RPM caution: Remote monitoring can boost care quality and revenue, but watch out for coding and documentation regs that may curb some enthusiasm

Jennifer SwindleCoding

Much attention has been paid to the explosion of telehealth technology and services during the pandemic. It is viewed as one of the bright spots in an otherwise bleak year in the business of healthcare. Mostly, the action has been in telehealth visits – doctors discussing care with patients over whatever communication devices they have, including phones. Most observers think an expansion of televisits is here to stay, but it is going to be more regulated post pandemic.

Another aspect of virtual care, remote patient monitoring (RPM), may turn out to have a more significant long-term impact on patient care and revenue than televisits. RPM, also called remote physiological monitoring, is the collection and/or analysis of data to help manage a treatment plan related to a chronic and/or acute health illness. It uses digital technologies to monitor, capture, and transmit vitals such as blood pressure, weight, heart rate, and blood sugar levels from patients to providers for assessment, recommendations and instructions.

Revenue enhancer
Thanks to an overhaul of CPT codes for 2020, RPM became one of the more lucrative Medicare care management programs even before the pandemic. The vast majority of RPM services are now billed under four CPT codes: 99453, 99454, 99457 and 99458. There is a small payment for initial patient enrollment into an RPM program, and then a monthly base payment for management of the device and patient readings. Finally, there is an optional service for each 20 minutes of care management – which can be provided by clinical staff – up to 60 minutes total. When added together, each RPM patient can earn a practice up to around $210 per month, according to McKinsey & Co. projections.

CMS has proposed further changes to these services for 2021, so when the current public health emergency ends, it is important to understand that you need to meet new coding requirements.
As with all services, medical necessity is crucial for coverage of RPM. It is also required that the provider obtain permission from the patient prior to providing RPM services; this patient consent must be documented in the medical record. The consent can be obtained on the same date as RPM services are provided.

The proposed rule for 2021 does clarify that RPM services can be provided to patients with acute conditions; chronic conditions are not required.

Who can provide RPM
Although the public health emergency waiver allows RPM for new patients, this will not be true once the emergency has ended, so only established patients can be monitored. RPM must be ordered and billed by the physician and/or other qualified healthcare professional (a provider with the ability to bill Evaluation & Management services, such as physician assistant, nurse practitioner, clinical nurse specialist; not ancillary staff).
There is some difference in what type of provider may furnish the service, as the 99091 can only be provided by the physician or other qualified healthcare professional; however, services for codes 99457-99458 can be provided by ancillary clinical staff as well, under the general supervision of the physician. The proposed rule also allows services for codes 99453-99454 to be provided by supervised clinical staff as well. RPM is not considered a diagnostic service, so it cannot be provided by an independent diagnostic testing facility.

One big change, which is at variance from most guidance on time-based codes, is the time for interactive communication. Historically, CMS has been clear that the time-based requirements consist of a combination of interactive communication, monitoring and management of the patient’s care plan, which is consistent with the code descriptors. In the proposed policy clarification, CMS has taken a different approach to the time component and is only considering the “interactive communication time.”
CMS stated that for purposes of CPT codes 99457 and 99458, interactive communication must total at least 20 minutes over the course of the calendar month for 99457; an additional 20 minutes of interactive communication is needed to report 99458. The interactive communication must have a real-time, synchronous, two-way audio interaction that is capable of being enhanced with video or other kinds of data transmission. The documentation throughout the month must support the time spent to achieve the right coding, but also must separately capture how much of the time was interactive communication, based on this requirement.

Remote patient monitoring codes and descriptions, 2021 proposed

CPT CodeDescription
99091Collection and interpretation of physiologic data (e.g., ECG, blood pressure, glucose monitoring), digitally stored and/or transmitted by the patient and/or caregiver to the physician or other healthcare professional qualified by education, training, licensure/ regulation (when applicable), requiring a minimum of 30 minutes of time each 30 days.
99453Remote monitoring of physiologic parameter(s) (e.g., weight, blood pressure, pulse oximetry, respiratory flow rate), initial setup and patient education on use of equipment.
99454Remote monitoring of physiologic parameter(s) (e.g., weight, blood pressure, pulse oximetry, respiratory flow rate), initial; device(s) supply with daily recording(s) or programmed alert(s) transmission, each 30 days.
99457Remote physiologic monitoring treatment management services. Clinical staff/
physician/other qualified healthcare professional time in a calendar month requiring interactive communication with the patient/caregiver during the month; first 20 minutes.
99458Remote physiologic monitoring treatment management services, clinical staff/physician/
other qualified health care professional time in a calendar month requiring interactive communication with the patient/caregiver during the month; each additional 20 minutes.

