Ahavi

Enabling Scientific Advancements in Health Care through Real-World Data and Analytics

Ahavi™ provides primary source-verifiable, de-identified, real-world health care data to researchers, scientists, and developers. Our customized environments offer industry-leading analytical tools to analyze your cohorts.

Third-party Certified Data Pipelines

Regulatory-grade, publication-ready, primary source-verified data.

Longitudinal Patient Health Care Journeys

Access to complete structured and unstructured data that can be linked back as far as 2019 and 2012, respectively.

Diversity in Patient Population

Access to high-quality data from all types of care settings across Pennsylvania.

End-to-End Access & Professional Services

Data access, expert cohort identification, end-to-end analytics support.

Ahavi is a real-world data platform developed by UPMC Enterprises to provide de-identified health care data to enable researchers, scientists, and developers to create curated datasets for accelerating research, clinical trial design, and AI development. By leveraging UPMC’s extensive datasets, Ahavi ensures that AI models, predictive analytics, and clinical decision-making tools are built on trusted, real-world data, helping solve some of the biggest challenges in health care.

5M+

PATIENTS

24+

HOSPITALS

Historic data since 2019

156M+

Patient Encounter Records

  • Allergies & Intolerances
  • Results
  • Plan of Treatment
  • Labs
  • Medication
  • Procedures
  • Social History
  • Problems
  • Immunizations
  • Vital Signs

Historic data since 2012

154M+Ambulatory Documents

123M+Adult ED & inpatient documents

42M+Legal & treatment documents

41M+Radiology documents

25M+Cardiovascular monitoring & imaging documents

23M+Transcription (inpatient, outpatient, & ED) documents

80%

Linkage rate between structured and unstructured data

Who Ahavi Serves

  • Pharma & Clinical Trial Enablement Partners
  • AI Developers
  • Academic Research Partners

How It Works

The Ahavi platform is able to deliver industry-leading access to data thanks to a six-step process that acquires data from across the UPMC system, de-identifies and validates it, before making it available in an easy-to-use portal.

  • Data Acquisition & Storage
  • Cohort Definition (Structured Data)
  • Data Augmentation (Unstructured Data)
  • Data De-Identification
  • Honest Broker Validation
  • Ahavi™ Researcher Portal

The true power of Ahavi is taking its tremendous datasets and using them to deliver best-in-class analytics and research and development services. Learn more about our services.

Ahavi’s™ Real-World Data Analytics services provide scalable, cost-effective solutions that harness both structured and unstructured data for deep exploratory analyses and retrospective studies. By leveraging advanced analytics, we help uncover meaningful real-world evidence to enable clinical trials, optimize treatment pathways, and inform data-driven decision making. Whether you’re conducting epidemiological research, assessing treatment effectiveness, or identifying emerging trends, our powerful analytics capabilities turn complex data into impactful insights.

Ahavi’s™ Research and Development Infrastructure services provide AI companies with seamless access to high-quality, de-identified data in a secure and compliant environment. Designed to accelerate innovation, our streamlined workflow ensures delivery of comprehensive datasets in as little as four weeks—eliminating common data accessibility barriers. Whether you’re training, validating, or fine-tuning AI models, our solution empowers your team with the data they need, when they need it, without compromising security or compliance.