Health level seven interoperability strategy: big data, incrementally structured.

Area of Science:

• Health informatics
• Big data analytics
• Clinical data interoperability

Background:

• The Health Level Seven Clinical Document Architecture (CDA) is a foundational standard for US Meaningful Use.
• Current interoperability strategies often face challenges with large, unstructured datasets.
• The need for efficient big data analysis in healthcare is growing.

Purpose of the Study:

• To describe how the HL7 CDA contributes to an "big data, incrementally structured" interoperability strategy.
• To present case studies demonstrating the leverage of CDA for big data analysis.
• To assert that semi-structured narrative in CDA format can aid big data analytics.

Main Methods:

• Two case studies were presented to support the assertion of CDA's utility.
• Case 1: Assessed clinical quality report generation using coded data alone versus coded data supplemented by CDA narrative.
• Case 2: Leveraged CDA to construct a network model for referral management analysis.

Main Results:

• Supplementing coded data with CDA narrative significantly impacted calculated clinical quality performance scores.
• The CDA-derived network model identified distinct patient characteristics across different referral workflows.
• CDA facilitates the flow of narrative data, which is then incrementally structured.

Conclusions:

• The CDA approach indirectly acquires data by prioritizing narrative flow, followed by incremental structuring.
• The growing adoption of CDA is attracting the attention of the big data community for its potential to supply large data volumes.
• Future exercises will quantitatively assess CDA's effectiveness in increasing data flow compared to other methods.