Data Resources

The Mount Sinai Health System naturally acquires a wide variety of data from clinical sources, as well as research. The Mount Sinai Data Warehouse and Research Data Services teams enable researchers to access and analyze this data efficiently with finely-tuned tools and resources—and transform it into knowledge and insights for better health care.

Mount Sinai Data Warehouse

The Mount Sinai Data Warehouse (MSDW) consists of clinical and operational data for use in clinical and translational research, as well as quality improvement initiatives. MSDW contains data from Mount Sinai's Epic EHR system, which was first deployed in May 2011. Data is extracted from the Epic Caboodle and Clarity databases and transformed into the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). Data is located on the Minerva High Performance Computing cluster. The data warehouse offers researchers access to:

  • - More than 12 million patient records 

  • - Over 105 million patient encounters 

  • - Over 211 million recorded patient diagnosis codes 

  • - Over 1 billion lab test results 

  • - Over 241 million medications records 

  • - Over 218 million clinical notes 

  • - Over 358 million procedures 

  • - Over 998 million vital signs and other flowsheet measurements 

  •  

Researchers planning new studies or grant applications can use self-service tools from Digital Transfer Partners (DTP) to quantify eligible cohorts: Leaf, ATLAS, and TriNetX. For IRB-approved research or QI projects custom queries can be performed and data marts created, tailored to specific eligibility and data analysis requirements.

Artificial Intelligence-Ready Mount Sinai (AIR·MS), a cloud-based, multi-modal health data platform, which integrates patient data generated from different clinical departments across Health Systems, offers identifiable and de-identified versions of MSDW datasets.

MSDW complies with federal and New York State patient privacy and data-security regulations, including 45 CFR 46 (the "Common Rule" for the Protection of Human Subjects), HIPAA, 42 CFR Part 2 and NYS Article 27-F. MSDW also complies with all applicable cybersecurity and Institutional Review Board (IRB) policies.

Learn more about the Mount Sinai Data Warehouse

 

AIR•MS

We are excited to support the AIR•MS project, which involves storing various datasets in a fast, in-memory database optimized for AI research. This project, which is being co-led by the Hasso Plattner Institute, will significantly accelerate AI research not only at Mount Sinai but throughout the United States and internationally. It not only contains MSDW data, but also other linked datasets from the various information systems throughout Mount Sinai, allowing for comprehensive AI models and tools to be built quickly.

Learn more about AIR•MS.