Flatiron Health will showcase its innovative real-world data research at the upcoming ISPOR 2025 Conference, taking place May 13-16 in Montreal, Canada. The healthtech company's real-world oncology data will be featured in more than 15 research presentations, including eight posters authored by Flatiron scientists.
The company's presence at this year's conference emphasizes how scalable, high-quality real-world oncology data and novel methodological approaches can support both research and regulatory applications in oncology.
"At this year's ISPOR, Flatiron scientists are using high-quality real-world data to validate novel methodologies that will shape the future of evidence generation and health outcomes research in oncology," said Stephanie Reisinger, Senior Vice President & General Manager, Real-World Evidence at Flatiron Health. "Leveraging innovative AI and machine learning, Flatiron is expanding the utility of global real-world evidence in regulatory decision-making and across a growing range of oncology use cases at an unprecedented scale."
Bridging the Gap Between Real-World Data and Clinical Practice
Among the highlighted research is a poster presentation validating the use of machine learning to extract real-world response data from unstructured information in electronic health records (EHRs). This approach offers a scalable and efficient method for generating high-quality oncology real-world data that can inform clinical decision-making.
Another significant presentation focuses on the acceptance of real-world evidence by regulatory bodies, including the US Food and Drug Administration and the European Medicines Agency. The research underscores the potential of real-world data to complement traditional clinical trial information in the drug approval process.
Flatiron will also introduce its Japan Breast Cancer dataset, a novel, de-identified real-world database derived from structured and unstructured data collected from routine oncology care in Japanese EHR systems. This development represents an important step in expanding global real-world evidence capabilities.
Advancing Methodologies in Real-World Evidence
The company's research presentations span a wide range of methodological innovations and clinical applications:
- Using machine learning to assess the association between rash and survival in patients with advanced non-small cell lung cancer (NSCLC)
- Applying regression discontinuity in time design for real-world comparative effectiveness studies
- Validating real-world response data generated using deep learning-based natural language processing across multiple solid tumors
- Examining the role of real-world evidence in recent multiple myeloma drug approvals in the US and EU
- Analyzing patient characteristics and treatment patterns in extensive-stage small cell lung cancer
- Augmenting race and ethnicity data in real-world oncology cohorts using the Bayesian Improved Surname Geocoding Methodology
- Estimating medication persistence from EHR data for tyrosine kinase inhibitors in EGFR-positive advanced NSCLC
Expanding the Impact of Real-World Evidence
In addition to the poster presentations, Flatiron will participate in a panel discussion on the role of real-world evidence in precision medicine. The panel will explore how real-world data can be leveraged across international borders to inform regulatory and reimbursement decisions within diverse healthcare systems.
This comprehensive approach to real-world evidence generation reflects Flatiron's mission to expand the possibilities for point-of-care solutions in oncology and use data to power smarter care for cancer patients. As an independent affiliate of the Roche Group, Flatiron continues to transform patients' real-life experiences into knowledge and create a more modern, connected oncology ecosystem through machine learning, AI, real-world evidence, and clinical trial innovations.
Attendees of ISPOR 2025 can visit Flatiron Health at Booth #601 and follow the company on social media platforms for updates from the conference using the hashtag #ISPORAnnual.