This CMS’ interpretation would appear to mean that the practitioner and clinical staff must use the RPM, analyze the data, assess it, update the care plan accordingly, and also spend at least 20 minutes talking on the phone or via video with each monitored patient each month. For example, if a doctor spent 50 minutes overall during the month in providing RPM services, but only 17 minutes of that time was actually interactive communication, RPM services could not be reported. If you have been capturing the total time of all services to arrive at your time and codes, this would certainly have a negative impact on how to code, as the time of monitoring and updating the treatment plan would not support the time component of the service. It is anticipated that this change will be one of the most challenged during the comment period.

It also should be noted that under the rule, CPT codes 99453-99454 could not be reported more than once during a 30-day period. Also, monitoring must occur over at least 16 days to be reported. The proposed rule also seems to suggest that 99457-99458 cannot be billed until after the initial 30-day period of monitoring.

All eyes will be on the final rule. Remote patient monitoring is a way for providers to use clinical staff to remotely monitor patients and improve revenue, but complying with these new regulations will not be as easy as it may have appeared during the pandemic.

Achieving Balance Integrity

Jesse FordRevenue Management

In the Age of Consumerism, you need to exhaust all other payment options before the bill goes out

Many years ago, on a flight home from Washington, D.C., I struck up a conversation with a fellow passenger who was heading home with her young son, a boy filled with joy and energy, who was bouncing around his seat like any other child his age. The difference was that he was blind, though you couldn’t tell how or even if this disability was impacting his life.
Nevertheless, the mother slowly revealed the financial burden that caring for her son demanded. It had made her an advocate; she had been in Washington to seek funding for new services for the blind. One of the most revealing stories she shared was about a medical bill she received for more than $100,000 for her son’s care.

Huge bills like that can be accurate, but I also know that such a large balance often reflects a claim error. Financial assistance was not going to help her enough, and she needed to continue to take her child to the hospital for treatment. She had commercial insurance, but her share of the cost was going to bankrupt her family.

The mother spent hours negotiating with her insurer, speaking with financial counselors and the billing office. I imagined how much energy that probably took and was not surprised that nobody she spoke to would or could help her. Amazingly, one day she happened upon the right person, who routed the claim to someone who examined it and contacted the coding department. As it turned out, the services were wrongly coded, so the insurer denied coverage. Documentation supported the use of alternative codes appropriate for the services, so the provider rebilled the claim and was paid by the insurer.

Not everyone is as lucky as my seatmate. This kind of error and its aftermath – savings wiped out and medical debt mounting – is what we at Salud consciously and diligently strive to avoid when we code, bill, and follow up with insurers and patients. Salud has coined the term “balance integrity” to describe the importance of ensuring that patients are billed accurately, but we take it further: We aim to bill patients accurately only up to their financial means and only after we have exhausted every possibility of an insurer paying for the services.

Consumerism demands these changes. People are seeing the cost of employer-sponsored and individual coverage rise, especially out-of-pocket maximums. A recent Urban Institute analysis of census data says at least 3 million Americans have already lost job-based coverage from the pandemic, and a separate analysis from Avalere Health predicts some 12 million will lose coverage by the end of this year.

As cost pressures rise, consumers are looking more closely at medical bills and wondering why healthcare costs so much. This is why regulatory changes aimed at surprise medical bills and price transparency loom on the near horizon.

Balance integrity requires accurate balances. Our definition of an accurate balance is that it matches the insurance explanation of benefits, and the balance does not include anything caused by a billing error. Providers must ensure that claims have been coded accurately, and that each field on a claim form, including modifiers, has been filled in appropriately.

When a provider makes an error, it can expect insurers to deny a portion or the entire claim with a denial that can be complex and easily shifted to a patient to resolve with their insurance. For a large academic medical center, 25% of our accounts have been denied, many with reasons such as “duplicate,” “non-covered,” “coding (error)” or “not medically necessary.” Providers’ payer follow-up staff need to advocate on behalf of patients and ensure that they solve challenging denials instead of transferring the problem to a patient to solve.

