A Framework for Aligning Data from Multiple Institutions to Conduct Meaningful Analytics

Area of Science:

• Health Informatics
• Health Services Research
• Data Science

Background:

• Collaborative networks enhance health systems through data sharing and comparative analytics.
• Standardized data collection, quality assessment, and cleansing are essential for meaningful healthcare analytics.
• A framework was developed for aligning data from healthcare delivery systems using a central registry.

Purpose of the Study:

• To present a framework for aligning data from multiple healthcare delivery systems.
• To highlight the importance of data quality assessment in collaborative analytics.
• To demonstrate an effective approach for creating high-quality datasets for cross-institutional analysis.

Main Methods:

• Developed a centralized data registry model with multiple layers of data quality assessment.
• Employed an iterative framework involving clear specifications and stakeholder dialogue.
• Implemented regular checkpoints for assessing data conformance, completeness, and plausibility.

Main Results:

• An iterative communication process is critical for central registries.
• Ensured clarity of data specifications, appropriate data quality, and thorough understanding of data context.
• Engaging diverse stakeholders in decision-making processes supports high-quality dataset development.

Conclusions:

• A standard data specification and submission process is insufficient for aligned data.
• An iterative data quality improvement framework with extensive communication effectively aligns data across institutions.
• This approach supports meaningful comparative analytics for improving healthcare practices.