Stanford
STAnford medicine Research data Repository

STARR has a number of types that are linkable to each other, and Research IT is able to de-identify these data modalities at scale. 

Data types

Data types in STARR

STARR has data from Stanford Health Care, Stanford Health Care Tri-Valley (includes pediatric population), University Healthcare Alliance dba Stanford Medicine Partners, Stanford Medicine Children’s Health fka Lucile Packard Children’s Hospital and Packard Children’s Health Alliance (adult population includes mothers). STARR is growing to support AI use cases and is bringing in more Hospital data sources. It has structured and unstructured, raw and “analysis-ready” data. The following data types are accessible either via self-service or a data consultation service. 

  • Electronic Health Record data: 
    • Epic Clarity: Research Technology receives a copy of Epic Clarity Electronic Health Records (EHR) data from the two Stanford Hospitals. Learn more about EHR data in STARR. A subset of the EHR data is available via self-service.
    • HL7 feeds: Research Technology also receives HL7 feeds in real-time from the two Hospitals such as Admit Discharge Transfer (ADT), and Billing Account Record (BAR). Learn more about HL7 data in STARR. The HL7 data is only available via a technology consultation service.
  • Imaging: STARR contains various modalities including radiology, cardiology and fundus imaging. Learn more about imaging data in STARR. To access this data, please request a consultation service.
    • Radiology Imaging:  The two hospitals use a single clinical PACS system. The shared PACS is maintained by the adult hospital and the data is made available for research use via a Vendor Neutral Archive (VNA). STARR has pulled historical pediatric and adult radiology DICOMs from the VNA. We anticipate that over 90% of radiology images since 2010 are available in STARR.
    • Cardiology Imaging: The two hospitals have two separate Cardiology PACS. STARR has ability to query/retrieve echocardiograms from both pediatric and adult hospitals. Additionally, STARR has ability to access pediatric Syngo Cardiology PACS metadata.
    • Other imaging:  Bulk of the adult retinal fundus imaging, but not all, are available via the VNA and hence available in STARR.
  • Bedside Monitoring Data: The two hospitals use two separate Philips PIC iX bedside monitoring systems. The data are archived to STARR. Research Technology takes that archived data and recreates the clinical grade bedside monitoring data in a more interoperable format (i.e., Physionet compatible). Learn more about bedside monitoring data in STARR. A subset of this data is available as self-service.
  • Other: Research Technology brings in ancillary/auxiliaryv clinical databases to augment the Clarity data. Such databases include Stanford Cancer Registry, ARIA Radiation Oncology database, Philips ISPM, Xcelera etc. These are brought in as needed by research teams or projects. To access such data types, please request a consultation service.

Linking data modalities in STARR

Data linking in research clinical data warehouses (r-CDWs) across sources and across different modalities use different approaches. 

  • Patient at two hospitals: The pediatric and adult hospital Epic Clarity data are linked by MRN. For a short period of time, it is possible that one patient presents two different MRNs. These are often resolved in a matter of days.
  • DICOM and EHR: These two modalities (DICOMs and Epic Clarity) are linked by accession_id at Stanford. This is essentially an order number e.g., physician orders a MRI for the patient. The accession_id is the mechanism to link DICOM image with the radiology report. 
  • Bedside monitoring and EHR: Bedside monitoring data is a complex modality to integrate with MRN. STARR has pediatric bedside monitoring data. This data often relies on bed number. A patient often goes from bed to bed, as a result, we need ADT feed (Admit/Discharge/Transfer) to link. For more details, please read the manuscript.
  • EHR and LADMF death data in STARR Tools: The LADMF has SSA number, Date of Birth (DoB) and Name. There are multiple ways of matching patients in two different sources. In STARR Tools where LADMF is integrated, if there is no SSN match with Stanford patient's SSN, we do not link. If there is a SSN match, we require that either DoB matches OR (First Name, Last Name AND Year of Birth) matches.