Some experiences and opportunities for big data in translational research

Area of Science:

• Bioinformatics
• Health Informatics
• Genomics

Background:

• Healthcare is increasingly information-intensive, with genomic data adding significant complexity.
• Translational research now operates in a data-intensive environment, often termed 'big data'.
• Advances in computing allow affordable management and processing of big data for academic research.

Purpose of the Study:

• To explore the challenges and opportunities of big data in translational research.
• To highlight the role of data standards in managing clinical data complexity.
• To demonstrate how data standards facilitate clinical application of big data.

Main Methods:

• Leveraging insights from the Electronic Medical Records and Genomics consortium.
• Utilizing advances in commodity computing for big data processing.
• Examining the impact of emerging data standards on clinical data consistency.

Main Results:

• Big data methods offer great promise but face challenges due to clinical data heterogeneity.
• Existing and emerging data standards enhance comparability and consistency of clinical information.
• Meaningful Use data standards simplify identifying clinical phenotyping patterns in electronic health records.

Conclusions:

• Data standards are essential for overcoming the challenges of big data in healthcare.
• Standardization facilitates the integration of genomic data and enhances clinical decision-making.
• The effective use of big data, supported by standards, is key to advancing translational research.