The City of Hope POSEIDON enterprise-wide platform for real-world data and evidence in cancer.

Abstract

e18813 Background: The City of Hope Center for Precision Medicine developed an enterprise-wide platform and precision medicine program to unlock the research potential and clinical value of complex and unique datasets by combining patient data with comprehensive genomic profiling and proprietary analytics. POSEIDON (Precision Oncology Software Environment Interoperable Data Ontologies Network) is a secure, cloud-based Oncology Insights Engine enabling exploration, analysis, visualization, and collaboration on our patient clinico-genomic data along with public data sources. This platform enables investigators to access and visualize data from clinical and multi-omics data and provides an engine that can be utilized for cohort discovery and exploration, preliminary feasibility testing to deriving patient specific insights based on real world data (RWD) and real-world evidence (RWE). Patients are consented through an IRB-approved protocol with active, opt-in participation. Methods: The POSEIDON Common Data Model (PCDM) is a standard, extensible data schema that incorporates patient data to support Precision Medicine. Data are incorporated from disparate data sources and stored in a combined harmonized manner promoting consistency of data and meaning across downstream applications. A multi-step process was created to capture and structure multiple data types into the PCDM. Natural language processing (NLP) tools are deployed to automate and structure valuable data elements from unstructured documents including pathology reports and clinical notes. NLP augmented software tools were developed to assist manual data abstractors to capture more complex terms and disease specific data elements which can include disease progression, progression free survival, and other outcomes. Results: Comprehensive data from 175,000 City of Hope patients are included within this environment for cohort exploration, longitudinal follow-up, outcomes, hypothesis development, and queries for synthetic controls. Data from disease specific-research registries constitute a rich dataset within POSEIDON by disease and tumor type, including lung cancer, colorectal cancer, breast cancer, leukemia, lymphoma and multiple myeloma, among other disease types. Automated genomic workflows were created to gain access to genomic profiling and whole exome sequencing. Genomic data is associated with the clinical data in the PCDM. Automated data flows from the Enterprise Data Warehouse EDW include data that is captured in discrete formats in the EDW and provided for in the PCDM and further enrich the data that flows from the disease registries. Statistically rigorous methods for de-identification are applied for collaborative studies. Conclusions: The City of Hope Center for Precision Medicine and the POSEIDON platform offer an exceptional resource for collaborative RWD & RWE studies.

Integrating Early-Stage Drug Development with Clinical Networks; Challenges and Opportunities: The City of Hope Developing Experience

“…Vendors typically complete the sequencing of specimens within 10–14 days of specimen receipt and deliver test reports directly to the COH electronic medical record as primary BAM, FASTQ, and VCF sequencing files. A centralized electronic data warehouse, POSEIDON, receives copies of the primary BAM, FASTQ and VCF sequencing files [ 36 ]. Data analysts and computational biologists have access to these data files for downstream analysis.…”

Leveraging the Academic Artificial Intelligence Silecosystem to Advance the Community Oncology Enterprise

“…The COH Data Center manages and ensures reliable availability of several petabytes of deidentified clinical and genomic data for AI-related projects. To facilitate AI research and clinical projects, the Data Center relies on an institution-wide data repository, POSEIDON (Precision Oncology Software Environment Interoperable Data Ontologies Network), to house patient clinical and genomic data [334]. AI-assisted natural language processing organizes POSEIDON data according to a Common Data Model to optimize and accelerate downstream data input into AI operational workflows.…”