Optimizing Health Care Revenue Cycle Management With AI

Discover how integrating artificial intelligence (AI) in revenue-cycle management (RCM) can revolutionize health care operations and improve financial outcomes, with examples of successful implementation in hospitals and health systems across the country as shared in an article by the American Hospital Association (AHA). 

“With third-party payer denials and the rising cost of collections, providers increasingly are exploring solutions,” wrote the AHA. “About 46% of hospitals and health systems now use AI in their RCM operations, according to an AKASA/Healthcare Financial Management Association (HFMA) Pulse Survey.” 

Almost 75% of hospitals are automating RCM through tools such as AI and robotic process automation (RPA) for limited specific functions. Using AI in health care RCM has the projected potential to reduce administrative burdens and expenses and increase efficiency and productivity. 

“Generative AI can prevent avoidable errors by analyzing extensive documentation to identify missing information or potential mistakes, thus optimizing coding and other processes, proponents argue,” wrote the AHA. 

Generative AI can be used to creating appeal letters and manage prior authorizations, but more advanced applications such as enhancing front-end processes and data validation are still in development. Additionally, it can improve communication within the revenue cycle by assisting in staff training and enhancing interactions with payers and patients.

A 2024 HIMSS report shared some key applications already in use, including automated coding and billing, predictive analytics for denial management, revenue forecasting and financial planning, patient payment optimization, enhanced data security and compliance, and operational efficiency. Examples include AI-driven NLP systems that assign billing codes, predictive analytics for identifying likely denials, AI-powered analytics for revenue forecasting, personalized payment plans based on AI algorithms, fraud detection for data security, and RPA for automating repetitive tasks.

For RCM improvement examples specifically, Auburn (New York) Community Hospital started leveraging RPA, NLP, and machine learning about 10 years ago and “…has experienced a 50% reduction in discharged-not-final-billed cases, a more than 40% increase in coder productivity and a 4.6% rise in case mix index.” 

Banner Health automated part of its “insurance coverage discovery by utilizing a service that identifies each patient's coverage, coupled with an AI bot that integrates this information into the patient’s account across various financial systems.” The health system utilizes bots to handle requests from insurance companies, automatically generate appeal letters, and determine the justification for write-offs based on denial codes and payment probabilities.

A Fresno community health care network reviews claims before submission with AI and identifies potential denials based on historical payment data and payer rules. This proactive approach has led to a 22% reduction in prior-authorization denials and an 18% decrease in denials for services not covered, saving 30-35 hours weekly on back-end appeals without requiring additional RCM staff.

To optimize AI's potential in RCM, AHA suggests optimizing staff time, improving accuracy, assessing risk factors, and forecasting significant adoption in the health care industry within the next 2 to 5 years. Generative AI may assist in identifying duplicate patient records, automating eligibility determination, coordinating prior authorizations, and suggesting solutions for administrative gaps. It may also enhance clinical documentation accuracy, reduce time spent on recordkeeping, assist with accounts receivable follow-ups, and create fact-based appeals to health insurers. Health systems can invest in mitigating risks associated with AI by establishing guardrails in data structuring and validating computer-generated outputs to prevent bias or inequitable impacts.

Reference 
3 ways AI can improve revenue-cycle management. AHA. Accessed June 4, 2024. https://www.aha.org/aha-center-health-innovation-market-scan/2024-06-04-3-ways-ai-can-improve-revenue-cycle-management