Leverage synthetic data to propel personalized medicine to new heights

SYNTHIA is a multidisciplinary collaboration of 32 consortium partners - SDG developers, FAIR data experts, clinical researchers, developers of therapies and data-based tools, legal experts, socio-economic analysts, regulatory, policy advocacy, and communication experts - that will provide a 360º vision on how to advance healthcare applications through Synthetic Data use.

We are set to revolutionize the field of personalized medicine by harnessing the power of synthetic data (SD). As the first IHI (Innovative Healthcare Initiative) Synthetic Data project to tackle the critical need for privacy - preserving data solutions in healthcare, SYNTHIA aims to propel research and innovation to new heights, ensuring that patients receive the best possible care while safeguarding their personal information.

Unlocking new possibilities in health research which are artificially generated to mimic real patient data, present a solution to many of the challenges faced in health research today. These data allow researchers to overcome the limitations of access to high-quality, real-world datasets and address growing concerns about patient privacy. However, questions have lingered about the quality and applicability of synthetic datasets, especially in diverse and complex scenarios.

SYNTHIA is addressing these challenges head-on by developing validated tools and methods for synthetic data generation (SDG) across various data types, including laboratory results, clinical notes, genomics and imaging. By focusing on six specific diseases - use cases - SYNTHIA will demonstrate the utility of synthetic data in advancing personalized medicine: Two solid tumors: Lung cancer, Breast cancer; Two blood cancers: Multiple myeloma, Diffuse large B-cell lymphoma; Alzheimer’s disease; Type 2 diabetes.

Our Objectives

  • Identify requirements for SD with the SYNTHIA clinical use cases.
  • Develop SDG methods, tools and access to RD.
  • Establish a framework for SD evaluation, ensuring privacy, quality and bias mitigation.
  • Validation of SD for various use cases.
  • Provide access to SD and SDG methods.
  • Build a community through public and private cohesion and strong communication.

Our Ambition

  • To unlock the potential of synthetic data (SD) in healthcare by addressing privacy concerns, ensuring robust quality, and building trust among stakeholders. By demonstrating that SD can preserve patient privacy while delivering high-quality results, we aim to accelerate research, improve AI models, reduce costs, and expand therapeutic options, all within the strict legal and regulatory frameworks governing biomedical innovation.
  • To maximize the potential of Synthetic Data Generation (SDG) in healthcare by developing and validating reliable tools and methods tailored for specific medical applications. By focusing on six major diseases, we seek to demonstrate the suitability of synthetic data (SD) for advancing research and clinical decision-making with quality equivalent to real data (RD). By addressing conditions with significant global health impact and unmet medical needs, we aspire to drive breakthroughs that benefit patients, the scientific community, and industry stakeholders.
  • To enhance SDG methodologies across diverse data types, including tabular, genomic, imaging, and m-health data, while improving the generation of realistic longitudinal datasets. We prioritize high-quality, multicenter patient data and clinical expertise for validation, ensuring robust results. By establishing tailored evaluation metrics, benchmarks, and standards, we will promote trust in SD applications and provide a transparent platform for responsible use, empowering researchers to accelerate innovation across a wide spectrum of healthcare challenges.

Use Cases

Workpackages

  • Our structured Work Packages (WPs) drive innovation, ensuring secure, high-quality, and ethically responsible synthetic data applications.
  • From developing robust SDG tools to navigating regulatory landscapes, each WP contributes to building a sustainable, federated platform that empowers researchers, clinicians, and policymakers.
  • Explore how SYNTHIA is unlocking new possibilities for data-driven healthcare solutions, view the 10 WPs > [link under construction]

Fostering trust through innovation

A key component of the SYNTHIA project is its dedicated federated platform, which will serve as a central resource for the research community. This platform will provide synthetic data generation workflows tailored to specific needs, along with robust frameworks to assess data privacy, quality, and applicability. Each dataset will be clearly labelled with its suitability for various research applications, building trust among stakeholders and promoting the responsible use of synthetic data.

Collaborative efforts driving success

The SYNTHIA partners from Medtech, Pharma, Academia, Medical research and Healthcare institutions are committed to advancing the use of synthetic data in healthcare. The project’s outputs will be made accessible to researchers worldwide, fostering a collaborative environment where innovation can thrive.

Join us in revolutionizing personalized medicine through synthetic data innovation. Connect with SYNTHIA today to be part of a future where data-driven healthcare solutions are accessible, ethical, and groundbreaking. [link under construction]