Life-saving therapies to patients in hours - the new algorithmic digital regulatory exchange model.

The growing scale and complexity of pharmaceutical quality data across the product lifecycle are outpacing the capabilities of today's document-centric regulatory paradigm. Current processes are slow, fragmented, and resource-intensive, constrained by unstructured file formats, inconsistent submission standards (eCTD and non-eCTD), and inefficient exchange mechanisms ranging from AS2 gateways to email and physical media. These limitations hinder data accessibility, reuse, and the scalability of regulatory review. Anderson et al. (2023) previously proposed a vision for real-time, data-driven regulatory exchange enabled by structured standards and interoperable digital infrastructure. However, practical implementation has remained largely theoretical. Here, we demonstrate that the concepts described in the prior work are both feasible and operational. In the present work, we describe a reference model that can support broader adoption. Using the Health Level Seven (HL7) Fast Healthcare Interoperability Resources (FHIR®) framework, structured data models were developed to connect heterogeneous sponsor systems, including both integrated and non-integrated environments. Chemistry, Manufacturing, and Controls (CMC) data were transformed into FHIR-conformant, machine-readable resources and exposed via standardized application programming interfaces (APIs), enabling automated assembly of regulatory submission content. Once represented as structured, interoperable data, regulatory information becomes a foundation for advanced analytics and artificial intelligence (AI). AI models can analyze content, generate potential regulatory questions, and support response development by querying authoritative data sources. This FHIR-based interoperability approach can enable timely data-centric regulatory workflows to reduce manual effort, improve efficiency, and ultimately accelerate patient access to high-quality innovative medicines.