The Inova Translational Medicine Institute at Virginia's Inova Fairfax Hospital and Cambridge, Mass.-based analytics firm GNS Healthcare are partnering to develop and commercialize computer models to predict the risk of preterm live birth.
Using next-generation sequencing technology and electronic medical record data, GNS and ITMI will license the models and corresponding software to academic researchers, health systems and pharmaceutical/biotechnology companies, officials say, in an effort to enable more effective diagnosis of the risk of preterm birth.
In the United States, 12 percent of babies are born at less than 37 weeks gestation, which causes nearly 10,000 deaths and costs as much as $28 billion per year. The causes of preterm birth are complex and often unknown; genetics are thought to play a role, but no individual genes have yet been identified as causative.
"We have 826 families in our preterm birth study with 285 babies born at less than 37 weeks of gestation," said John Niederhuber, executive vice president of Inova Health System and chief executive officer of ITMI, in a press statement. "Partnering with our colleagues at GNS provides the best opportunity to build a risk assessment/predictive model that takes into account the many variables, including genomic, clinical, environmental and behavioral factors, that combine to cause a preterm delivery."
Together, Inova and GNS will work toward commercial availability of the preterm birth predictive models and corresponding software – including optional access to the underlying ITMI data, officials say.
The models will be built from ITMI's massive database, which includes both normal birth and preterm birth family cohorts, using GNS's data analytics platform, REFS, or Reverse Engineering and Forward Simulation, and will link genetic and molecular factors with clinical data and health outcomes.
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. These models will characterize the complex relationships among many variables in order to identify the associations and underlying causal mechanisms of preterm birth and will allow for personalized prediction of preterm birth risk and gestational length.
This, in turn, will help prioritize the testing of potential new diagnostic and treatment plans for at-risk patients, officials say.
Using this preterm birth genomic data set, "We will build models that can document the complex interactions underlying preterm birth," said Colin Hill, CEO and co-founder of GNS Healthcare, in a press statement. "These models will create new ways for clinicians and scientists to understand these interactions and will accelerate the discovery of new diagnostic tools and treatments for this condition, as well as other complex conditions."