Hi, I'm David Kartchner

I build large language models (LLMs) to extract, synthesize, and rigorously analyze biomedical data to power applications in biomedicine, drug discovery and healthcare. I am currently building Truveta's proprietary language model powered by the electronic health records of 120 million patients.

Prior to Truveta, I was a PhD student in the Laboratory for Pathology Dynamics advised by Cassie Mitchell. My dissertation research focused on semi-supervised learning and large language models (LLMs) for knowledge graph construction and information extraction with limited to no labeled data. I previsouly completed a MS in Mathematics from Brigham Young University advised by Jeff Humpherys.