Newswise -- LOS ANGELES (Oct. 15, 2025) -- Cedars-Sinai is bolstering its machine learning and artificial intelligence (AI) capabilities by adopting a synthetic data platform, a move set to transform the way medical data is leveraged for research and clinical care.
Synthetic data platforms use artificial intelligence to produce new data that mimics real-world patient data, without disclosing any private information. This approach allows organizations like Cedars-Sinai to simulate various scenarios and outcomes, providing valuable insights for medical research and clinical decision-making, while still maintaining a high level of accuracy and validity in research findings.
For example, Cedars-Sinai can take real patient data and convert it into a new dataset that reflects patient profiles and treatment scenarios. This synthetic dataset could be generated within one hour, offering a significant advantage in speed and efficiency over traditional methods that require time-consuming processes to retrieve real patient data.
"The use of synthetic data at Cedars-Sinai reflects our pursuit of cutting-edge technologies to advance medical research and improve patient care," said Craig Kwiatkowski, PharmD, senior vice president and chief information officer at Cedars-Sinai. "This supports our broader strategy of building a more connected data ecosystem -- one that gives our teams easier access to a wider range of data that helps drive real-world innovation in healthcare."
To conduct this work, Cedars-Sinai is partnering with Syntho, an Amsterdam-based company that participated in the Cedars-Sinai Accelerator program in 2022. Syntho provides artificial intelligence-based, privacy-enhancing technology to generate anonymous synthetic data.
Cedars-Sinai also is exploring the use of synthetic data in tandem with the recent launch of a new Digital Innovation Platform, as it develops a comprehensive data platform tool set to address some of the most pressing challenges in healthcare. The initiative will leverage Cedars-Sinai's clinical expertise, infrastructure, research capabilities and vast data resources to develop companies that tackle healthcare issues, in partnership with Cedars-Sinai staff, investors and venture-builder Redesign Health.
Jason Moore, PhD, chair of the Department of Computational Biomedicine, and Nicholas Tatonetti, PhD, vice chair of Computational Biomedicine, are leading research efforts on synthetic data at Cedars-Sinai. They sat down with the Cedars-Sinai Newsroom to share more about the role of synthetic data in a healthcare setting.
What are the benefits of using synthetic data?
Moore: Synthetic data is generated using artificial intelligence to model various patterns in real data and produce new data that preserves these patterns. This synthetic data does not have the same privacy and security issues as real data, making it easier -- and much faster -- to use for research. That's because synthetic data doesn't require approval from committees or governing bodies like an internal review board.
Synthetic data also makes it easier to collaborate and share information with other internal teams and external institutions.
Tatonetti: The speed, accuracy and sheer volume in which we can access synthetic data opens the door to studying new and complex conditions like rare diseases.
What is the difference between de-identified data and synthetic data?
Moore: De-identified data is real data with patient identifiers removed, while synthetic data is completely artificial. This artificial data is generated to preserve the relationships and patterns in the original data, making it useful for research without the privacy concerns associated with real data.
What about the privacy and security of synthetic data?
Moore: One of the biggest motivators of using synthetic data is to ensure patient privacy and security. Synthetic data eliminates the possibility of re-identifying patients, thus allowing researchers to work with data without the same restrictions as real data.
How will the partnership with Syntho advance our work with synthetic data?
Tatonetti: Through our partnership with Syntho, we hope to achieve three things:
* Lower the barriers to clinical research, allowing more investigators to conduct studies without lengthy approval processes associated with real data
* Speed up the process of launching and dropping studies, enabling researchers to quickly test and iterate on their hypotheses
* Allow students and trainees in the Cedars-Sinai Health Sciences University to use synthetic data, providing them with realistic datasets to learn from, build tools on, and conduct analyses.
What are the limitations of synthetic data?
Moore: Synthetic data has limitations and does not handle all data types well -- like discrete genetic data -- so it's imperative we understand these limitations in our workflows. It's also critical we effectively communicate these limitations to our users to prevent user frustration and fatigue.
Cedars-Sinai Health Sciences University is advancing groundbreaking research and educating future leaders in medicine, biomedical sciences and allied health sciences. Learn more about the university.
