Today, it’s hard to imagine a medical facility managing its revenue cycle without a software system. I bet medical billers and coders — the central pillars holding up the revenue cycle at any healthcare organization — would have much to say about the efficiency of these systems. In fact, they do:
Images credit: Trustpilot (all image rights belong to Trustpilot Inc.)
Yes, software can be hard, and we can’t always get what we want. But if we try to introduce artificial intelligence to help billers and coders, we may get what we need.
AI medical coding and billing come to the rescue. That’s going to be our topic of discussion today. Let’s talk through all the whys and hows of using AI software to improve revenue cycle management.
I bet you sense the timing for such AI innovations is ripe; you just need details before you dip a toe in the water.
- Computer-assisted coding and billing in medicine work wonders. Companies enjoy higher revenue due to faster, more accurate, and more comprehensive coding and streamlined revenue cycle management. Scaling up becomes available almost immediately.
- We can apply different AI technologies to empower medical coders and billers. However, natural language processing seems to be the most promising.
- Machine learning algorithms do not replace human coders and billers. Instead, they elevate them to a supervising position.
Table of Contents:
- Traditional Medical Billing & Coding Process Flow
- Overview of Paper-Based Claim-to-Payment Chase
- How Will AI Help Medical Billing and Coding
- Possible Challenges Faced by Artificial Intelligence in Medical Coding and Billing
- How Topflight Can Help
Traditional Medical Billing & Coding Process Flow
On the face of it, medical billing and coding look pretty straightforward. As providers, we need to set in code all healthcare services received by the patient and bill them to the payer.
We must cross-reference all diagnoses, treatments, examinations, etc., to accurately describe provided services and maximize the revenue potential.
Of course, the devil is in the details. Coders and billers (to a greater degree) must handle quite a few things to keep the revenue cycle afloat. Medical billers play key parts at the beginning of patient interactions and towards the end, while coders hum away in the middle of the process.
As you know, in many healthcare organizations, medical billing and coding can be carried out by the same person. However, as we continue to explore billers’ and coders’ responsibilities side by side, you’ll notice that coding, in particular, is perfect for automation. AI and medical coding are destined for each other.
Also Read: Healthcare App Development Guide: Everything You Need to Know
Let’s quickly recap medical billing tasks. As we go through the list, we’re trying to identify the most laborious, repetitive tasks we can pass on to artificial intelligence.
But before we go any further, here’s a brief disclaimer: artificial intelligence medical billing does not imply we don’t need human talent anymore.
What do billers do?
- Handle correspondence: emails, messages, voice mails, and phone calls (to answer patients’ and insurance companies’ questions)
They often use task management systems to keep tabs on these activities. We could apply AI to sort all their tasks according to their impact on a business’s revenue. Therefore, an optimal scenario is to find a CRM, ERP, or task management platform with AI capabilities.
- Capture patient data, for example, demographics, payment info
You’re right to assume that this task is the front desk’s responsibility. However, billers sometimes have to check and correct any data inconsistency in patient documentation. This data typically gets into the system manually. We could develop a natural language processing app to ease data entry.
- Verify patient eligibility and benefits
For many billers, that still means hanging on the line with an insurance carrier or a clearing house. Ideally, AI medical billing software connects with the corresponding system on the payer’s side to run patient eligibility verification.
- Add charges into a practice system (from a split fee or superbill), or copy this info from an EHR to some other practice management/billing software.
An AI-assisted practice management system can automatically pull the required data as necessary, removing the need for manual work.
- Communicate with providers (some things may be missing: charges, diagnoses, modifier confirmations — anything necessary for drafting a claim and sending it to an insurance company)
Again, AI in medical billing can absolutely handle that and automatically pull data from EHRs and other platforms, asking doctors to verify edge cases.
- Send claims to a clearing house/payer and track their progress
This is definitely a no-brainer area for applying machine learning for medical billing. Why make people click buttons when an AI can automatically send fully prepared claims as soon as they are ready and then monitor the responses based on a set turnaround time for reimbursement.
- Handle rejections from a clearing house to ensure the claims are processed and passed onto insurance carriers. Includes preparation of reconsiderations and appeals.
This is an area for the next potential breakthrough of artificial intelligence in medical billing. The billing software will need to rely on deep learning for the algos to continue learning from errors. And the outcome will be more cleared claims in the future.
- Manage received checks and payments (mailing them to a bank or preparing them for the management)
Electronic payments should take care of that without any AI assistance. However, management might appreciate automatic revenue forecasts based on completed, missing, and delayed payments. Medical billing automation can set you apart from the competition.
