ODA's framework empowers Causal AI to push beyond the constraints of traditional machine learning accelerating patient outcomes and revolutionizing the healthcare industry.
UCSF Hope Consortium
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.Read more
Children's Cancer Therapy Institute
Children’s Cancer Therapy Development Institute understood correctly diagnosing a rare childhood cancer such as sarcoma can be critical to assigning the correct treatment regimen. With a finite number of pathologists worldwide specializing in pediatric/young adult sarcoma histopathology, access to expert differential diagnosis early in case assessment is limited for many global regions.
CCTDI used the ODA Framework to develop and support a deep learning convolutional neural network (CNN)-based differential diagnosis system to act as a pre-pathologist screening tool that quantifies diagnosis likelihood amongst trained soft-tissue sarcoma subtypes based on whole histopathology tissue slides. The CNN model is trained on a cohort of 424 centrally-reviewed histopathology tissue slides of alveolar rhabdomyosarcoma, embryonal rhabdomyosarcoma and clear-cell sarcoma tumors, all initially diagnosed at the originating institution and subsequently validated by central review.
The ODA Framework and the CNN model was able to accurately classify the withheld testing cohort with resulting receiver operating characteristic (ROC) area under curve (AUC) values above 0.889 for all tested sarcoma subtypes. The positive result demonstrated the potential of machine learning to assist local pathologists in quickly narrowing the differential diagnosis of sarcoma subtype in children, adolescents, and young adults.Read more