Demo: How to use DISQOVER for IDMP submission

The video provides a practical demonstration of how the DISQOVER platform, configured as a knowledge graph, facilitates the complex data aggregation and retrieval necessary for ISO IDMP (Identification of Medicinal Products) regulatory submissions. The presenter establishes the platform's utility by showcasing its ability to integrate diverse data sources—including public databases, text-mined Summary of Product Characteristics (SmPC) documents from providers like Averbis, and referential master data from organizations like IMA. This consolidation is crucial because IDMP requires linking vast amounts of structured and unstructured data about medicinal products to ensure global regulatory harmonization.

The demonstration walks through a specific use case: exploring medicinal products related to HIV infection. Users begin by filtering the medicinal product category, refining the search based on the condition (HIV infection) and the active substance (e.g., Emtricitabine). The platform instantly updates the results, displaying detailed information for specific formulations (e.g., hard capsule vs. oral solution). A key feature highlighted is the ability to preview and download regulatory documents, such as the EMA SmPC, directly within the platform interface, thereby streamlining the process of gathering required submission materials.

Furthermore, the demo emphasizes the platform's capabilities in handling controlled vocabularies and multilingual data, which are essential components of IDMP compliance. The presenter shows how dosage forms are mapped to specific controlled vocabulary terms, complete with term IDs and defined relationships to parent terms (e.g., linking a specific solution term to the broader 'solution' category). Crucially, the system lists all available language translations for specific data points, allowing users to filter and access necessary localized regulatory information, such as the German translation for an oral solution. Finally, the demonstration underscores the critical importance of data provenance; every piece of information within the Knowledge Graph is tagged with its original source, ensuring a perfect audit trail and allowing users to consolidate and visualize private and public data seamlessly, supporting both regulatory submission and downstream activities like exploring associated Adverse Events.

Key Takeaways:

• IDMP Data Aggregation Challenge: The DISQOVER platform is specifically configured to address the data complexity of IDMP submissions by consolidating disparate data sources, including public data, text-mined regulatory documents (SmPC), and internal master data, which is essential for meeting EMA and FDA requirements.
• Knowledge Graph Foundation for Compliance: Utilizing a Knowledge Graph structure allows regulatory and data teams to efficiently navigate complex relationships between medicinal products, active substances, indications (e.g., HIV infection), and dosage forms, ensuring comprehensive data compilation for IDMP.
• Regulatory Document Access Integration: The platform provides immediate, integrated access to critical regulatory documents, such such as the EMA SmPC, allowing users to preview and download them directly from the detailed product view, significantly accelerating the submission preparation workflow.
• Controlled Vocabulary Management: Essential for IDMP, the platform demonstrates the capability to map dosage forms to specific controlled vocabulary terms, including the association of term IDs and the definition of hierarchical relationships to parent terms, ensuring data standardization.
• Multilingual Compliance Support: The system supports global regulatory requirements by listing and allowing filtering of all available language translations for specific data points (e.g., dosage forms), which is vital for submissions to multiple regulatory bodies outside of the primary market.
• Data Provenance and Auditability: Every piece of information within the Knowledge Graph is meticulously tagged with its original data source (e.g., Averbis or IMA), providing a perfect overview of data provenance, which is critical for maintaining regulatory compliance and audit trails (e.g., 21 CFR Part 11).
• Consolidation of Private and Public Data: The platform enables the seamless integration and visualization of proprietary internal data alongside external public reference data, allowing users to focus on a single entity (like an active substance) and view all associated information regardless of its origin.
• Efficient Data Filtering and Discovery: The demonstration highlights the ability to apply multiple sequential filters—first by condition (HIV infection) and then by active substance (Emtricitabine)—to quickly narrow down the list of medicinal products requiring IDMP data compilation.
• Downstream Application Potential: Beyond submission preparation, the consolidated and structured data foundation supports further exploration, such as linking active substances to reported Adverse Events, demonstrating the utility of the Knowledge Graph for pharmacovigilance and safety monitoring.

Tools/Resources Mentioned:

• DISQOVER Platform: A knowledge graph technology platform used for data discovery and aggregation.
• Averbis: A provider mentioned for supplying text-mined SmPC documents.
• IMA: A source mentioned for providing referential master data.

Key Concepts:

• IDMP (Identification of Medicinal Products): A set of five ISO standards defining the globally harmonized identification and exchange of information on medicinal products, crucial for regulatory bodies like the EMA and FDA.
• Knowledge Graph: A structured data model that uses nodes (entities) and edges (relationships) to represent complex, interconnected information, making data discovery and integration highly efficient for regulatory data management.
• SmPC (Summary of Product Characteristics): A regulatory document approved by the competent authority (e.g., EMA) that contains essential, detailed information about a medicinal product.
• Data Provenance: The record of where data originated and how it has been processed, which is a critical requirement for regulatory compliance and data integrity in the life sciences sector.