Virtusa / vLife / Data as a service

ELECTRONIC MEDICAL RECORDS (EMR)/ELECTRONIC HEALTH RECORDS (EHR)

79 GB data
238 tables
534 columns
728,551,920 records
46,520 lives

Source: Medical Information Mart for Intensive Care (MIMIC) academic data

ELECTRONIC MEDICAL RECORDS (EMR)/ELECTRONIC HEALTH RECORDS (EHR)

Medical Information Mart for Intensive Care III (MIMIC-III) is a large, freely available database composed of health-related data associated with more than 40,000 patients who stayed in critical care units of a New York–based medical center between 2001 and 2012. The database includes information such as demographics and vital sign measurements made at the bedside (~1 data point per hour).
Source: MIMIC academic data

  • De-identified data in accordance with HIPAA
  • Diverse and very large population of ICU patients
  • Data from Social Security Administration Death Master File
  • Supported by National Institute of Biomedical Imaging and Bioengineering (NIBIB) of National Institutes of Health (NIH)
  • 160+ APIs at disposal
  • EMR, medical record, electronic billing system, free text format
  • Hospital admissions – 49000+
  • Median Age – 65.8 Years
  • Median Length of stay at Hospital – 6.9 Days
  • Median Length of stay at ICU – 2.1 Days
  • Laboratory measurements per admission – 380

Click here to access the API

CLAIMS

22 GB data
7 tables
207 columns
135,137,553 records
2,326,856 lives

Source: CMS SynPUF US government research data

CLAIMS

The claims database is built from data created by the Centers for Medicare & Medicaid Services (CMS) for Data Entrepreneurs’ Synthetic Public Use File (DE-SynPUF). DE-SynPUF, a freely available database, was created with the goal of providing a realistic set of claims data in the public domain while providing the highest degree of protection to the Medicare beneficiaries’ protected health information. The DE-SynPUF provides a robust set of metadata on the CMS claims data that has not been previously available in the public domain.
Source: CMS SynPUF US government research data

 

  • CMS.gov is a federal government website managed and paid for by the U.S. Centers for Medicare & Medicaid Services
  • Statistical disclosure limitation was used to protect confidentiality of beneficiary data in the DE-SynPUF​ ​
  • Synthetic processes are used to protect elements of the data ​
  • 100+ APIs at disposal​
  • 2 million+ unique beneficiaries​
  • 6 million+ outpatient claims​
  • 280,000+ inpatient claims​
  • Time period 2008–2010

Click here to access the API

CLINICAL TRIALS

4.57 GB data
40 tables
301 columns
19,714,645 records

Source: AACT database of Clinical Trials Transformation Initiative (CTTI)

CLINICAL TRIALS

The clinical trials database is fostered from AACT, a relational database that contains all information about every study registered in ClinicalTrials.gov. The Clinical Trials Transformation Initiative (CTTI) is a public-private partnership to develop and drive adoption of practices that will increase the quality and efficiency of clinical trials. Source: AACT database of Clinical Trials Transformation Initiative

 

  • Duke University is the host of the CTTI​
  • Support from the U.S. Food and Drug Administration​
  • CTTI is composed of more than 80 member organizations representing academia, clinical investigators, and government and regulatory agencies
  • 70+ APIs at disposal​
  • 7 million+ clinical trials​
  • 200+ countries​
  • 400K+ facilities​
  • 49000+ sponsors

Click here to access the API

HUMAN GENOME

1.1 GB data
9 tables
108 columns
5,957,338 records
30,175 lives

Source: ClinVar database of National Center for Biotechnology Information (NCBI )

HUMAN GENOME

The human genome database is created from a database of the National Center for Biotechnology Information (NCBI) that advances science and health. It provides access to biomedical and genomic information. The NCBI houses a series of databases relevant to biotechnology and biomedicine and is an important resource for bioinformatics tools and services.
Source:  National center for Biotechnology Information

  • The NCBI is part of the United States National Library of Medicine
  • All NCBI educational materials are available to reuse
  • 14 handpicked APIs at disposal
  • 350K+ allele gene information
  • 30K+ distinct genomes​

Click here to access the API

GOVERNMENT AGENCIES

1 GB data
6 tables
106 columns
5,788,223 records

Source: Govt. Health Data Database

GOVERNMENT AGENCIES

The government agencies database is an agglomeration of six different databases. The database binds together all the data silos mentioned below.

 

  • Health data is from a federal government website managed by the U.S. Department of Health and Human Services​
  • EHR vendors are managed by an agency of the Department of Health and Human Services​
  • CMS data is in the public domain and free to use
  • Disease surveillance: 3,659,360 records
  • Certified EHR vendors and products: 1,932,498 records
  • HCAHPS survey: 1,792 records
  • MACRA report for the provider: 11,678 records
  • Hospital readmission reduction: 19,830 records
  • Inpatient prospective payment system: 163,065 records

Click here to access the API

IMAGES

The images database is an agglomeration of three different databases. It contains brain tumor images, mammograms, and chest X-rays.

  • MRI data was provided by the 2015 MICCAI Brats Challenge as a part of research
  • Open-access biomedical image search engine provides the chest X-ray images
  • Mammograms are from Digital Database for Screening Mammography and are shared to facilitate research and development
  • Brain scans – 1705 objects
  • Chest X-rays – 7471 objects
  • Mammograms – 1804 objects

Click here to access the API

MEDICAL DEVICES

150,652 510(k) clearances
6,430 classifications
7,353,273 adverse events
38,232 pre-market approvals
130,247 recalls
251,771 registrations and listings
1,259,118 unique device identifiers

 

Source: U.S. Food & Drug Administration (FDA) Database

MEDICAL DEVICES

The medical devices database is created from the database provided by OpenFDA. It provides access to various aspects of the medical devices. OpenFDA is created with the goal of providing easy access to public data. It indexes high-value, high-priority, and scalable public-access data in developer-friendly standards.
Source: Open FDA

  • A 510(k) is a premarket submission to demonstrate that the device marketed is safe and effective
  • Devices are classified medical specialties referred to as panels
  • Exhaustive recall information reports
  • Geographic information of device manufacturers
  • 510(k) clearances – 150652
  • Classification – 6430
  • Adverse events – 7353273 records
  • Pre-market approval – 38232 records
  • Recalls – 130247 records
  • Registrations and listings – 251771 records
  • Unique device identifier – 1259118 records

Click here to access the API

Have a question about vLife?

Contact us

    Yes, I want Virtusa to keep me up-to-date with recent industry developments including insights, upcoming events, and innovative solution capabilities according to the privacy policy
  • This field is for validation purposes and should be left unchanged.