Balance integrity means we evaluate and take into account a patient’s ability to pay. For the indigent or people with deductibles and co-pays beyond their means, providers should try to advocate on behalf of the patient with financial assistance, including charity write-offs, discounts, payment plans and perhaps a zero-interest credit card.

If there isn’t someone else who could be billed for services, balance integrity demands we assist patients with finding alternative insurance coverage, such as Medicaid, COBRA or liability insurance.

Balance integrity results in higher payments because most patients do not pay balances that they cannot afford, and insurers tend to pay more than patients. The industry should embrace price transparency rather than trying to sandbag it. If we truly want to be service-oriented, we need to do what’s right for the patient by ensuring that nobody facing a healthcare crisis should also confront the shock of a huge healthcare bill they should not have to think about, much less try to pay.

Succeeding with virtual care: HIT and coding logistics

SaludCoding, Telehealth

A joint presentation from Salud, MedAstute Consulting and Apollo HIT

The operating revenue outlook for most healthcare providers is dire, as patients are only slowly returning to scheduled medical encounters. With the changes to regulations as part of the response to COVID, telehealth services have become a lifeline for many providers.

During the pandemic, hurdles to adopting telehealth have mostly been set aside. The entry costs for providing a simple televisit are low, as long as both parties have Internet and decent Wifi. But this being healthcare, it’s not THAT uncomplicated. There are a host of coding and documentation considerations, and the regulations are far from static.

This session is about the behind the scenes work you need to make telecare a success, now, and we hope long into the future.

Watch the recording | Download the presentation

Revenue cycle faces unprecedented challenges, but old truths point the way to new solutions

Jesse FordCOVID-19, Revenue Management

We’ve done it before.

While we cope with financial and mental stress in an uncertain environment, revenue cycle leaders can draw upon the well of experience they have in adjusting to previous change in our dynamic healthcare industry. We’ve withstood several downturns in the economy. We’ve overcome vast changes in the payer market, reimbursement systems, coding systems and new technology. And we have incorporated groundbreaking new ways to treat patients. We know how to cope with change, and as we reflect on our current state, we should keep focused on the verities that existed before COVID, because they are still here, and in some ways are more profound today.

Patient satisfaction
Our patients may be facing new circumstances, and we need to advocate for them to ensure their experience with revenue cycle is not a source of pain. Generally, I’ve always believed in treating patients with kid gloves, particularly the higher-balance accounts. That truth remains. Anticipate patient pain, help patients find insurance coverage, simplify the process for applying for financial assistance, offer flexible payment arrangements, and make sure that patient balances are accurate and we are not asking patients to solve insurance problems that we are better prepared to handle.

This is a great time to design a model that better marries service with effective collection practices. Our industry has focused on price transparency, as it should, but our model should also aim to simplify how patients navigate revenue complexity, by providing communication and payment options that patients prefer and understand. And, our work today can look for innovative models that boost collections in a patient-friendly way, such as leveraging social psychology, segmentation based upon advance analytics, and/or through a focus on working with patients on the front end.

Employee engagement
Revenue cycle experts are certainly facing new circumstances, as health systems move staff home, ask staff to take on different responsibilities, and sometimes furlough large pools of experienced caregivers. A truth that existed before today’s pandemic still remains; as revenue cycle leaders, we need to ensure our staff are engaged in their work. Engagement is a key to quality, productivity and satisfaction.

Salud helped staff transition to home by establishing virtual “coffee breaks” so that staff take some time to connect. We were lucky to already have a home-based model, and our experienced “at-home” staff shared how they created the best at-home work experience.

From Salud’s inception, we have aimed to design our models to put the right accounts in front of our staff at the right times. We refer to this as meaningful work. Through analytics and robotic process automation, we have continuously reduced repetitive “drone” work, and engaged staff with problems to solve.

Our truth is also founded in treating employees like adults. We give our staff objectives, exceptional training and technology-enabled resources to accomplish goals – and then set them free to get the job done.

