Ensemble, Cohere partner on LLM for revenue cycle management

Ensemble Health Partners and Cohere, an enterprise AI company, plan to build a large language model, or LLM, specifically for revenue cycle management.

The companies announced on Tuesday that they will expand their partnership to create healthcare's first revenue cycle management (RCM)-native LLM. This will be a fully custom model shaped by RCM-specific insights using Ensemble's data from health system partners, including operator expertise, documented procedures, industry-wide patterns, payer trends and denial behaviors.

 "For more than a decade, Ensemble's domain expertise has powered our clients' financial performance and award‑winning RCM results. What we're building with Cohere elevates this advantage," Judson Ivy, Ensemble's president and CEO, said in an announcement.

"Our associates' operational knowledge, well‑defined processes and insight into payer behavior are shaping how models learn and solve problems that will help us reduce friction across the patient financial journey and continue delivering the trusted results health systems count on," he continued.

Ensemble and Cohere are flipping the script on AI use in the revenue cycle by offering an RCM-native LLM versus other popular AI products that merely wrap prompts around general-purpose LLMS, the companies said. Consequently, the models fail to accurately manage payer-specific behavior, regulatory nuance, workflow dependencies and complex, multi-step processes within the revenue cycle.

An RCM-native LLM, though, would not have to rely on heavy context engineering to teach an LLM RCM logic at inference time, Ensemble explained. Rather, the LLM would be taught RCM tasks and have AI agents embedded to power end-to-end workflows across the entire revenue cycle.

Overall, the companies aim for the LLM to closely mirror the thought processes and working methods of high-performing RCM operators to drive higher accuracy and productivity compared to off-the-shelf LLMs.

"Together with Ensemble, we're committed to building purpose‑built AI solutions that truly understand the complexities of healthcare revenue cycle operations," said Cohere co-founder and CEO Aidan Gomez. "By pairing Ensemble's deep domain expertise with our secure, enterprise‑grade AI capabilities, we can create agents that deliver greater accuracy, consistency, and reliability while meeting the highest standards of privacy and security. Our shared goal is clear: reduce administrative burden so providers can focus on delivering exceptional patient care."

The RCM-native LLM is expected to be ready later this year.

The timing could be perfect, as 80% of health systems responding to a Healthcare Financial Management Association and AKASA survey last year said they are taking action or implementing generative AI for revenue cycle management.

More health system leaders said their organizations are exploring, piloting, implementing or making some tangible strides with generative AI adoption compared to two years ago. Still, about 20% of organizations had not even begun adopting generative AI, including LLMs, for RCM.

Major barriers to adopting this AI include integration with existing IT systems, cost and budget constraints and concerns about data security.

Jacqueline LaPointe is a graduate of Brandeis University and King's College London. She has been writing about healthcare finance and revenue cycle management since 2016.