Revenue cycle management company Ensemble Health Partners is working with clinical intelligence company Cohere to build the healthcare industry’s first RCM-native large language model.
Four things to know:
1. The custom LLM will be informed by Ensemble’s operational experience and data, fine-tuned on real RCM tasks and then embedded into AI agents that power end-to-end orchestration from patient intake to account resolution, according to a March 31 news release.
2. The system is designed to efficiently navigate the multi-step rules and documentation requirements set forth by payers and to closely mirror the thought processes and working methods of high-performing RCM operators.
3. The project will not use identifiable client data or PHI for model training, according to the release. It will draw on Ensemble’s broad insights from working with a variety of health systems, including operator expertise, documented procedures, industry‑wide patterns, payer trends and denial behavior. This will be supported by synthetic datasets created from properly certified, deidentified sources within a HIPAA-compliant environment.
4. The companies said the RCM-native model is designed to enhance — not replace — EHR-driven content by providing greater context and task-specific guidance and assisting operators in navigating payer requirements that fall outside of EHRs. It will also support decision-making, documentation and follow-up actions beyond what the host system offers.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.