Truveta Data comprises billions of EHR data points, representing more than 100 million patient journeys from more than 20,000 clinics and 800 hospitals, updated daily. Truveta Data is held to the highest standards of data quality and provenance, with a rigorous quality control process, outlined in this whitepaper.
Truveta Language Model
Advancements in AI have presented a unique opportunity to transform and clean massive streams of healthcare data to make it available for research, innovation, and patient care. This whitepaper explains the Truveta Language Model, a large-language model used to clean billions of EHR data points for health research.
The pace of medical advancement has been limited by inaccessible data, hard-to-use tools, and opaque research methods, impeding trust. Truveta Studio addresses these challenges by enabling scientifically rigorous research with immediate access to data, powerful analytics and AI, and real-time collaboration. This whitepaper provides an overview of Truveta Studio and how it can accelerate research.
Our security systems protect data through every stage of the data process and have been validated to meet the most rigorous standards for security and privacy. This paper focuses on how we store and secure Truveta Data.
Founded by health systems, Truveta has a deep commitment to patient privacy. This whitepaper shares details of Truveta’s advanced de-identification process and how identifiers in Truveta Data are managed and protected according to HIPAA standards.
Powering device research
Medical device companies are challenged by a significant lack of real-world data on device use in clinical practice. In this whitepaper, learn how Truveta provides critical device specific information linked to deep clinical data to accelerate device research for over 150,000 unique medical devices.
Advancing cardiovascular research
Cardiovascular disease is a leading cause of death in the US, but researchers face many challenges when seeking to study the safety and effectiveness of drugs and devices used to treat it. This whitepaper highlights historical limitations of RWD and explains how Truveta addresses them to accelerate research on outcomes and care.
Truveta Mapper: A zero-shot ontology alignment framework
We share the technical details behind Truveta Mapper the underlying AI technology in the Truveta Language Model. Truveta Mapper leverages a multi-task sequence-to-sequence transformer model to perform alignment across multiple ontologies in a zero-shot, unified, and end-to-end manner. This paper was originally published at arXiv.
We believe it is a moral imperative to harness the power of data to improve healthcare. We know we’ve taken on an enormous responsibility, and we pursue our work with a commitment to patient privacy, broadly enabling research and transparency about our data, all in close coordination with our member health systems.
A time-series analysis of anxiety diagnoses and prescriptions from January 2018 to January 2023
Time-series analysis of first-time pediatric speech delays from 2018 to 2022
Comparative effectiveness of semaglutide and tirzepatide for weight loss in adults with overweight and obesity in the US: A real-world evidence study