Whether you’re planning a new or future clinical trial, or adapting your systems to protocol changes once a trial is underway, you need test health data at scale in order to ensure your systems will operate smoothly to the requirements of the trial. Real patient data requires special privacy safeguarding measures, while producing synthetic health data normally incurs significant costs and delays.

The TrialTwin platform allows you to access fresh synthetic health datasets at scale, in minutes or hours, as many times as you need. This data is fully realistic and scientifically accurate, and matches your exact requirements for any clinical trial, but comes with no copyright or privacy constraints. The TrialTwin platform thereby greatly accelerates and simplifies the clinical development process, from initial planning to FPI to trial completion.

Yes, TrialTwin™ is a user-friendly and easily customizable platform, which provides a “no-code”, integrated, centralized trial simulation and validation solution. Using TrialTwin requires no specialist computer programming skills.

From realistic people (SynthPerson™) based in real locations, to their full background information and realistic personal health records (SynthPHR™), to fully customized trial processes and outcomes (SynthTrial™) – along with more types of synthetic data which you can see here[LINK TO PLATFORM PAGE OF DESCRIPTIONS OF SYNTHPRODUCTS] – TrialTwin™ generates a digital twin to allow you to run foolproof testing of every aspect of your study before your systems and protocols go into production.

Please see this paper presented by our Chief Technology Officer in 2021, which discusses synthetic health data in the context of the SAS language and the pharmaceutical industry: http://nihpo.com/AD-162_PharmaSUG2021_12.pdf

This depends on the exact usage of the data. For example, synthetic data created for a RAVE ALS is validated by the customer first – the customer verifies that the output structure exactly matches the data they get directly from their RAVE instances, after which the relevant team analyses the data using automated rules that will be applied to that data in the real study. For the mapping between the CRFs and SDTM, the customer will apply their mapping to our synthetic data and the test is then that all the rules can be applied correctly. Any error in the data, e.g. a field not correctly using an assigned codelist, would produce an error in the mapping.

We at TrialTwin also proactively run our own testing and reporting. Going with the previous example, we also check if any fields or forms failed to be created (a method which has proved highly efficient at detecting ALS errors); we test and verify that all of the rules have been applied correctly; and we check that every field uses the correct format and the appropriate assigned codelist. We then produce our own reporting which demonstrates the process we have applied to produce each part of the data.

In addition, we maintain regular contact with our customers to obtain their feedback on any change to our platform, and any new implementation needed for the synthetic data we are creating for them. We listen to our customers, and when necessary we deliver changes in fast turnaround times. We keep our customers clearly and regularly informed, so they have full transparency and confidence in what we do.