Ambient Findability: Developing a Flowsheet Ontology for i2B2.

Area of Science:

• Health Informatics
• Biomedical Data Science
• Nursing Informatics

Background:

• Nursing flowsheets often contain redundant and jargon-filled data, hindering research.
• Large volumes of unstructured clinical data pose challenges for secondary data analysis.
• Standardized data ontologies are crucial for interoperability and research.

Purpose of the Study:

• To describe the process of developing a standardized ontology from local nursing flowsheet data.
• To enhance the understandability and usability of nursing flowsheet observations for researchers.
• To facilitate data integration and analysis using a common data model.

Main Methods:

• Importing over 250 million nursing flowsheet observations into an i2b2 (Informatics for Integrating Biology and the Bedside) framework.
• Utilizing focus groups to derive a new, standardized ontology model with 18 identified templates.
• Encoding 100 key patient observation measures (representing 50% of all observations over 36 months) using SNOMED CT (Systematized Nomenclature of Medicine - Clinical Terms).

Main Results:

• A new ontology model was successfully derived, comprising 18 distinct templates.
• 100 critical patient observation measures were encoded using SNOMED CT.
• A significant 78% of the identified concepts were successfully mapped to the standardized ontology.

Conclusions:

• The developed ontology model effectively addresses redundancy and jargon in local flowsheet data.
• Standardization using SNOMED CT significantly improves the interoperability and research potential of nursing observation data.
• This process enables more efficient secondary use of clinical data for research purposes.