Developing electronic data methods infrastructure to participate in collaborative research networks.

Area of Science:

• Health Informatics
• Health Services Research
• Data Science

Background:

• Collaborative networks are vital for learning health systems, enabling data sharing and analysis to identify best practices.
• This case study details the infrastructure and processes an integrated health system used for a complex data submission.

Purpose of the Study:

• To describe the development of infrastructure and processes for preparing and submitting a large, complex dataset to a national collaborative network.
• To highlight the key components and challenges of large-scale data submission within a healthcare setting.

Main Methods:

• Submitted four years of data across clinical areas including diabetes, heart failure, sepsis, and orthopedic procedures.
• Extracted data from multiple clinical and administrative systems, encompassing over 376,000 patients and 5 million encounters.
• Implemented a formal quality assurance (QA) and feedback process for data tracking and review.

Main Results:

• A structured process, emphasizing an experienced project team, thorough documentation, and clear communication, was essential for managing timelines and data quality.
• The data submission was resource-intensive, requiring an incremental approach to ensure data quality.
• A formal QA and feedback loop was utilized for data review and refinement.

Conclusions:

• Effective data submission to collaborative networks requires a robust, structured approach with dedicated resources.
• Participation in such networks, despite being resource-intensive, can significantly enhance a learning health system's data capabilities.
• Key success factors include an experienced team, comprehensive documentation, and consistent communication.