The Evolution of Coding and What’s on the Horizon

Coding and coding technologies have undergone a dramatic – and rapid – evolution. What began as a manual, paper-based process involving massive ICD-9-CM diagnostic and procedural code manuals has transformed into a highly specialized digital cloud-based process bolstered by predictive analytics, artificial intelligence (AI), and natural language processing (NLP).

Now, computer-assisted coding (CAC) enables technology to electronically review notes within electronic health records and apply system logic and standard coding rules to propose and group codes based on the presence of diagnostic words and phrases. (Download our white paper here.)

Clinical documentation integrity (CDI) tools also are helping improve provider documentation and ensure ICD-10’s higher specificity levels are supported. But substantial advances are still on the horizon. For example, clinical language understanding (CLU) is being integrated with CAC and bringing with it the ability to analyze free text within clinical documentation to extract appropriate data for use in various healthcare applications, including coding.

Expect also to see robotic process automation (RPA), or bots, in healthcare leveraging AI to automate mundane, rules-based processes such as ensuring bundled procedures include all the required codes and modifiers.

Autonomy and the future of technology-driven coding

Autonomous Coding promises a fully automated solution capable of "understanding" unstructured clinical notes that rapidly and accurately code charts without any human intervention. The adoption of predictive analytics and the potential already demonstrated by continued advances in AI, ML, and NLP have set the stage for emerging technologies that are poised to transform coding into a fully autonomous process in which the coders of today are tomorrow’s auditors.

This kind of predictive insight reduces revenue losses because of missed procedure coding. When coupled with AI and ML to boost its accuracy over time, enhanced CAC technology accelerates the overall process and advances coding automation by expanding its potential beyond routine cases. While details and kinks get worked out, these areas of advancement will have a significant impact on coding.

Where will this take us? Fully autonomous coding. Let me explain.

As the accuracy of automated coding technology expands, it brings the process closer to full autonomy. However, pushing CAC across the last mile to actual autonomous coding requires technology capable of "understanding" unstructured clinical notes. This is where coupling clinical language understanding (CLU) with AI, ML, and NLP comes into play.

CLU analyzes the free text within clinical documentation and extracts appropriate data for use, drawing upon clinical knowledge and computational linguistics to create a digital narrative of the physician’s documentation. It then applies this understanding to determine what within the documentation is relevant and which codes are most appropriate to assign to the case.

Autonomous coding technology also will understand what it does not know and flags those charts for human review. The result will accelerate end-to-end coding processes, complete charts in seconds, and the whole process in minutes while pushing accuracy levels to near perfect and generating astronomical productivity gains – a 700% increase in one pilot program.

Ultimately, autonomous coding promises to accelerate the revenue cycle by eliminating missing reimbursement opportunities, backlogs, delays, and claims errors that plague human-centered coding processes. It’s also elevating professional coders by transitioning them into the role of auditor – where yet another emerging technology, bots, will support them. Bots are AI-powered "digital critters" used for repetitive and manual tasks like claims reviews.

In coding, bots stand in for human auditors on cases requiring only cursory checks, such as ensuring bundled procedures include all the needed codes and modifiers. This frees auditors to focus on the more complex cases requiring deeper quality assurance before being released as claims. As a result, adding bots to the coding process at any level of automation can further reduce the risk of denials and, subsequently, lost reimbursements.

A robust CAC-powered single-path coding initiative can help provide better care while improving the revenue cycle. With time, the value and ROI on AI-based CAC and ancillary supporting solutions are only set to increase, making it a future-proof choice in healthcare technology – taking the sector further from the days of manually-driven inputs and procedures.