Interoperability of Genomic Data Standards: Translations Between HL7 FHIR Molecular Definition Resource and GA4GH Variation Representation Specification

Presentation Time: 01:30 PM - 02:00 PM

Abstract Keywords: Data/System Integration, Standardization and Interoperability, Data Standards, FHIR
Primary Track: Clinical Research Informatics
Programmatic Theme: Novel Methods for Variant Detection and Interpretation from Omics Data

Alignment of HL7 and Global Alliance for Genomics and Health (GA4GH) standards is essential to bridge gaps in interoperability. We produced semantic and technical mappings between the HL7 FHIR Molecular Definition (MolDef) and GA4GH Variation Representation Specification (VRS) 1.3 standards as an ongoing effort to achieve automated bidirectional translations. Our system demonstration will present this tooling with examples and discuss how the translations can be utilized in other applications.
Speaker(s):
Robert Freimuth, PhD
Mayo Clinic

Author(s):
Salem Bajjali, Master of Science - Mayo Clinic; Aly Khalifa, Ph.D. - Mayo Clinic; Sarah Senum, M.S. - Mayo Clinic; Xianfeng Chen, Ph.D. - Mayo Clinic; Robert Freimuth, Ph.D. - Mayo Clinic;

Creating Gold Standard Data for Cancer Research: The Curation Assistance Tool for Transforming Unstructured Clinical Text into Machine Learning-Ready Datasets

Presentation Time: 02:00 PM - 02:30 PM

Abstract Keywords: Clinical and Research Data Collection, Curation, Preservation, or Sharing, Collaborative Workflow Systems, Data Quality, Enterprise Data Warehouse/Data Lake, Ontologies, Natural Language Processing
Working Group: Natural Language Processing Working Group
Primary Track: Data Science/Artificial Intelligence
Programmatic Theme: Proactive Machine Learning in Biomedical Applications: The Power of Generative AI and Reinforcement Learning

Memorial Sloan Kettering’s Curation Assistance Tool (CAT) transforms unstructured clinical text into high-quality, standardized datasets. Integrating with REDCap and standard terminology, CAT enables researchers to create gold standard data for machine learning models. This streamlines cancer research by enhancing data quality, model performance, and collaboration across teams.
Speaker(s):
Andrew Niederhausern
MSKCC

Author(s):
John Philip, MS - Memorial Sloan Kettering Cancer Center; Javier Villarreal Almanza; Nadia Bahadur, Masters of Clinical Research - Memorial Sloan Kettering Cancer Center; Tatyana Sandler - Flatiron Health; Tatyana Sandler, MS, RN - MSKCC;

Scalable Deployment of OHDSI ATLAS for Supporting Self-Service Data Science Capabilities Across Multi-Institutional Clinical Research Network

Presentation Time: 02:30 PM - 03:00 PM

Abstract Keywords: Data-Driven Research and Discovery, Enterprise Data Warehouse/Data Lake, Advanced Data Visualization Tools and Techniques
Primary Track: Clinical Research Informatics
Programmatic Theme: Health Data Science and Artificial Intelligence Innovation: From Single-Center to Multi-Site

This system demonstration presents a scalable deployment of OHDSI ATLAS to support self-service data science across the Greater Plains Collaborative (GPC) Clinical Research Network using the PCORnet Common Data Model (CDM). Leveraging cloud infrastructure with AWS and Snowflake, the system dynamically harmonizes OMOP and PCORnet CDMs in real time, enabling secure, federated data sharing. The deployment empowers researchers with advanced analytics capabilities while maintaining compliance with data governance standards and supports real-time data exploration and cohort generation.
Speaker(s):
Abu Mosa, PhD, MS, FAMIA
University of Missouri School of Medicine

Author(s):
Vasanthi Mandhadi, Masters - University of Missouri; Md Saber Hossain; Md Kamruz Zaman Rana, MSHI - University of Missouri - Columbia; Md Soliman Islam, M.Sc; Yaswitha Jampani - University of Missouri - Columbia; Shaun Ferguson, BS - University of Missouri Kansas City; Lemuel Waitman, PhD - University of Missouri;