Скачать или смотреть AI-enabled health research with Truveta Language Model

This year, Truveta announced Truveta Language Model (TLM), a large-language, multi-modal AI model for transforming electronic health record (EHR) data into billions of clean and accurate data points for health research on patient outcomes with any drug, disease, or device.

TLM combines pre-trained open large language models with additional training on the most representative clinical data set to achieve over 90 percent accuracy on diagnoses, medications, lab results, clinical observations, and more. Utilizing clean, de-identified data from health system members, TLM is trained upon input representing nearly 100 million patient journeys, including 5.5 billion diagnoses, 3.1 billion encounters, and 2.4 billion medication orders.  

Comprehensive, clean, real-time data like what TLM has unlocked would previously take researchers years to source and clean; and cost millions of dollars to achieve. Now with complete, clean EHR data, researchers can begin asking and answering healthcare questions instantly, carving years off their research process. It’s known in healthcare that it takes 17 years for research at the bench side to change and improve patient care. With AI innovations, like TLM, this lengthy process is getting some much-needed innovation.