Improving cash position
The reality is, nobody was perfect at collecting money before COVID, and we are certainly not perfect today. Reduced volumes caused by the COVID crisis free up some staff time to plug holes. One Salud client reflected that it finally was able to get through special projects such as account cleanups, building edits and working backlogged accounts. It is a great time to catch up, but also to design a model that identifies and addresses holes in the revenue cycle. Some systems are rededicating themselves to denial management, which leads to innovative process improvements throughout the revenue cycle. Others are instituting better ways to identify what they haven’t identified themselves, by auditing zero balance accounts to find gaps in business office processes (e.g., billing mistakes, inappropriate write-offs) and payer underpayments.

Growing with the digital age
Another truth that predates COVID and will endure after it is gone is the need to survive in a digital age. Claims denials and chronic underpayment are age-old problems in revenue cycle, but we can’t just throw endless staff time at these issues. Instead, process automation, analytics and, someday soon, artificial intelligence are means to achieving revenue cycle optimization, which combined with expert staff takes the guesswork out of reimbursement.

These are big challenges, made all the more difficult by COVID. And yet, we’ve done big things before and can do them again.

Evaluation and management changes are coming to outpatient care sites

Jennifer SwindleCoding

The Centers for Medicare & Medicaid Services’ 3-year-old Patients over Paperwork initiative, designed to free doctors and non-physician practitioners to focus more on patient care, has led to the first major revision of evaluation and management (E&M) office visit codes in more than a quarter century. The changes are limited to medical office/outpatient services, but they are significant and will require effort to prepare.

In 2018, the American Medical Association assembled a joint work group representing its Current Procedural Terminology (CPT®) Editorial Panel and the AMA/Specialty Society RVS Update Committee. The group worked with CMS and convened a coalition of 170 state and specialty medical societies to simplify the requirements and make them clinically relevant. One of the main goals is to reduce the administrative burden by getting rid of redundant and/or unnecessary documentation in the medical record that does not have a meaningful impact on actual patient care.

Obviously, much has changed since the 1995 and 1997 versions of E&M. Those could not have anticipated the impact that electronic health records would have on provider documentation. Healthcare today is more focused on patient needs and utilizes a team model not seen as much that many years ago.

Medical necessity still critical
One thing that has not changed and is not impacted by the changing guidelines is that medical necessity should be the overarching criterion for determining the level of service.

The big changes to E&M are:

  • The level of service will be determined either by medical decision-making or by time
  • Elimination of CPT code 99201 for new patient visits. There will be no variation from new to established patient for documentation content, medical necessity or medical decision-making.
  • History and examination documentation will not be factored into determining the level of service

Significant changes were made in how to determine the medical decision-making component to correlate it with medical necessity. Extensive edits were made to the elements for code selection, including removing ambiguous terms such as “mild” and clarifying “acute or chronic illness with systemic symptoms.”

Recalculating total time
The other methodology to capture the correct level of service is based on the total time, which includes both face-to-face time and non-face-to-face time that is specific to the patient’s total care for a particular day of service, but no longer needs to have a counseling component. It is the time personally spent assessing and managing the patient on the date of the encounter and includes:

  • Preparing to see the patient (e.g., review of tests)
  • Obtaining and/or reviewing separately obtained history
  • Performing a medically appropriate examination and/or evaluation
  • Counseling and educating the patient/family/caregiver
  • Ordering medications, tests and procedures
  • Referring and communicating with other healthcare professionals (when not separately reported)
  • Documenting clinical information in the electronic or other health record
  • Independently interpreting results (not separately reported) and communicating results to the patient/family/caregiver
  • Care coordination (not separately reported)

While this is a CMS change only, we at Salud will be monitoring the commercial payers closely to see if they adopt the new methodology, and you should too. Also, you must keep in mind that it impacts only a few of the E&M services, and there will still be a need to follow the current existing guidelines for other types of E&M services, so there will potentially be dual rules dependent upon payer and setting.

Different providers will be impacted differently. Those who provide most services in an inpatient setting, such as hospitalists and intensivists, will see no change, while providers that function nearly exclusively in an outpatient or office setting will have significant change.

Understanding the changes, educating on the changes, and monitoring successful implementation will be necessary. Salud will be offering presentations on the E&M changes to industry groups and will certainly work with coding clients. The AMA offers tools and resources to help practices transition to the new reporting guidelines that take effect Jan. 1, 2021. That includes a checklist to help guide a practice through the E&M changes.

