Inpatient coding and the role of documentation software

Published on February 8, 2017

First published on here.

by Crystal R. Stalter, CPC, CCS-P, CDIP

Long before ICD-10 became a focus, working as a clinical documentation improvement (CDI) manager with physicians to improve their progress and/or operative notes was a challenge. They either got it, or they didn’t.

As the transition from paper charts to an electronic medical record (EMR) began, providers started to understand how to better document their visits since they had to choose from dropdown menus and multiple options to complete their notes.

As ICD-10 approached, a new awareness of medical necessity denials and revenue impact took shape. Providers began looking for ways to document better in less time.

Enter natural language processing (NLP) and front-end speech. Products and software came along that allowed physicians to dictate their notes in real-time into the EMR. The NLP software “learned” the physician or provider’s speech patterns and saved their profile, making each experience with documenting faster and more accurate.

Working with documentation software

Some providers embraced this technology with open arms, and others, well, they were less enthused. It has been interesting to me over the past six months or so to watch my healthcare providers interact with their technology. I have a keen interest in this since every day at my job we strive to make technology better for the providers in an effort to give them more time to spend with their patients. In addition, we want the technology to be interactive between the providers, their clinicians and their coding staff. Here are a just a few of my observations:

Physicians have a love/hate relationship with their EMRs. When I am with a physician who is sitting in the room with me and typing away, or dictating into his phone (some have actually done this right in front of me), it has been interesting to me to see just how quickly they move from field to field, or, when the occasion has allowed me to actually listen, to see just how specific their documentation is.

At times, I have even interjected that they may want to include type or acuity in their notes. I should give the disclaimer that most of my providers know what I do for a living, so they are usually not offended by my “help.”

In fact, they laugh and tell me their coding manager thanks me every time I’m in the office. This has led me to question why, as we are over a year and a half into ICD-10, are we still reminding providers about documentation? Without message overload, how can we develop content relevant to their specialty that is complete, efficient and easily resolved? Obviously, correcting underspecified conditions at the time of the patient encounter has a direct ripple effect through the lifecycle of that patient’s stay.

As an inpatient, the entire patient encounter has the opportunity to be reviewed by a CDI specialist, especially if the patient is a Medicare patient. The CDI specialist is tasked with reviewing that patient encounter in its entirety, and ensuring that the conditions for which the patient is treated are fully documented, allowing for CC/MCC coding opportunities which affect the diagnosis-related group (DRG) assignment.

With the transition of healthcare into a more value-based reimbursement model, the capture of all conditions is imperative, and has a direct impact on severity of illness and risk of mortality scores which affect the overall risk adjustment and quality scores of the hospital.

Software to assist CDI, like NLP technology to reason the patient encounter and identify those conditions with query opportunities, is paramount to helping a CDI team to be more efficient in their work. Automating the chart review process allows for more chart reviews during their day, and potentially reaching beyond just Medicare patients to other payers for an even greater impact on quality and reimbursement for the hospital.

Effect on coders

Once the patient is discharged, it is the coding teams’ time to shine. If the hospitals’ providers and clinicians have an EMR using NLP technology, their jobs are much easier. From the physicians/providers to the CDI specialists, documentation has been more robust, conditions have been queried and fully specified, and by the time it has reached coding, it has become a fully documented encounter.

All that is left is for coding to assign the appropriate diagnosis codes to their highest specificity, ensuring capture of CC/MCC conditions and appropriate DRG assignment. All in all, a faster process from discharge to claim submission. Of course we understand it is not always this simple, but it could be, and perhaps should be.

In the outpatient setting, there are fewer steps between the face-to-face encounter and bill submission, but the documentation needs are one in the same. Much like my “in-person” reminder to my doctor to include “type” when documenting my encounter, how can we effectively use the NLP engine to do this with each encounter?

When the physician or mid-level provider documents to the fullest specificity, the coding team is able to assign the most appropriate diagnosis code, ensuring much less time that balance is registered in accounts receivable as “not paid”. Medical necessity denials are not a concern, and conditions that qualify as a hierarchical condition category are submitted with the most appropriate diagnosis code.

Of course, I am not able to observe all these processes first-hand as a patient, but my experience on the “other side” gives me insight into the life cycle of my encounter and claim. I can see the diagnoses that were submitted when I review my insurance claim, and that gives me insight into what occurred or didn’t occur with the documentation of my encounter.


There is no question that fully specified documentation is the key to quality care, compliance, and eventual reimbursement. Technology has come such a long way to support the providers’ efforts to complete their documentation in the most efficient manner possible. We can reach them at the time of the patient encounter, providing them with tools and insight for fully specifying patient conditions.

In turn, the CDI specialists and coders are more efficient in their roles, having software engines that do the heavy lifting and provide them with complete documentation from which fully specified diagnosis and procedure codes can be assigned.

At the beginning and the end of this cycle is the patient. Giving providers time to spend with their patients and ensuring the patient’s encounter is fully and completely documented is the focus of my job every day. As a patient, I am appreciative of my doctors’ time; as a CDI manager, I am grateful for insight and perspective to help us help the doctors, hospitals, and staff.

Editor’s Note: Stalter is the CDI manager for M*Modal in Pittsburgh, Pennsylvania. She has over 30 years of experience in the healthcare industry, with most of her focus on coding, compliance, and physician documentation. She has spent many of those years as a consultant, working with physicians and hospital HIM departments to improve their workflow processes and revenue cycles. For questions please contact editor Amanda Tyler at Advice given is general. Readers should consult professional counsel for specific legal, ethical, clinical, or coding questions. Opinions expressed are that of the author and do not represent HCPro or ACDIS.