Hope leverages the ODA framework to prevent preterm births.
By using ODA’s framework, the UCSF Hope Consortium managed all data from its study – from EHR, wearables, multiple “omics” and others – allowing for effective analysis.
UCSF’s Hope Consortium conducted a study on the causes of premature birth for a demographic it serves. The scope of the study entailed storing, managing and analyzing data from pregnant women, including surveys, social determinants, FitBits, clinical charts, biospecimen analyses and other such data.
Enter ODAs framework: set up on a local cloud, our framework managed both structured and unstructured data for the study. Data also came from several “omics”, all which seamlessly worked with the framework.
ODA’s framework offered several analysis pipelines: clustering, prediction, and causal analysis. Not only did the framework and federation learning leverage the data to make predictions, but it also sifted through data to find the cause of the preterm births through causal analysis.
As a result of employing ODA’s framework, the study achieved its goal: create data driven preventive care programs to decrease pregnancy hospitalization, reducing hospital preterm birth costs. Further, the partnership allowed the study to provide population health data insights to enable scalable prenatal personalized care.