Health Technology Assessment (HTA) and regulatory engagement remain a central component of SYNTHIA, helping to ensure that innovations in synthetic data are developed in a way that is relevant, acceptable, and useful for healthcare decision-makers.
To support this objective, SYNTHIA established an HTA and Regulatory Advisory Group comprising experts from HTA agencies, regulatory organisations, and healthcare decision-making bodies. The group provides independent advice and stakeholder perspectives throughout the project, helping to explore how synthetic data could be used in real-world HTA and regulatory settings.
On 18 June 2026, the Advisory Group reconvened for its third meeting. Building on the first two meetings held in April and November 2025, this third forum moved from exploring the potential of synthetic data towards examining how it might be assessed when presented as part of an HTA or regulatory evidence submission.
Putting synthetic data to the test
Previous discussions highlighted that the acceptability of synthetic data depends strongly on the context in which it is used. To make the third meeting more tangible, SYNTHIA therefore adopted a vignette-based approach, using hypothetical evidence submissions inspired by real-world scenarios.
Two lung cancer scenarios were explored:
- An AI-enabled medical device for analysing chest X-ray images for suspected lung cancer, where synthetic data were used for training and validation.
- An indirect treatment comparison, where synthetic individual patient data (IPD) were used to enable patient-level adjustments when comparator IPD were unavailable.
Invited experts formed a mock HTA and regulatory assessment committee and considered the submissions as though they were conducting a real appraisal. The committee examined whether the use of synthetic data was appropriate and justified, as well as the quality and presentation of the evidence. Advisory Group members then discussed the scenarios and the committee's feedback in breakout groups.
When is synthetic data acceptable?
The exercise demonstrated that decision-makers can engage constructively and critically with synthetic data, but that its acceptability depends strongly on why it is being used, the role it plays within the evidence package, and how transparently its generation and limitations are communicated. Participants saw greater potential for synthetic data when it is used to enable analyses that would otherwise not be possible, support sensitivity analyses, supplement existing evidence, or explore generalisability and underrepresented populations. Greater caution was expressed when synthetic data are used to replace real validation evidence, substantially change decision-critical estimates, or reduce apparent uncertainty without sufficient empirical justification. This distinction was also visible across the two scenarios. The AI-enabled medical device case raised concerns around representativeness, patient acceptability and the need for independent real-world validation. The indirect treatment comparison was received more positively because synthetic IPD addressed a clear evidence gap, although further technical validation was still considered necessary.
What value does synthetic data add?
One central question emerged from the discussions: What value does synthetic data add?
Participants stressed that future submissions should clearly explain why synthetic data are needed, why real data are insufficient or inaccessible, and what new information the synthetic data contribute. Clear reporting will also be essential. Decision-makers need to understand the underlying data sources, how synthetic data were generated, how fidelity, utility and representativeness were assessed, and how uncertainty should be interpreted. Participants particularly cautioned against synthetic data creating a false impression of precision. Confidence in synthetic evidence will depend on rigorous validation and transparent communication of both its strengths and limitations.
Key conclusions
The third HTA and Regulatory Advisory Group meeting marked an important progression in SYNTHIA's engagement with healthcare decision-makers. By moving from theoretical discussions to realistic appraisal scenarios, the meeting provided valuable insight into how synthetic data might be considered within future HTA and regulatory submissions. The discussions highlighted that synthetic data may have an important role where it enables otherwise difficult analyses or complements existing evidence. However, its use must be supported by a clear justification, transparent methods, appropriate validation, and a strong understanding of uncertainty and limitations. The mock committee approach also proved to be a valuable way of exploring these questions in a realistic decision-making context and could be applied to other synthetic data use cases in future. The insights gathered during this third forum will help guide SYNTHIA's ongoing work to advance the responsible and effective use of synthetic data in healthcare decision-making.
If you are interested in learning more, please send an email to communications@ihi-synthia.eu and we will connect you with Michael Bell, key contact for SYNTHIA Partner NICE.
Read about 2nd and 1st SYNTHIA HTA & Regulatory Advisory Group here >
