDTM datasets. The input to this module is raw metadata or raw datasets from the EDC. The raw data/metadata collected in the CRF is compared against the SDTM/sponsor defined metadata. The right match will be predicted using Machine Learning. The objective is to predict about 70% of the SDTM variables and have the system trained with the selection from the user for the remaining 30% of the variables. The more studies are used for SDTM mapping in the tool, it’s better for the System to get trained with the model. Once mapping specifications is finalized, the SDTM datasets is generated as per the specification. The system will read the specification and construct programming code. There will be a single standalone program for each SDTM domain based on the mapping specification.

Key Benefits:

Converts studies from raw data model to target SDTM

Auto generates mapping specification for raw data to SDTM Transformation

Provides input to SAS Program for Regeneration of dataset for target model

Integrated ML/NLP solution for keyword detection and prediction

Define R3

Pre-loaded with the CDISC Metadata and Controlled Terminologies. Create Study/Upload XPT’s & Annotated CRF/Process/View as Define.xml – in minutes.

Reverse Engineer Define XML from related studies to extract Study Metadata. Progressively Add XPT’s/Edit Study Metadata/Edit Exception Report and view in Define XML specification format.

View and Edit all Exceptions in place in UI View/Edit all levels of the Study Metadata – Domain, Variable, Value, Where Clause, Code list, External Code list, Computation Methods and Reference Docs in place.

Export the Study Metadata as Excel and Re-Import with changes/corrections Configurable to User requirements.

Key Benefits:

Pre-defined or Customized template for your Study or Submission data

Auto adjustment for linking and formatting in a final document

Validator

The Validator module helps confirm your data compliance standards which will accelerate agency’s (FDA / PMDA) review. Highlighted parts are Data Aptness checks and Compliance Conformation checks. Validator will also assist to set your own customizable Data Review Rules – That is rules to safeguard the quality of the data in addition to regular standard compliance checks.