A multi-technique approach to bridge electronic case report form design and data standard adoption

Area of Science:

• Clinical Informatics
• Biomedical Data Standards
• Health Data Management

Background:

• Integrating clinical research data requires robust data standards for harmonization and sharing.
• Common Data Elements (CDEs) are crucial for data standardization but adopting them in eCRF design faces methodological barriers.

Purpose of the Study:

• To demonstrate a novel approach for designing data standard-compliant electronic case report forms (eCRFs).
• To facilitate the adoption of data standards in clinical research through an automated eCRF design process.

Main Methods:

• A multi-technique approach combining information retrieval, natural language processing, and an ontology-based knowledgebase.
• Utilizing research questions as queries to retrieve and associate relevant CDEs for eCRF construction.

Main Results:

• The CDE-based eCRF builder achieved a precision of 0.84, recall of 0.80, and F-measure of 0.82.
• Successfully provided suggested CDEs for 88.8% of test questions with 90.3% accuracy.

Conclusions:

• The developed approach effectively overcomes barriers to data standard adoption in eCRF building.
• The CDE-based form builder offers a practical solution for data standard-compliant eCRF design.