About Our Data
About Our Data
Culmination’s Unique Dataset
We have developed a comprehensive Data Lake platform comprising deidentified health records, -omics data, outcomes, and claims data. This resource is accessible to our partners to support therapeutic target discovery, enable novel diagnostics, and drive healthcare cost reduction.
We provide access to the following data types:
- Approximately 2 million longitudinal patient journeys
- 450,000 new annual cases
- 9+ million linked biospecimens
- 1 trillion genetic variants
- 20 million digital images
- 6 million radiology images
- Regular data refreshes
- Historical data de-identification
- EHR, lab tests, slide and radiology images, unstructured notes, -omics data, etc...
The Data
Data in our data lake has been collected over the last 40+ years by our partner Intermountain Health.
Intermountain Health owns 33 hospitals and 385 clinics spanning 9 states in the Intermountain west.
Our ongoing partnership includes regular data updates, access to prospective patient enrollment and access to more than 9+ million archival clinical tissue samples
Products and Services
- Cohort Design and Recruitment. As a Culmination partner, you gain access to exclusive Discovery Cohort records via Apex — our searchable intelligence platform. Build custom cohorts with rich data including diagnoses, prescriptions, genomics, biospecimens, imaging, and standardized EHRs.
- Prospective Study Enrollment. Culmination supports prospective cohort enrollment and biospecimen collection through a dedicated clinical coordination team and partnership with Intermountain Health. We recruit targeted patients and provide blood, plasma, or tissue samples to advance your research.
- Genomics. We receive ~7,500 residual blood samples monthly and have 120,000 buffy coats available for DNA extraction across all disease areas. Our standard package includes 30X whole genome sequencing with fastq, VCF, and variant calling. Custom analyses and prospective collections are also available.
- Archival Tissues. Culmination has access to over 10 million FFPE tissue blocks, enabling high-quality RNA-seq for molecular phenotyping across diverse organ systems — including archival samples from proposed study cohorts.
- RNA-seq Molecular Phenotyping. We routinely generate RNA-seq data to identify patient clusters, differential gene expressions, and pathway differences. A broad range of archival tissues are available to support and optimize study design.
- Histology. Culmination has access to over 10 million H&E-stained FFPE tissues, with 2.7 million slides digitized and growing monthly. Custom histological staining is available from archived blocks.
- Radiological Images. Culmination has access to 2.5M radiologic images, including CT, X-ray, and MRI.
- Clinical Insights and Analytics. Culmination offers deep clinical records, including EHRs, notes, and pathology reports, enabling precise cohort creation and lifetime disease journey analysis. We apply ML to identify comorbidities, predict disease onset, and model clinical progression.
Discovery Cohorts
We structure data into Discovery Cohorts, enabling clear visibility into the breadth and depth of available data across disease areas. As a partner, you will have access to comprehensive data summaries to support your research and development efforts.
Discovery Cohort data is organized in Apex, Culmination’s searchable Intelligence Platform. As a partner, you will have access to Apex where you will have the ability to easily build your own custom cohorts.
Apex Discovery Cohort Summaries
Our data and capabilities cover the full spectrum of disease, and we can quickly add custom disease summaries depending on your specific needs and interests.
Contact us to find out how Culmination’s multimodal data can advance your research program.