With more than 7 million oncology patient journeys spanning more than 100 cancer types, Truveta is leading a new era in cancer research, delivering an unprecedented breadth of regulatory grade data to support researchers in accelerating oncology therapy adoption and advancing critical cancer research.
We provide the most representative, complete, and timely patient journey data, exceeding FDA standards of data quality, data provenance, and audit readiness. With EHR data from more than 120 million patients from leading US health systems linked with closed claims for more than 200 million patients, Truveta Data enables researchers to study yesterday’s care today with the most complete view of the longitudinal patient journey.
With this expansive oncology data, Truveta now provides researchers with a complete, longitudinal view of the patient experience across all care settings.
Truveta Data empowers researchers to understand rich diagnosis information along with more than 100 million imaging studies across all modalities (e.g., CT, PET, ultrasound, mammograms, MRI, etc.) and mortality data and closed claims, so researchers gain access to a unique and holistic view of cancer treatment and its broader health impacts.
With advancements in Truveta Language Model and the Truveta Genome Project, Truveta will expand into lines of therapy, reasons for discontinuing therapy, progression-free survival, and treatment response across ever-broadening and diverse patient populations.
Overall, these data will serve to conduct robust health economics and outcomes studies, advance clinical trials, and drive progress in precision medicine.
The American Cancer Society estimates that 1 in 8 men will be diagnosed with prostate cancer in their lifetime, with 313,780 new cases expected this year in the US alone. Truveta Data includes longitudinal data from almost 900,000 patients diagnosed with prostate cancer.
Most real-world datasets in oncology contain only data from a patient’s medical oncologic care, such as when the cancer has progressed and advanced treatments are needed. These data miss all the care the patient was provided in other settings, like urology or primary care, which may include surgeries, medications, and radiation therapies.
Truveta Data combines these longitudinal data, along with stage, grade, biomarkers, performance status, and critical outcomes to enable researchers to advance their discovery within the disease.
According to the US Center for Disease Control (CDC), breast cancer is the second leading cause of death for women in the United States, affecting more than 272,454 women in 2021.
Truveta Data includes more than 19 million mammograms, which are a critical tool in screening, diagnosing, and treating breast cancer, as well as stage, grade, biomarkers, performance status, primary diagnosis, disease progression, metastasis, procedures like mastectomy, and more to enable researchers to advance critical insights in breast cancer care.
In addition to prostate and breast cancer, Truveta enables the study of any cancer, from the most common (e.g., lung, colorectal, melanoma, bladder, non-Hodgkin lymphoma, and more) to the less common or rare (e.g., esophageal, pancreatic, gastrointestinal stromal tumor, multiple myeloma, leukemia, glioblastoma, cervical, ovarian, osteosarcoma, thyroid, and more).
Traditional approaches in real-world oncology data require manual curation of data, involving teams of hundreds or thousands of clinical abstractors to painstakingly extract information from clinical notes. These laborious efforts come at the expense of scale and disease coverage, with most datasets containing small cohort numbers or only focusing on the most prevalent oncologic diseases.
Through breakthroughs with the Truveta Language Model, Truveta leverages AI technologies at scale to deliver novel data across all cancer types, while maintaining quality through clinical-expert, human-in-the-loop feedback systems. For example, Truveta receives all clinical notes generated during a patient’s care. This includes progress notes, nursing evaluations, procedure/operative reports, referral notes, discharge summaries, imaging reports, and more. The Truveta Language Model extracts clinical concepts from notes at scale, linking them to structured data to enable robust research across all cancer types.
Updated daily for the most current view of patient care, Truveta Data accelerates evidence generation by replacing costly clinical trials and registries with immediately available, regulatory grade data. This allows for faster, more efficient evaluations of cancer therapies, ensuring that life-saving treatments reach patients more quickly.
For more information about Truveta’s expanded oncology data and analytics capabilities, visit the Truveta oncology page.
