NLP/LLM Interest Group

Large language models hold enormous potential for transforming healthcare, but their deployment is often bottlenecked by unstructured data, fragmented pipelines, and inconsistent model-data alignment. Nimblemind.AI addresses these challenges with an agentic AI framework that automates the full clinical data lifecycle from ingestion and de-identification to inference and interpretability. Building on the paper, “Agentic AI Framework for End-to-End Medical Data Inference”, the talk will discuss how specialized agents collaborate to process multimodal data, link structured EHR fields with clinical narratives, and route tasks to the most appropriate foundation or domain model. This framework demonstrates how autonomous agent coordination can turn LLMs into operational tools to contextualize patient records, ensure reproducibility, and generate transparent explanations of model outputs.

The talk will wrap up with a demo of Nimblemind.AI's new platform, NimbleLabs, where users can add a simple clinical description and relevant data to generate a fully operational, specialty-specific predictive model ready for real-world clinical environments.

Navin Kumar, PhD is the co-founder of Nimblemind.AI, a company building agentic AI systems to make clinical data interoperable and actionable. Born and raised in Singapore, Kumar earned their PhD at Yale University under Nicholas Christakis, publishing over 60 papers and securing more than $1M in research funding on AI-driven approaches to population health. Before founding Nimblemind.AI, they led data science and AI initiatives at NYC Health + Hospitals, the nation’s largest public healthcare system, and deployed predictive models that improved chronic disease screening and reduced missed appointments across over one million patients. Witnessing firsthand how data inefficiency limits equitable care, Kumar launched Nimblemind.AI to build scalable, transparent AI infrastructure that improves outcomes, especially for minority populations.