What about coders? They have somewhat fewer tasks. Nevertheless, their work is very stressful as it requires complete concentration. And it’s pretty much repetitive and manual in nature.
- Assign ICD-10 codes to all performed services on a patient health record
Finding an appropriate code in the sea of 14,400+ codes is not exactly an easy feat. And ICD-11 introduces 4x more codes.
But it’s not only about the quantity. Coders must also attribute the most appropriate codes: every diagnosis or treatment can be coded differently.
Of course, that’s the best target for applying machine learning in medical coding. Algorithms can learn from approved claims and identify patterns for distributing the most applicable and revenue-efficient codes.
- Manage appeals if auditors reject certain codes or insist on adding, removing, or replacing some other codes in a chart
That’s the most tricky part of coding, and since AI in medical coding relies on past experience, we get yet another confirmation for applying this technology. Machines can untangle the mess of cross-coding when dealing with clinically supported conditions with casual relationships.
Overview of Paper-Based Claim-to-Payment Chase
I honestly thought to include this section here just as a reverence for days gone by when providers had to deal with paper and mail. It turns out, as of 2017, 77% of physician practices still relied on paper-backed processes for billing.
I couldn’t find more recent stats, but even if the rate is closer to 40-50%, that’s still a lot. If you’re a healthcare provider, you know it’s a nightmare for the healthcare industry.
- Collect data for claims
- Prepare and submit claims
- Work through denials
- Register payments
And all of that manually, using mail delivery services. When carriers have strict deadlines for submitting claims, such a paper-based workflow is a disaster.
And note that we’re only discussing the switch to digital workflows. AI and ML-driven data processing is the next step after digitization.
Again, if you’re a provider stuck with paper workflows, you should absolutely check out solutions like GaleAI. I kid you not; you’ll be impressed by the new efficiency of AI-powered coding and billing. This is a must for effective revenue cycle management in the 21 century.
Artificial intelligence in healthcare has already set out on a quiet revolution.
How Will AI Help Medical Billing and Coding
Now that we’ve identified the main areas of applying AI for medical coding and billing let’s take a closer look.
AI in medical coding
First, let’s look at how we can improve medical coding using artificial intelligence.
- What data can we automatically recognize?
AI can flawlessly parse through patient records, doctor notes, and any other documentation — in other words, any digital documentation is a perfect target.
In addition to that, we can also parse scans and other professional imagery produced during treatment. And if we happen to have piles of paper-based notes or, God forbid, patient records, we may choose to use OCR technology (optical image recognition). Turning hand-written notes into digital text makes it possible to seamlessly train smart algorithms.
- How specifically can we apply AI?
How AI manifests during coding is completely up to us. We may use real-time feedback to highlight questionable codes and suggest code replacements.
For example, IBM Watson helps ProSciento, a clinical research organization, code 84% of terms using a single AI-enabled search.
Or we can also apply ML algos post-factum, processing a batch of patient charts and forwarding the good ones onto billing while notifying coders about the ones that need a second thought. Finally, we may use both approaches. Fortunately, the tech allows it.
- Whom is AI coding empowering?
The most obvious answer is coders. Depending on the flow of our app, they become either “super-smart” coders who juggle thousands of codes in a fraction of a second. Or they become supervisors who only need to assess complex edge cases flagged as risky by the system.
However, we can also extend the medical coding AI functionality to providers. If doctors input their notes electronically, we can suggest codes on the fly, drafting a chart for further re-examination by machine learning algorithms.
The benefits of AI in medical coding
Based on these applications of AI, we can get the following improvements:
- virtually unlimited scaling
Superbills get ready faster, way faster, because AI works non-stop, 24/7, and processes more patient records than any human possibly can within the same time frame. It’s like we’re limited only by a cloud provider’s capacity; these are pretty affordable these days.
- higher accuracy and thorough coding
ML helps us capture all necessary codes without missing even pesky ones that may slip through the cracks with manual coding. As a result, providers get appropriate reimbursement without leaving anything on the table. They avoid under-coding due to forgetting to input a modifier or severity level.
- lower operating costs
Since AI takes on a significant load with coding, we can hire fewer manual coders and promote our staff to supervising positions. Or they can handle other, more critical tasks requiring human attention. There’s also less strain on the auditing side.
