Flexible solutions to work with real-world data
Every NashBio engagement starts from the same foundation: de-identified electronic health record data on 4M+ patients from Vanderbilt University Medical Center, natively linked to genomes, medical images, waveforms and more than a billion clinical notes, curated to be AI-ready.
What changes is the combination of data types tailored to your specific use case, and how much of the work your team does vs. ours.
License the data and analyze it yourself. Or bring in our clinicians and data scientists to run the analysis with you. The environment you work in comes with either.
Curated Data
License structured clinical data on 4M+ patients, then add the layers your question needs: 312K+ whole genomes, 11M+ diagnostic imaging studies, 1.9M+ digital ECGs, or specialty measures curated by practicing cardiologists and oncologists. Every layer links at the patient level, with no third-party tokenization, and arrives AI-ready.
Expert Services
Our in-house clinicians, bioinformaticians and data scientists work on your question directly. Reserve on-demand hours for feasibility checks and cohort design, or hand us a study end to end, from defining the question to delivering the results.
Advanced Technology
Query your licensed data with SQL, R and Python in BigQuery and JupyterLab, and use advanced AI tools to work with complex data types like clinical notes, imaging and waveforms. Size cohorts in the Data Dashboard before you commit to a dataset. No egress or transfer fees, and our experts can work beside your team in the same environment.
Having access to a wealth of multimodal information, genetic information, and a huge population which is very diverse, where we can actually track patients throughout their life, holds a promise of boosting our understanding of chronic disease and also boosting our ability to find the relevant targets we want to pursue in future drug development.
