TriNetX Datasets
Explore real-world data from TriNetX in your own environment
TriNetX makes it easy for clinical researchers to query, license, and download real-world clinical data that is aggregated and harmonized directly from healthcare organizations on a continuous basis.
Start with the right source
TriNetX real-world datasets are clinically rich, harmonized, and directly sourced from our federated global network of healthcare organizations.
Supported by our dedicated team of data scientists and internationally recognized real-world evidence researchers, our datasets deliver billions of high-quality, date-stamped observations, harmonized into formats suitable for your research.
Because our datasets are sourced live from healthcare organizations within our federated network, you’ll always have access to the freshest EHR insights — with new observations, results, and medication orders regularly updated, so you can accelerate your research with the very latest from the frontline of patient care.
Demographics
Medications
Vitals
Diagnoses
Lab Results
Genomics
Procedures
Oncology
Mortality
Breadth of our data:
- Over 145M patients globally
- 22M patients with EHR + closed claims
- 55.9M tokenized linkable patients
Key features of our data:
- Downloadable, row-level
- EHR only datasets
- EHR + closed claim datasets
- Mortality
- Social Determinants of Health (SDoH)
Longitudinal Datasets
Our longitudinal datasets provide a unified, clinically rich view of patient care, delivering deep, patient-level insight across diseases, encounters, and care settings. These datasets include longitudinal histories for over 145 million patients, sourced directly from EHR data contributed by more than 100 healthcare organizations. With multi-year follow-up across inpatient and outpatient environments and quarterly refreshes to ensure recency, they provide the breadth and temporal depth to support teams across the healthcare ecosystem by enabling advanced analytics, evidence generation, and enterprise-scale decision-making.
Key Data Elements
- Encounters and visit types (inpatient + outpatient)
- Diagnoses and procedures
- Medications (including in-clinic administrations where available)
- Laboratory results and vital signs
- Derived comorbidities
- Demographics, including race and ethnicity
Use Cases
- RWE generation for clinical, regulatory, and HEOR work
- Reconstruct individual patient histories
- Patient journey analysis across multiple conditions
- Train predictive models using thousands of well-represented patient co-variates
- AI/ML model development and validation
- Market and treatment landscape assessment
- Strategic forecasting and opportunity evaluation
These datasets support teams across the healthcare ecosystem who rely on longitudinal, clinically rich data to build predictive models, assess markets, inform evidence strategy, support regulatory and publication work, and guide product planning and performance monitoring across therapeutic areas.
Define your cohort.
If you’re a TriNetX subscriber, you already know how to quickly explore billions of health facts and define new research cohorts through our flexible web-based cohort builder.
If you’re new to TriNetX, rest assured that no subscription is required. You and a researcher from our Clinical Sciences team will use this same tool together to build the exact cohort you need. We believe in transparency at every step.
Review the data.
We’ll carefully review the summary statistics and fill rates with you to make sure your cohort comes with all the data you need to power your analysis. Refine the size and criteria of your cohort until it’s perfect.
Request and license.
The order process is clear and quick. Our terms grant you rights to the data for one year, with the option to receive refreshed data on your cohort quarterly during that time.
Download.
Within days of finalizing your cohort, we’ll notify you that your files are ready. You can download a compressed folder containing CSV files or import the data directly into your in-house application.
Billions of Clinical Facts.
New Research Possibilities.
See how one of our power users defined his criteria, requested his dataset, and arranged his files to answer a critical question about the relationship between eGFR and heart failure.
Linked Datasets
Our linked datasets combine data sourced from EHR and insurance claims into a single, longitudinal record - for each one of the 22 million patients represented in both sources. Secure and rapid tokenization allows us to match EHR and claim records on a per-patient basis without ever accessing or exposing personally identifying information. The result is a robust record that follows a patient across time and between providers, bringing demographics, clinical observations, treatment details, and costs under one view. By further linking with federal death registries and private obituaries, we support analyses of long-term survival in addition to the full array of HEOR, efficacy, and safety analyses.
Use Cases
- Incidence and prevalence
- Long-term safety and efficacy
- Treatment patterns
- Drug adherence and persistence
- Burden of Illness
- Cost of care
- Disease Progression
- Overall survival
Key Data Elements
- Demographics
- Diagnoses
- Procedures
- Medications
- Labs
- Encounters
- Enrollment
- Claim headers & lines
- Costs
- Rx fills
Complete the form below to download the Curated Dataset Snapshot!
"*" indicates required fields
Let's Get Started
Need to reach out? We’re here to help.
Access and Analyze Rich, Secure, Real-Time Data
TriNetX is a global network of healthcare organizations and life science companies, driving real-world research to accelerate the development of life-saving therapies.
From trial operations to evidence generation, we put you at the forefront of discovery.
Clinical Trial Design & Optimization
Datasets & Analytics
Non-US Oncology
Real-World Evidence Generation
Pharmacovigilance & Drug Safety