AI transforming Healthcare by Optimizing RCM

Cracking the code

The large aging population has naturally created a significant demand for health services, which, in turn, places considerable pressure on health systems and the number of physicians and nurses needed to meet this demand. However, this deficit also extends to revenue cycle management.

In a survey by PricewaterhouseCoopers and Becker’s Hospital Review, 83 percent of healthcare leaders reported labor shortages, closely mirroring the 84 percent who said their organizations were behind on cash collections. Nearly two-thirds of respondents (63 percent) believe that technology is essential to addressing this issue.

Another survey of over 200 chief financial officers and revenue cycle vice presidents revealed an even grimmer personnel outlook, with 90 percent reporting labor shortages in their billing departments. Respondents indicated that half of their billing roles were currently vacant, and 48 percent admitted to witnessing patient billing errors due to the lack of experienced staff for coding, claims, and reimbursement.

The pace and demands of modern health systems are often overwhelming, with manual administrative tasks diverting providers’ attention from patient care. When a hospital system lacks sufficient coding staff, the medical coding burden often shifts to providers, leading to burnout and frustrating payment cycles between providers and payers. I’ve witnessed this dynamic repeatedly.

The application of artificial intelligence (AI) can alleviate the growing burden on providers and their health systems. Advances in AI techniques also make it possible to enhance often unreliable medical claims data with highly dependable, clinically comprehensive information. Key data insights buried in electronic health records (EHR) can become more accessible, searchable, and useful for clinical purposes, such as narrowing down a diagnosis or informing a treatment plan.

AI has emerged as a transformative tool, enabling hospitals and health systems to identify tasks that can be automated. This frees up medical coding staff to focus on more complex cases and relieves providers of administrative burdens, allowing them to spend more time with patients.

Navigating data gaps

The biggest challenge for AI companies aiming to help health systems maximize clinical value is data gaps. The healthcare industry often relies on point-to-point solutions that address specific issues, such as reducing denials or measuring infection rates, but these solutions may not capture all relevant data due to these gaps.

Every health system refines its clinical processes to optimize patient flow, identify those in greatest need, and efficiently capture relevant information for both clinical and claims purposes. They continually face the classic challenge of balancing increased access, high quality of care, and reduced costs.

Machine learning and other AI methods, such as large language models and natural language processing, can help bridge the gap between clinical care and administrative tasks. When implemented effectively, AI can allow practices to refocus clinicians on patient care while technology handles the review and translation of medical records for reimbursement, clinical registries, population health, and other applications.

Currently, in healthcare system revenue cycle management, nurses, residents, providers, and medical coders all review charts to extract data for specific use cases. While their methods are similar, their purposes vary.

In the future, artificial intelligence software will offer more meaningful access to the codes generated from any interaction with a provider.

Health systems will accurately code cases for insurance claims on the first attempt, reducing denials and optimizing payment efficiencies. Clinicians will gain a comprehensive view of patients throughout the care continuum, as reflected in medical codes. Researchers will be able to identify the right patients for clinical trials using this data. Surgeons and other specialists will contribute to national registries to track effective techniques.

By taking a holistic approach to AI implementation, we have a unique opportunity to leverage high-quality data for use cases that advance healthcare beyond just the revenue cycle. AI will not only address labor shortages but also enhance the performance of health system professionals, leading to improved patient care.