Also Read: App development Costs: The Ultimate Guide
- use AI to train new staff
Finally, AI can serve the purpose of teaching new hires. Algorithms can compare correct and incorrect coding instances and show new coders the pattern or explain why using other codes is more beneficial.
AI in medical billing
Now let’s go through the same exercise for medical billing.
- What data can AI recognize?
In the case of medical billing, algorithms parse insurance cards, health records, and other digitally captured texts. So we are mainly dealing with NLP, enhanced by a neural network to help identify the risk of rejected claims and form patterns for successful claims.
- How does AI serve billers?
AI helps validate the patient’s insurance eligibility and automate claims submission and tracking. Providers can train algos on rejected claims to predict issues and highlight “risky” ones before they are sent to payers.
Machine learning can also help onboard patients by recognizing their IDs and adding or correcting the corresponding data in health records.
As an experiment, we can allow billers to input data with voice.
Another area of AI application is ranging billers’ tasks according to priority (their impact on the bottom line).
- Whom is AI coding empowering?
On the medical billing side, AI features face billers primarily, but we should also remember that insurance carriers need to support the same infrastructure to churn out approvals or denials faster.
The benefits of AI in medical billing
Medical billing AI brings to the table the following wins:
- more approved claims
- higher revenue due to more accurate code attribution
- lower operating costs
- less burnout
So in a gist, medical billing and medical coding augmented by machine learning lead to:
- less burnout and lower operating costs
- faster claims processing
- more complete claims, accurately describing all treatment and diagnosis procedures
- higher revenue and a healthy, predictable cash flow
Please note that AI only partially replaces coders and billers and promotes them to supervising positions.
Possible Challenges Faced by Artificial Intelligence in Medical Coding and Billing
What about the challenges healthcare organizations may face when applying machine learning in medical billing and coding?
Medical software dealing with patient data must be secure and HIPAA compliant. So it goes without saying that AI-driven medical billing and coding applications that process critical financial and health data must meet these standards.
Also Read: HIPAA Compliant App Development Guide
Different data formats
The ubiquitous interchangeability. Businesses still work with software systems that output data in various formats, which makes it harder to sync. Even if we want to create an AI application to automate coding and billing for our own organization, we have to account for sharing this data with third parties, who may use different tools.
Integrations with carriers
Besides varying data formats, we also need to ensure our insurance partners can seamlessly plug into our automation workflow. There are two ways to address that, either integrate our AI systems with an insurance carrier’s APIs or provide them with our own APIs and tools for syncing claims.
Billers and coders may be under the impression that a company is looking to replace its jobs when undertaking AI implementation. It takes a substantial effort to educate them and explain how their upgraded workflows will benefit the business.
Super intelligent billing and coding robots don’t come out of nowhere. Access to historical data on coded patient charts and processed claims (both rejected and approved) is critical for algorithms training.
Machine learning algos will need to continue learning based on new data and internal audits. That means we must set up a neural network capable of analyzing new data, auditor feedback, and historical data.
Most healthcare organizations still code according to the ICD-10 standard. However, ICD-11 has been in effect since January 1, 2022, and a slow transition to the new format has already started. ICD-11 has more codes and other changes allowing for even more accurate coding.
Topflight’s Experience in this Space
We have solid experience working with various AI automation projects, including natural language processing and imagery recognition. More importantly, we know how to merge this ML/AI development expertise with engaging user interfaces. Because even AI-powered applications operate under human supervision.
We provide full-cycle machine learning development services: from strategy and design to development, testing, and maintenance.
One of the success stories we’re happy to be part of is GaleAI. Their motto is “From medical notes to medical codes in seconds.” GaleAI’s ML engine helps provider increase their revenue potential by up to 15% and saves a great deal of time for coders.
During exuberant tests, a 1-month retrospective audit revealed that the GaleAI platform captured 7.9% of codes missed by human coders, translating into up to $1.14M.
If you have questions about artificial intelligence medical billing or coding and how it can work at your place, reach out.
Frequently Asked Questions
How can we switch from paper based claims to fully automated practice?
It’s best to take one step at a time. First, digitize all existing paper claims using OCR (optical character recognition), train ML algos utilizing this data set, and proceed to controlled automation with human supervision. Only after that can we talk about 100% automated medical coding and billing.
How does AI medical coding work?
AI automatically codes all patient charts based on retrospective data analysis or machine learning algorithms enhance coders’ productivity by advising on appropriate/missing codes.
How does AI medical billing work?
Machines automatically collect and verify necessary data, submit claims, and track their status. Human intervention is only required in edge-case scenarios.