.png)
Key Takeaway: The never-ending stream of articles about healthcare AI has made it difficult to identify where in the revenue cycle healthcare organizations are prioritizing AI integration in the near term. To help sift through the noise, we’ve identified three key areas of RCM where healthcare organizations are either prioritizing or actively leveraging AI to streamline processes and improve operational efficiency: medical coding, prior authorization, and patient estimates.
Medical coding refers to the process of translating healthcare diagnoses, procedures, services, and equipment into universal alphanumeric codes for billing and reimbursement purposes.
While essential for ensuring accurate reimbursement for services provided, medical coding has remained a largely manual, error-prone process for the past several decades and was found to be one of the primary contributors to the $256.6 billion spent annually on “administrative complexity,” in a study by the Journal of the American Medical Association. Additionally, current challenges such as the shortage of medical coders, ever-changing guidelines, and increasing costs have added additional administrative burden to revenue cycle departments and are putting organizations at risk of staff burnout, backlogs, and delayed payment cycles.
To solve the challenges outlined previously and set their departments up for long-term stability, revenue cycle leaders across the country are turning to AI-powered medical coding technology. The most sophisticated type of medical coding AI solution currently available is autonomous medical coding. Powered by multiple subfields of AI such as natural language processing, machine learning, and deep learning, the purpose of autonomous coding solutions is to accurately assign codes to patient encounters and send them to billing, all without any human intervention.
By fully automating the coding process, autonomous medical coding solutions can significantly reduce the administrative burden placed on coders and other revenue cycle staff, accelerate payment cycles, reduce coding-related costs, and ensure high coding quality and compliance.
Autonomous medical coding has been very well-received by health systems, hospitals, and other healthcare organizations, and interest continues to increase year after year. At a recent KLAS Research RCM Summit, revenue cycle leaders said that “autonomous coding and claims management are at the top of their wish lists,” highlighting coding automation as a top priority heading into 2024. Supporting these findings was a recent survey by the Healthcare Financial Management Association, which revealed that around 60 percent of healthcare organizations either use autonomous coding or plan to, with half of the respondents who plan to incorporate the technology intending to adopt a solution within six to 12 months.
Prior authorization is the process through which healthcare providers obtain approval from insurance payers before certain medical services, treatments, or procedures can be performed.
Despite its importance in ensuring that patients receive appropriate care and that the care is aligned with payer guidelines and coverage policies, prior authorization is notorious for being a highly manual process that dramatically increases administrative burden. Due to factors such as extensive paperwork and a lack of standardization among different payer requirements, physicians and their teams spend an average of nearly two business days each week completing prior authorizations, ultimately taking valuable time and resources away from patient care.
AI can help healthcare organizations reduce the administrative burden associated with prior authorization, expedite approvals, and minimize denials by automating the analysis of clinical guidelines, payer policies, and patient histories. Supporting this is an analysis by McKinsey & Company, which suggested that “AI-enabled prior authorization“can automate 50 to 75 percent of manual tasks, boosting efficiency, reducing costs, and freeing clinicians at both payers and providers to focus on complex cases and actual care delivery and coordination.
In terms of current adoption trends, a report from the recent KLAS Research RCM Summit found that prior authorization is “one of the key revenue cycle areas in which provider attendees have used automation,” with 9 percent of the attendees reporting that their organization currently automates prior authorization. Echoing these findings is a survey conducted by the American Medical Association, in which nearly half (48 percent) of over 1000 physicians said that AI would be most helpful in the "automation of insurance prior authorization."
Patient estimates provide patients with the estimated cost (both the total cost and out-of-pocket breakdown) for medical services, treatments, and procedures upfront to facilitate informed financial decisions.
For healthcare organizations, providing accurate patient estimates is incredibly important. When inaccurate estimates are provided, it can lead to additional administrative burden (disputes must be handled manually by resource-strained revenue cycle staff), and most importantly, decreased trust from your patients due to a poor patient experience. It’s worth noting that the recent No Surprises Act has put additional pressure on providers and payers to improve price transparency (in some cases, the bill actually requires that patients receive “good faith” price estimates prior to receiving care).
Traditional tools leveraged by providers to calculate patient estimates rely on standard algorithmic functions. While these tools have helped improve the accuracy of patient estimates (as well as the process for patients themselves), AI promises to bring additional levels of sophistication to the process.
AI-based tools for patient estimates leverage machine learning models to comb through vast amounts of patient, provider, and payer data. Taking into account insurance coverage, benefits, medical history, and other pertinent information, these models can provide more accurate patient estimates compared to non-AI-based solutions and, because they leverage machine learning, the accuracy improves over time. By improving patient estimate accuracy with AI, RCM leaders empower patients to make informed financial decisions, increase patient trust, and strengthen the patient experience.
Patient estimates was one of the first areas of revenue cycle management where healthcare organizations prioritized AI integration, according to a 2020 study. In that same study, 62 percent of the revenue cycle, healthcare IT, and healthcare executives surveyed said that patient estimates would emerge as a leading area for AI integration by 2023, and more recent data reveals this to be the case today.
Learn more about AI in Healthcare in Nym and AHIMA’s webinar, The Rise of AI: Different Applications of Natural Language Processing and Large Language Models in Healthcare.
Interested in learning more about autonomous medical coding with Nym?