January 2021 is not far off, so the time to start training is now.

Want some good news? Start with recovered cash today, and much more to come through automated processes and understanding of payer behavior

Frank MassiRevenue Management, Zero balance

Despite the return of elective procedures at most hospitals and outpatient centers, not nearly enough patients have been showing up, perhaps fearful of what they perceive as high-risk environments. As a result, healthcare’s COVID-19-fed economic downturn has reached epidemic proportions, leaving organizations of all types and sizes scrambling to identify any new or accelerated sources of revenue.

Instead of mass layoffs or furloughs, some forward-looking health systems are seeking cash-yielding solutions that are non-disruptive to current operations. They are looking beyond COVID-19’s impact for lasting positive effects on cash and efficiency. Here are four tactical and strategic priorities that should be pursued simultaneously right now:

  • Take advantage of the opening presented by the dramatic and sudden reductions in volumes and shifts in account mix due to the COVID-19 crisis to design and implement a new business office operating model that effectively “future-proofs” cash
  • Use reviews of past and prospective payments analysis to discover and recover significant new cash
  • Take the low-risk approach of choosing projects completely unaffected by the crisis so staff can stay focused on their own related urgencies
  • Short-list only those vendor partners who will perform the work completely at-risk and with no upfront fees

These are not mutually exclusive objectives. And now is the perfect time to address all four in a single project with a single, at-risk vendor partner.

When zero means quick cash
At a time when many institutions are in the midst of a severe revenue downturn, seeing a cash recovery of $110,000 in the first month, and more than $727,000 in just over three months, as a 450-bed hospital client of ours did recently, or $4.8 million in four months, as a large Midwest hospital received, is much needed good news.

This process, known as zero-balance reviews, involves both a retrospective and prospectively modeled look at paid and/or written-off claims. These reviews of closed accounts use a process of reimbursement analysis followed by the grouping and analyzing of like claims to find out why some are underpaid and where there may be significant trends that convert to large sums of recovered cash immediately. As importantly, it identifies the underlying issue(s) and corrective actions to take. As a result, tens of millions of dollars in future revenues have been protected from leaking away into a river of red ink.

Zero balance reviews will pay even larger dividends when normal volumes return. Much revenue leakage is caused by providers failing to code and bill according to payer rules; analysis of payment to charges catches accounts paid properly per payer contracts but underpaid as they were coded incorrectly.

Automating denial management
If you are a health system with a robust denial management system, many of your claims look right. If you are a health system with a robust reimbursement analysis program, many of your claims will be paid according to how they were billed. Working with a partner with an effective coding team and an AR team that understands the payer market across the spectrum will show you why and how those claims were underpaid. Working with a partner that can also detect errors across the full spectrum of your revenue cycle operation will show you why and how to lift performance across the board front-to-back.

Using advanced automation in the review process means that thousands of claims can be reviewed instead of a few dozen per day through manual processes, which removes the only viable objection to zero balance reviews – that they involve many small balances not seen as worth a lookback by staff straining to handle new claims.

Salud isn’t the only vendor out there that does this work, but we have turned it into a tech-enabled specialty. Our process includes:

  • Contract modeling, automated claims status reports, and historical 835 electronic payment explanation data to find zero balance accounts with recovery opportunities
  • SaludSynapse, our business intelligence platform, provides rules-driven workflow that streamlines the appeals process and maximizes results
  • Sophisticated analytical reimbursement models are built specifically for all the national payers and tuned smartly to each state’s payer rules and tendencies

Audits find root causes of underpayment
Salud expands the net by finding underpayments as a result of many other breaks in the process like coding, billing, and as a result of analysis of percent of charges ratios. Other solutions also do not have our technology-enabled workflow, intricate knowledge of national and local payer practices, or our data mining and analysis tools.

The fact that zero balance reviews are non-disruptive even amid the pandemic is a huge bonus. They are unaffected by the huge shift in AR to non-elective procedures due to massive procedure cancellations as well as labor shifts and reductions in business office staff or coding.

Regular audits of the business office through this program provides well-articulated root causes of underpayment. Processes and systems are calibrated to address the inevitable challenges brought by the interdependencies and continually evolving roles of business office people, process and technology, thus protecting future revenue streams.

The time to deliver cash for current operations is now, with an even bigger payoff to come.

