30th

April

2025

April Webinar Wednesday
5 days to go!
Register Now

20th

May

2025

CSS 2025
25 days to go!
Register Now

16th

November

2025

EU Connect 2025 – Call for Papers is Open!
205 days to go!
Register Now
  1. Home
  2. /
  3. Communications
  4. /
  5. PHUSE Blog
  6. /
  7. Free Synthetic Health Data for US Active Clinical Trials Available Now

Free Synthetic Health Data for US Active Clinical Trials Available Now

Screenshot 2022-09-20 at 16.15.01.png

NIHPO announces the availability of realistic, scientifically accurate synthetic health data for 39,000 active clinical trials in the US. Each clinical trial bundle includes a:

  • Synthetic Person (SynthPerson™) – a realistic synthetic person located within the US with full background information (place of birth, location of residence, gender, race, etc.)
  • Synthetic Personal Health Record (SynthPHR™) – including a realistic medical history with drugs (from the FDA’s Orangebook), lab results (using LOINC), procedures and treatments (using SNOMED-CT)
  • Synthetic Trial (SynthTrial™) – full results of a simulated trial, including all domains of the CDISC SDTM standard.

The clinical trial packages are available here: https://trialtwin.com/CT/us/

These synthetic health data outputs are the result of the collaboration of NIHPO with the PHUSE Test Data Factory Working Group.

Users of the PHUSE Open Data Repository (PODR) will also be able to access and download these trial bundle files.

What type of studies will be shared?

All studies which are currently active at https://clinicaltrials.gov in the following status:

  • Not yet recruiting
  • Recruiting
  • Enrolling by invitation
  • Active, not recruiting

Right now, there are 38,920 studies in the US that match those conditions.

What is PODR about?

The structure and functionality of a Python-based platform that generates synthetic health data at scale from real-world data.

This non-real (yet realistic) synthetic health data provided by PHUSE can be of assistance during software development and testing. And to evaluate corner cases.

Early adopters report that synthetic health data can potentially shorten quality assurance cycles and also provide a crucial tool for end-to-end system validation. Finally, and very importantly, this synthetic health data are available with no copyright, legal, privacy or regulatory blocks.

The motivation behind this platform is to allow all staff levels at an organisation participating in clinical trials to easily create and use synthetic data with no restrictions. It is our hope that this platform will accelerate the development and approval of both new medical devices and pharmaceutical products.

Empowering the PODR

Some of you may already know about the benefits of using the PODR. With the objective of serving valuable and useful CDISC synthetic health data for clinical trial tests, generated synthetic subjects (SynthPerson™) with full medical history (SynthPHR™) and with SDTM test data (SynthTrial™) are created.

All this relevant information will be freely available to PHUSE members for search and download through the PODR on the NIHPO website.

How can I access it?

Click the links below to access 10 clinical trial cases for each of the following countries:

Contact us: info@nihpo.com www.trialtwin.com NIHPO, Inc. 15625 NW 15 Avenue Miami, FL 33169USA