This session introduces a solution architecture for automating the transformation of raw, unstructured, and multimodal clinical data into a standardized OMOP data model using large language models (LLMs) and Agentic AI. We outline the end-to-end system developed by John Snow Labs as part of its Patient Journeys product platform, which integrates document understanding, de-identification, clinical reasoning, medical terminology normalization, temporal context extraction, and longitudinal patient modeling into one scalable pipeline, running securely in each organization’s cloud. By harmonizing structured EHR, FHIR, and claims data with scanned documents, free-text notes, and medical images, the solution builds a more clinically complete patient data model that significantly improves the accuracy of downstream use cases such as risk adjustment, outcomes analysis, quality reporting, and decision support. Attendees will walk away with a practical understanding of how to architect and deploy healthcare data pipelines that make unstructured & multimodal data ready for secondary use.
Speaker
David Talby
David Talby is the Chief Executive Officer at John Snow Labs and Pacific AI, helping companies apply artificial intelligence to solve real-world problems in healthcare and life science. He has extensive experience building and running web-scale software platforms and teams – in startups, open-source projects, for Microsoft’s Bing in the U.S. and Europe, and to scale Amazon’s financial systems in Seattle and the UK. David holds a Ph.D. in Computer Science and Master’s degrees in both Computer Science and Business Administration. He was named USA CTO of the Year by the Global 100 Awards in 2022, Game Changers Awards in 2023, And ACQ5 Global Awards in 2025.
