Truveta extends its real-world data platform to support oncology research and clinical decision-making

Truveta has expanded its real-world data (RWD) platform to include oncology, offering access to over 7 million patient journeys across more than 100 cancer types. The data aims to support researchers with a more complete view of the cancer care continuum and facilitate evidence generation for treatment evaluation.

The company’s oncology dataset draws from electronic health records (EHRs) representing more than 120 million patients, alongside closed claims data for over 200 million individuals in the US. According to Truveta, the data, “exceed[s] FDA standards of data quality, data provenance, and audit readiness,” and is updated daily to reflect the most recent patient care information

“Truveta has established itself as a leader in delivering regulatory-grade, RWD that drives meaningful progress across a wide range of conditions—from cardiovascular and metabolic diseases to infectious disease, migraine, public health, and more,” said Terry Myerson, CEO and co-founder, Truveta. “Now, we bring that foundation to oncology.”

The expanded dataset includes more than 100 million imaging studies, including CT, PET, MRI, and mammograms, as well as data on mortality, biomarkers, lines of therapy, treatment response, and disease progression. It also includes information on cancer stage, grade, and performance status, linked with structured clinical notes.

“Our expanded data capabilities provide researchers with unparalleled insights into the full patient journey,” said Michael Simonov, MD, vice president of Product at Truveta. “These data will enable deeper understanding of how to diagnose and treat disease, unlocking new opportunities to drive evidence-based advancements in oncology care.”

The oncology dataset includes nearly 900,000 patient journeys for prostate cancer and more than 19 million mammograms. The company notes that many existing oncology datasets capture only medical oncologic care and may exclude early interventions provided in primary care or surgical settings. Truveta integrates data across care settings, which may include surgery, radiation, and diagnostic procedures.

Truveta uses natural language processing and AI through its Truveta Language Model to extract clinical concepts from unstructured notes, such as progress reports, operative summaries, and imaging documentation. This process is supported by, “clinical-expert, human-in-the-loop feedback systems,” according to the company.