What AI Can and Can’t Yet Do in Payment Integrity

It’s important to be realistic about what AI can and can’t do currently.

Artificial intelligence (AI) has been a buzzword in payment integrity for years. Companies are increasingly using AI and data mining to identify healthcare savings. This technology can be helpful in the right scenarios.

Data versus Nuance

AI, which includes technologies like machine learning, works well in certain settings involving relatively straightforward claims data. It is good at analyzing data, recognizing patterns and outliers, compiling statistics, and making calculations in scenarios where the appropriate code assignment is obvious and there are no gray areas. But not every scenario is strictly data-driven. Some situations need to be evaluated and interpreted, and that means they require human experience and intelligence.

When a patient’s chart is reviewed, clinical decisions governing diagnosis and treatment are made by a physician. This includes the creation of notes verifying what actually happened and precisely for what the payor is paying. Physicians are required to understand and document the situation, defining the evaluation methods and processes utilized to care for the patient and determine the level of care provided, patient risk categories and circumstances, etc. Artificial intelligence is not always capable of picking up on the nuances required for this. Medical records still need to be reviewed by humans to determine things that data alone may not be able to answer.

AI cannot use human experience to make decisions. It is not well-suited for situations that require logical reasoning or interpretation of notes.

A Matter of Intent

Accurate coding should recreate a physician’s thought process. Machines may be able to identify and analyze codes and keywords, but they cannot interpret intent. Take, for example, the selection of a principal diagnosis on an inpatient claim, through which the coder is supposed to identify the condition that was found, after study, to have occasioned the admission. This requires some interpretation of what’s going on in the patient’s stay that may not be accurately captured in the kind of data points that machine learning relies on – in other words, discrete pieces of data, such as specific codes or keywords.

AI can collect the data, but it takes a human reader capable of asking questions to put that data together into a story that accurately reflects the physician’s intent and the patient’s experience. This may involve discussion with a physician to find out whether certain factors were ruled in or ruled out during the encounter. If a particular keyword shows up in a record, does it mean that factor was ruled out? AI may not be able to tell.

Gray Areas

Relying on AI for broad-stroke information can also be problematic. For example, say you have a particular facility whose AI-reviewed data is showing a high rate of codes for certain complications. At first pass, this facility looks like an outlier, and could potentially be a problem. When a human reviews the data, it turns out that the facility is a trauma center. So, the codes were appropriate, but the AI mistakenly flagged it as an anomaly.

These problems are a measure of the complexity of the healthcare field. Coding has so many variables that it sometimes requires a bit of human ingenuity to figure out what is really going on for any given case. This is especially true in situations where there is a gray area around the coding process, such as in cases of sepsis, where the criteria are not always simple and clear-cut. Even in the simplest situations, coding and reimbursement are extremely complex, and technology alone cannot guarantee improvements in payment integrity.

One sure way in which AI can benefit a payment integrity program, however, is by tracking and flagging more common errors. This in turn frees up resources to allow your team to focus on the more complex situations that AI may not be as good at handling.

Until AI starts to look more human-like – think Data from Star Trek, as opposed to Alexa – the best payment integrity work will come from a combination of humans and machines. When experienced coders are equipped with the best tools, you get the best of both worlds.

Facebook
Twitter
LinkedIn

Laura Collier

Laura Collier is president of Penstock, a payment integrity and reimbursement consulting company. Penstock is an affiliate of Goodroot, a community of companies reinventing healthcare one system at a time. Goodroot is committed to eliminating medical debt, lowering healthcare costs, and increasing access to quality care.

Related Stories

Leave a Reply

Please log in to your account to comment on this article.

Featured Webcasts

2026 IPPS Masterclass 3: Master MS-DRG Shifts and NTAPs

2026 IPPS Masterclass Day 3: MS-DRG Shifts and NTAPs

This third session in our 2026 IPPS Masterclass will feature a review of FY26 changes to the MS-DRG methodology and new technology add-on payments (NTAPs), presented by nationally recognized ICD-10 coding expert Christine Geiger, MA, RHIA, CCS, CRC, with bonus insights and analysis from Dr. James Kennedy.

August 14, 2025
2026 IPPS Masterclass Day 2: Master ICD-10-PCS Changes

2026 IPPS Masterclass Day 2: Master ICD-10-PCS Changes

This second session in our 2026 IPPS Masterclass will feature a review the FY26 changes to ICD-10-PCS codes. This information will be presented by nationally recognized ICD-10 coding expert Christine Geiger, MA, RHIA, CCS, CRC, with bonus insights and analysis from Dr. James Kennedy.

August 13, 2025
2026 IPPS Masterclass 1: Master ICD-10-CM Changes

2026 IPPS Masterclass Day 1: Master ICD-10-CM Changes

This first session in our 2026 IPPS Masterclass will feature an in-depth explanation of FY26 changes to ICD-10-CM codes and guidelines, CCs/MCCs, and revisions to the MCE, presented by presented by nationally recognized ICD-10 coding expert Christine Geiger, MA, RHIA, CCS, CRC, with bonus insights and analysis from Dr. James Kennedy.

August 12, 2025

Trending News

Featured Webcasts

The Two-Midnight Rule: New Challenges, Proven Strategies

The Two-Midnight Rule: New Challenges, Proven Strategies

RACmonitor is proud to welcome back Dr. Ronald Hirsch, one of his most requested webcasts. In this highly anticipated session, Dr. Hirsch will break down the complex Two Midnight Rule Medicare regulations, translating them into clear, actionable guidance. He’ll walk you through the basics of the rule, offer expert interpretation, and apply the rule to real-world clinical scenarios—so you leave with greater clarity, confidence, and the tools to ensure compliance.

June 19, 2025
Open Door Forum Webcast Series

Open Door Forum Webcast Series

Bring your questions and join the conversation during this open forum series, live every Wednesday at 10 a.m. EST from June 11–July 30. Hosted by Chuck Buck, these fast-paced 30-minute sessions connect you directly with top healthcare experts tackling today’s most urgent compliance and policy issues.

June 11, 2025
Open Door Forum: The Changing Face of Addiction: Coding, Compliance & Care

Open Door Forum: The Changing Face of Addiction: Coding, Compliance & Care

Substance abuse is everywhere. It’s a complicated diagnosis with wide-ranging implications well beyond acute care. The face of addiction continues to change so it’s important to remember not just the addict but the spectrum of extended victims and the other social determinants and legal ramifications. Join John K. Hall, MD, JD, MBA, FCLM, FRCPC, for a critical Q&A on navigating substance abuse in 2025.  Register today and be a part of the conversation!

July 16, 2025

Trending News

Prepare for the 2025 CMS IPPS Final Rule with ICD10monitor’s IPPSPalooza! Click HERE to learn more

Get 15% OFF on all educational webcasts at ICD10monitor with code JULYFOURTH24 until July 4, 2024—start learning today!

CYBER WEEK IS HERE! Don’t miss your chance to get 20% off now until Dec. 2 with code CYBER24