Real-world data with the clinical depth to answer your question
NashBio provides life science research teams access to de-identified electronic health records for more than 4 million patients from a single academic medical center, natively linked to genomes, medical images, waveforms and clinician-curated specialty measures.
Data at a glance
- 4M+
- de-identified unique subjects
- 312,000+*
- whole genomes
- 4.6 years
- average length of clinical data
- 750+
- peer-reviewed publications
*Not all whole genome sequences may be available for licensing.
Flexible options to meet your needs
Explore our solutionsData products
License the structured clinical foundation, then add genomes, imaging, waveforms or specialty measures as your question changes.
Expert services
Bring in our clinicians, bioinformaticians and data scientists for a feasibility question or a full study, delivered end to end.
Technology
Query your licensed data in place with SQL, R and Python in a secure, dedicated environment.
Who we serve
Built for the teams turning data into breakthroughs
Biotech teams hunting targets, pharma running clinical development, and Medtech and Diagnostics companies training the algorithms inside their products.
See who we serveWhy NashBio?
One source, every layer, expert hands
One population, every layer
Clinical records, genomes, imaging and waveforms come from the same patient, so a cohort defined in one layer holds in the others.
Academic-center depth
Data born at Vanderbilt University Medical Center, on an integrated EHR since 2001, covers specialist-verified diagnoses and the latest advanced therapies.
Scientists, not just a data feed
Our clinicians, bioinformaticians and data scientists work alongside your team, from a first feasibility question through a delivered study.
Governed access without friction
Query licensed data in place with SQL, R and Python in a secure, dedicated environment.
Latest from NashBio
See all resources
Oncology
Precision at Scale: Introducing NashBio’s Clinical Specialty (CS) Oncology Dataset for End-to-End Longitudinal Research
Discover NashBio’s CS Oncology: a robust dataset linking registry-confirmed cancer diagnoses with over 7 years of longitudinal EHR data for clinical research.
Oncology
Mapping the Road to Diagnosis: Longitudinal Biomarkers in Precision Oncology
Conventional oncology datasets miss the pre-diagnosis period. Learn how NashBio links longitudinal RWD with registry-confirmed endpoints to map the complete patient journey.
AI
AI Reveals Hidden Barriers to Statin Therapy: How VUMC’s Latest AI Breakthrough Demonstrates the Power of Clinical Notes - and How NashBio Delivers These Insights at Scale
Leveraging AI framework innovations from VUMC, NashBio systematically extracts hidden statin adherence signals from unstructured clinical notes to accelerate cardiovascular research and precision medicine.
Ready to dig deeper? Bring us your use case and we will get the data you need.
Or get NashBio updates by email.