Health Data Inovation Program (HDIP)

The Health Data Innovation Program is a collaboration between Keck Medicine of USC, Keck School of Medicine, and USC aimed at providing robust research, operational data, and digital platform to bring innovation to the patient's bedside.

Active focus Data to practice Applied research across clinical systems, imaging, outcomes, and population health.

Leadership

Portrait of Alen Oganesyan

Alen Oganesyan

Associate Chief Information Officer

Portrait of Laura Madsen

Laura Madsen

Administrator Enterprise Data, Analytics and AI

Portrait of Jose-Luis Ambite

Jose-Luis Ambite

Director of Research Innovation, Health Data Innovation Program, Director of CTSI

Portrait of Dario Kuzmanovic

Dario Kuzmanovic

Program Director, Research Data Science, Director, Research Informatics & Health Innovation

Portrait of Yesha Patel

Yesha Patel

Associate Director, Data Science & AI

Accomplishments

Created a custom AWS Data Lake

Designed and deployed a secure AWS-based data lake to unify research and clinical data sources into a scalable environment. This accomplishment establishes modern cloud architecture that supports large-scale analytics, governed access, and future machine learning expansion.

Implemented an Enterprise Biorepository, OpenSpecimen

Launched the enterprise instance of OpenSpecimen, centralizing biospecimen tracking, governance workflows, and consent data across studies and sites. This achievement modernizes biospecimen informatics and creates a scalable foundation for translational research programs.

Self-Service Analytics

Enabled self-service analytics capabilities so teams can independently explore securely governed clinical and research data in real time. This significantly increases research efficiency and data literacy while reducing turnaround time for data access.

Installed KECKCap, a Part-11 compliant installation of REDCap and integrated the FHIR API

Deployed KECKCap to meet FDA Part-11 requirements for electronic data capture, e-consent, and regulatory workflows, and integrated the FHIR API for interoperable clinical data exchange. This modernizes secure data capture and ensures compliance for clinical trials and regulated research environments.

Installed EMERSE

Implemented EMERSE to provide clinicians and researchers a secure platform to search and analyze unstructured clinical notes. This advances natural language search capabilities across narrative medical data and accelerates cohort discovery and chart review.

SMART Transfer and AI Summarization

Implemented SMART transfer and AI-based clinical summarization features to enable automated structured data transfer and intelligent record summarization. This enhances clinical workflows by reducing manual data entry and improving data quality.

Enhanced i2b2 to connect with USC's IRB system iStar

Enhanced i2b2 to integrate directly with iStar for automated human subjects compliance verification and secure dataset delivery. This reduces administrative burden and ensures responsible, policy-aligned access to research data.

Data.world Data Catalog

Implemented data.world data catalog, integrating diverse data sources into a unified platform that supports metadata enrichment, governance, and collaboration. This tool streamlines data discovery, standardizes business terminology, and empowers teams to make data-driven decisions.

Services and Resources

Clinical Data Extraction

  • Analyst Assisted EMR Data Extraction
  • KECKCap for Researcher Operated EMR Data Extraction

Clinical Data Capture & Management

  • REDCap
  • KECKCap - Part-11 Compliance

Data Discovery Tools

i2b2 - For Keck Data Counts.

TriNetX - For KECK Data as well as Regional, National and Global Data.

LADR - The Los Angeles Data Resource (LADR) is a federated network connecting de-identified patient data from Keck Medicine of USC, UCLA Health, Cedars-Sinai, City of Hope, and Harbor-UCLA/LAC+USC Medical Center. It enables researchers to perform cohort discovery and feasibility analyses across these major Los Angeles health systems while maintaining strict data security and local control.

EMERSE - Search Keck's Clinical Notes from the EMR.

N3C - The National COVID Cohort Collaborative (N3C) is a large, NIH-funded clinical data collaborative that brings together institutions nationwide to create one of the largest, most comprehensive clinical cohorts in U.S. history.

All of Us - The All of Us Research Program is a national precision medicine initiative led by the NIH that collects health data from over a million diverse participants across the United States. The dataset includes electronic health records, survey data, biospecimens, and wearable device information to help researchers understand how lifestyle, environment, and genetics affect health.

ENACT - The ENACT Network (Electronic health Records Network for Analysis, Communication, and Translation) is a federated platform that connects multiple CTSA institutions to enable cross-site cohort discovery and data exploration. It allows researchers to securely identify study populations and collaborate across institutions without sharing identifiable data.