Free EMR Newsletter Want to receive the latest news on EMR, Meaningful Use, ARRA and Healthcare IT sent straight to your email? Join thousands of healthcare pros who subscribe to EMR and EHR for FREE!

Healthcare Analytics Project Works To Predict Preterm Birth

Posted on August 12, 2013 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

A large northern Virginia hospital and a Massachusetts analytics firm are partnering see if data mined from EMRs can better predict the risk of preterm live birth.

The Inova Translational Medicine Institute at Virginia’s Inova Fairfax Hospital is working with Cambridge, MA-based analytics firm GNS Healthcare to create and commercialize computer models to predict the risk of preterm birth, reports Healthcare IT NewsThe two are using next-generation genomic sequencing technology and EMR data to build the models.

The models will be built using ITMI’s large database, which is stocked with data on both normal and preterm family cohorts. GNS will then attempt to link genetic and molecular factors with clinical data and health outcomes, Healthcare IT News said.

Once created, GNS and ITMI will license the models and software — as well as optional access to underlying ITMI data — to academic researchers, health systems and pharma/biotech companies. The ITMI database includes whole genome sequencing (SNP, CNV, SV), RNAseq expression, CpG methylation, proteomic, metabolomic, imaging, EMR, clinical phenotypes and patient survey data for over 2,400 individuals, Healthcare IT News reports.

The two partners are attacking a large problem. As Healthcare IT News notes, 12 percent of babies born in the U.S. are delivered at less than 37 weeks gestation, which causes nearly 10,000 deaths per year and costs $28 billion annually.  Researchers suspect that genetic factors help to prompt preterm birth, though no specific genes have been identified to date.

But there’s many more problems to take on using this approach, and translational medicine projects of this kind are popping up nationally. For example, recently New York’s Mount Sinai Medical Center launched a new program designed to link information stored in the EMR with genetic information provided by patients. As of May, 25,000 patients had signed up for the biobanking program.

I believe this is just the tip of the iceburg. Using EMR data with genomic information is a very logical way to move further in the direction of personalized medicine. I’m eager to see other academic medical centers and hospitals jump in!

Adding Genomic Info to The EMR

Posted on May 15, 2011 I Written By

Katherine Rourke is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

Today I read an interesting blog item making the case for including validated genomic test data in EMRs.  The author argues that with the increasing relevance of genomic testing to treatment, it’s critical to offer clinicians access to such data.

As the author notes, some specialties have already begun to tailor drug treatments to individual patients based on their genomic profile.   For example, DNA sequencing of tumors in non-Hodgkin’s and Mantle Cell lymphoma can lead to personalized cancer vaccines that can produce great results, notes writer Gerry Higgins of the NIH.

Such data can also be used for a growing number of clinical situations, such as tailoring Coumadin doses to specific patients and providing psychiatric patients with the appropriate drug.

However, EMRs currently don’t allow for integrating such data, Higgins notes.  To do so, EMRs will need to accept unstructructed data and make it accessible for analysis  via decision support tools.

Until clinicians demand such data, it’s not likely to become a standard part of EMRs.  To date, while oncologists, pathologists and genetics experts are rapidly becoming aware of the value of these tests, the rest of the medical world is just catching up.

But over time, personalized medical treatments like these will become common. To support these treatments,  EMR systems will need to incorporate the tools and the capabilities needed to build on genomic analysis.  If Higgins is right, EMR vendors should get on this right away.