Large EMRs can provide data for population cardiac studies

Echocardiogram readings housed in large electronic medical records can be a good resource for researchers hoping to study the link between cardiac structure and function and heart disease, stroke and other cardiovascular diseases and events, according to a recently published study.

The research, published in the Journal of Clinical Bioinformatics, found that while data irregularities abound in the echocardiogram data found in large EMRs, the errors are easily correctable with filters and the data itself was largely complete.

The data can be extracted efficiently from the EMRs, solving some of the time and cost challenges of studying cardiac structure and function traits in large populations, the researchers found. Moving forward, they recommended further study on how to refine the extraction and filtering of semi-structured and unstructured echo data.

Questions about how to turn the data in EMRs into tools for population health management will be an increasing focus of Office of the National Coordinator for Health IT. ONC head Karen DeSalvo said this summer that microdata, including genomics and proteomics, are logical areas for her office to focus on as it shifts away from a heavy emphasis on Meaningful Use of electronic health records.

Right now, only 18 percent of hospitals widely use predictive analytic tools to group patients within a population based on the likelihood that they'll need a health intervention.

For more information:
- here's the study (.pdf)

Suggested Articles

Roche, which already owned a 12.6% stake in Flatiron Health, has agreed to buy the health IT company for $1.9 billion.

Allscripts managed to acquire two EHR platforms for just $50 million by selling off a portion of McKesson's portfolio for as much as $235 million.

Artificial intelligence could help physicians predict a patient's risk of developing a deadly infection.