Applying SDTM/CDISC Standards for Automated Regulatory Compliance in FDA Submissions

In the evolving landscape of clinical research and regulatory affairs, the application of artificial intelligence (AI) to automate Study Data Tabulation Model (SDTM) compliance, as mandated by the Clinical Data Interchange Standards Consortium (CDISC) and required by the U.S. Food and Drug Administration (FDA), is becoming increasingly critical.This review explores the methodologies, tools, and models employed to automate SDTM mapping and validation processes.By evaluating rule-based engines, machine learning (ML) algorithms, and deep learning techniques, the study provides a comprehensive analysis of their effectiveness, accuracy, and compliance with regulatory standards.The paper also presents a theoretical model, experimental results, and industry case studies.Challenges such as data heterogeneity, lack of transparency, and auditability are discussed alongside strategic solutions.Future directions highlight the importance of explainable AI, interoperability, and regulatory acceptance of AI-assisted data standardization.This work aims to guide researchers, developers, and regulatory professionals in optimizing AI applications for SDTM/CDISC compliance.