Computable longitudinal patient journeys from structured and unstructured EHR data

A suite of large pre-trained language models demonstrated the ability to accurately extract computable clinical data from unstructured electronic health records and integrate findings into knowledge graphs representing longitudinal patient journeys. The system facilitates understanding of real-world patient trajectories and treatment responses by converting free-text clinical notes into structured, queryable data. Published in Nature Medicine, the approach is broadly applicable across disease areas, including oncology, where real-world evidence from EHR data is increasingly used to study treatment outcomes and care patterns.