In Analytics & Data Management, Artificial Intelligence, Coding & Compliance, Medical Billing & Claims, Revenue Cycle

Insufficient charge capture is a high-impact issue for healthcare organizations and can result in lost revenue and compliance issues. Given current margin pressures, healthcare organizations cannot afford to have sub-optimal processes in this area. Although hospitals and health systems have been working on charge capture challenges for a while, their considerable efforts can still benefit greatly from the application of advanced technologies.

The time has come to apply emerging technologies, such as artificial intelligence (AI), to reduce the time and effort that revenue integrity teams spend on charge capture and, ultimately, increase detection of missing charges, provide more complete claims, accelerate cash flow, and drive appropriate revenue.

Why AI for Healthcare Finance

AI entails using computers to do work that usually requires human intelligence, thinking, or cognition. An AI system “learns” by combing through large volumes of data and uncovering patterns. Although AI applications have not been used widely in healthcare finance, they are now increasingly used in clinical settings (such as interpreting radiology images and diagnostics) and have benefited other industries—and healthcare has the depth and breadth of data required to make these kinds of solutions work.

A well-designed, AI-driven charge capture solution can reliably predict missing charges in patient accounts prior to claim submission. It works with a hospital or health system’s existing technology to flag missed charges alongside providers’ existing coding and claim workflows. And, to be most effective, it needs to deliver charge prediction results in real time, at the point of decision-making, so the user can act quickly to resolve discrepancies, and ensure a more complete claim prior to submission.

Armed with the potential missing charges flagged by the AI system, revenue integrity teams can then review the clinical documentation for the cases in question to ensure services were documented and coded correctly. Then they can accept or reject the charges flagged by the charge capture solution. Some commonly predicted charges include missed or incorrect diagnostics, images or tests, or implants or supply codes. Overlooked or deficient documentation for drugs and injection administration can also be identified.

Constraints of Traditional Rules-Based Systems

AI solutions have some distinct advantages over traditional rules-based options, which report potential missing charges based on manually-created flags triggered by certain conditions. With traditional systems, the rules or flags are often either too aggressive or too conservative, with aggressive rules flagging too many issues and conservative ones failing to detect critical missteps.

And maintaining rules-based systems is time-consuming and resource-intensive due to constant chargemaster and clinical process updates, which require someone to adjust the relevant rule. On the other hand, an AI solution learns without human intervention, and also learns over time based on charge predictions that are accepted or rejected. As new data emerges, it will start to recognize updated patterns as well as any outliers.

Deep Data = Accurate Charge Capture Predictions

By using artificial intelligence to predict missing charges, healthcare providers can more efficiently close gaps, avoiding the potential revenue and productivity pitfalls associated with a sub-optimal process. Change Healthcare now offers a cloud-based solution, Charge Capture Advisor, which works alongside providers’ existing HIS, coding, billing systems, and manual processes as part of a comprehensive charge-capture strategy.

Charge Capture Advisor is trained on the powerful Change Healthcare AI service, which in turn is trained on more than 500 million service lines making up over 180 million unique claims that touch $245 billion in charges. The result: a continuous learning system designed to help revenue integrity teams streamline and optimize the charge capture process.

Get the deep dive now on how Charge Capture Advisor uses AI to improve charge capture.

Jason Williams is Vice President, Business Analytics, at Change Healthcare

While the science and medicine of health care continue to advance, it’s less obvious how to make the same progress when it comes to costs. That’s where payment accuracy comes in. When payers produce bills for reimbursement that are accurate, there’s less administrative cost for both payers and providers — ...

Recommended For You

Start typing and press Enter to search

© 2019 Change Healthcare