Many HIM professionals caught on to the limitations of
NLP and demanded more. They needed a tool comprehensive
enough to improve accuracy, enhance efficiency, and redefine
their current coding workflow so that it could be consolidated
into a unified workspace.
As a result, CAC’s evolution continued by taking NLP a few
steps further. Now, sophisticated CAC technologies utilize
artificial intelligence (AI) and machine learning to enable far
more accurate code suggestions. Essentially, the AI analyzes
the electronic documentation and uses what it has learned to
apply coding rules and guidelines. The AI considers all written documentation within a patient record to build out codes.
It can understand when it is appropriate to combine codes,
how to comprehend negations, and more. The machine learning then learns code suggestion patterns from each action
performed by a coder within CAC and will overlay what it has
learned from those actions to consistently suggest accurate
codes. The more data and information that is fed through CAC,
the more it will learn, and the more accurate it will be for coders to review and validate.
These innovations are driving improved revenue cycle
outcomes every day. But how else will CAC technology be
leveraged to unlock new opportunities and applications of
its data? While many answers have yet to emerge and will
evolve over time, other opportunities have already come to
Better Workspace Organization
Many organizations are beginning to use CAC not only for
coding, but also for CDI, quality, case management, auditing,
management reporting, and more. It is important that CAC
systems be tailored to address specific roles and workflows.
As a result, the AI can be configured to automate workflows
within the application
In other words, when AI is incorporated into the workflow
organizations can ask such questions as: How does an or-
ganization prioritize which charts hit which coder’s queue?
Are these priorities based on payer, coder specialty, patient
type, or other factors? What is AI’s role in CDI? How do or-
ganizations prioritize which cases should be reviewed by a
CDI specialist each day? Is this based on possible query op-
portunities that are generated from target reasons or events
that occurred during the patient stay—perhaps patients with
congestive heart failure lacking specificity or patients with
clinical indicators of sepsis? These custom workflows can
and should be configured, enhanced, and automated by AI to
enable a streamlined and collaborative approach.
A unified, collaborative workspace also provides many
benefits. Abstracting, querying, and other customary coder
tasks can be performed within newer CAC technologies,
eliminating the need to toggle between multiple systems.
Because CDI is also commonly integrated within CAC, cod-
ers have the benefit of knowing what the CDI specialist did
while the patient was present. In addition, coders and CDI
specialists can communicate by leaving notes or book-
marks for each other or for other end users such as auditors
or management. These features, in addition to those result-
ing from other innovative tools, go beyond the traditional
functions of CAC. They have allowed end-users to signifi-
cantly increase their productivity and to achieve greater
revenue cycle outcomes.
Data-driven organizations can leverage CAC to gain new
insights into their data—and determine areas for opportunity. In-depth reporting capabilities allow management to
track and monitor productivity, query impact, query turnaround times and response rates, and monitor case mix
index trends, just to name a few. Organizations also are
looking to track and monitor hospital-acquired conditions,
patient safety indicators, hospital readmissions within 30
days, and patients with current or previous hierarchal condition categories. The ability to extract these insights from
CAC will help to paint a picture of an organization’s current
state, processes, outcomes, patient population, and other
key factors that will allow them to determine where they
New industry demands will surface, further expanding future needs and uses for CAC. AI and machine learning in
these technologies will continue to get smarter and will
learn new mechanisms for problem-solving in ways previously unimaginable.
Organizations looking to position themselves for future
success should seek CAC solutions from vendors who values
artificial intelligence and machine learning, enabling them
to provide more accurate code suggestions, logical workflows, and the ability to adapt to the ever-changing needs of
the healthcare industry. ¢
1. AHIMA e-HIM Work Group on Computer-Assisted Coding. “Delving into Computer-assisted Coding” (AHIMA
Practice Brief). Journal of AHIMA 75, no. 10 (Nov-Dec
Kristi Fahy ( email@example.com) is an account executive at DVS, a
premier partner of Dolbey.
CAC technologies, designed to
be a productivity tool, have come
a long way since they first made
their debut in the early 1990s.