OP138 USE OF ARTIFICIAL INTELLIGENCE (ML/NLU/NLP/NLG) IN REGULATORY(SCIENTIFIC) DOCUMENTS AUTHORING.

Aim: Demonstrating the validated tool to compress CSR writing time with capabilities that facilitate data retrieval from multiple sources to assist in compilation, evaluation and interpretation of information that supports the content development Method: Generates the pre-filled CSR automatically using AI techniques such as ML/NLP/NLG. Most of the CSR content assembled from source documents such as protocol, SAP etc. The tool automatically writes the CSR content from the documents mentioned above. Results / Discussion: Creating Regulatory documents such as eCTD modules 2.7.3 & 2.7.4 (Clinical summary efficacy & safety respectively), Investigator brochure, Clinical Study Report (CSR) etc., is highly manual and time consuming for medical writers. Good percentage of contents for the above-mentioned documents comes from various source documents such as Protocol, SAP, Safety Narratives, In-text tables, Integrated summary of safety and efficacy etc. Automating these scientific documents writing by utilizing AI techniques such as ML and Natural language processing/understanding /Generation (NLP/NLU/NLG) will reduce the efforts significantly. This paper will demonstrate the tool that we developed for automating the scientific document to CSR writing by using Artificial Intelligence (AI) techniques. The CSR template follows the ICH-E3 guideline, and the tool can also accommodate sponsor-defined templates. Conclusion: The benefits of this application are lean writing, multi-person authoring, Traceability report, Interpretation of tables in simple English, Post-text to In-text table conversion, authoring safety narratives and Integration of sponsors workflow. The author can visualize the consolidated comments and edits from multiple reviewer(s) in one place. These features can save lot of time for medical writers so that, they can focus on discussion points and interpretation of study results. [ABSTRACT FROM AUTHOR]