Veradigm, a healthcare data and technology company, partnered with Snowflake’s Frontier Engineering team to build a proprietary AI model for medical comprehension and complex medical coding. Working together, the teams delivered the custom model in seven weeks.
Designed to streamline provider workflows, support coding accuracy and reduce administrative work, the model was trained on synthetic clinical data grounded in Veradigm's real-world records, so patients’ private data wasn’t accessed. The model helps providers assign accurate codes for complex cases such as patients with chronic disease or multiple conditions. It also extracts structured data from unstructured records and supports quality and risk adjustment programs.
For Veradigm's clients, that means less time spent on manual coding and more complete, accurate documentation.
"Our clients need AI that handles the complexity of real-world healthcare, not just general tasks," said Gaurav Kaushik, SVP Applied Intelligence at Veradigm. "With Snowflake's Frontier Engineering team, we built a model in seven weeks that performed up to nine times better on complex medical coding while protecting patient privacy. It's designed to help our clients reduce administrative burden and improve coding accuracy. That gives their teams more time for patient care and for growing their practices."