With paying for value ascendant, diagnostic coding accuracy grows more crucial

Jennifer SwindleCoding

Value-based payment has been steadily growing in healthcare in the past few years, thanks to programs such as the Hospital Inpatient Value-based Payment Program and the Merit-based Incentive Payment System (MIPS, part of the Quality Payment Program for physicians). More recently, this movement has gained new agency due to risk-based programs in the commercial payer market. For providers, these initiatives, while promoting innovation and safety in clinical care, also put diagnosis coding under the microscope.

Coding at the highest level of accuracy and specificity has always been instrumental in supporting claims of medical necessity and painting a picture of the clinical condition of the patient. Too often, however, providers have bumped along with incomplete diagnosis coding, leaving a bare sketch of the patient’s condition, not truly a finished picture. With value-based payment apparently here to stay – and perhaps to become a much bigger amount of reimbursement at risk – providers that want to stay in business must be exacting in diagnostic coding accuracy.

Outpatient providers have learned this lesson faster, because the regulations are clearer in regard to capturing definitive diagnoses. They already know that documentation with phrases such as “consistent with,” “compatible to,” “possibly,” etc., likely will be kicked back to them with a denied claim.

Providers face many areas of risk in documentation; here are just a few:

  • Every encounter, regardless of setting, needs to have a clearly stated or easily inferred chief complaint. Even on an inpatient facility record, where a provider or possibly multiple providers see the same patient daily, each individual provider who sees that patient must document a chief complaint every day to show that what he or she was doing was medically necessary.
  • When you open a patient’s electronic health record, some documentation is auto filled, so you need to go in and edit those fields for the current visit.
  • Voice recognition/natural language processing systems may misinterpret something, causing documentation to be incorrect. Careful proofreading and editing is required by the provider.Problem lists are often not well maintained and providers hesitate to remove things they did not add; however, if the problem list pulls into a current note and is left unedited and the note is authenticated, that provider is indicating that problem list is true and accurate on that date.

Patients often present, particularly in the office or emergency department setting, with one complaint, but at the end of the visit, there are multiple conditions listed. These may be problems the patient has had historically; however, if there is no evidence they were addressed or impacted the care, a list does not support coding those conditions.

Providers are the only individuals who can diagnose a patient, so elements in the chart that are clinically abnormal cannot be coded until the provider makes the diagnosis. Abnormally low pulse oximetry, abnormal lab values and abnormal echocardiogram tracings may be evident to the provider of a condition, but until that condition is documented, this is just additional data in the chart. Coders or clinical documentation improvement specialists may use these reports to formulate queries for clarification, but they do not support coding.

Examples of some common scenarios:

Patient presents with uncontrolled diabetes. The coder can only code E11.9, diabetes, not otherwise specified. There is no code for uncontrolled diabetes. There are separate and distinct codes for diabetes with hyperglycemia (E11.65) or diabetes with hypoglycemia (E11.64X, last digit depending on with or without coma), but the condition must be captured by the provider. The coder cannot look at the lab results and code anything more than unspecified until it is clarified by the provider. It matters: Both E11.65 and E11.64X are in a higher weighted risk adjustment category, which impacts the patient’s risk adjustment factor, which will impact an individual provider MIPS score, as well as potentially impact payment.

Patient has urosepsis. The coder can only code N39.0 for unspecified urinary tract infection. Is that what is meant, or does the patient have septicemia or sepsis? Without clarification, serious conditions may not be able to be coded, not only impacting the risk adjustment factor, but also failing to reflect the true acuity of the patient being treated.

GI bleed and anemia. The coder is able to code K92.2 for gastrointestinal hemorrhage and D64.9 for unspecified anemia. There is a more specific code, D50.0, for iron deficiency anemia secondary to blood loss; however, this cannot be chosen unless the provider captures the cause and effect relationship of the two conditions, i.e., anemia secondary to GI bleed.

Diagnosis coding is crucial first and foremost to accurately reflect the severity of the patients being treated and served. However, accurate and complete diagnosis coding also can significantly impact the revenue cycle and financial health of the organization. As value-based purchasing grows, so will the importance of coding accuracy.

While AI in healthcare matures, finding the right data is a starting point

Jesse FordRevenue Management

In our fall newsletter, I asked, “Has AI really arrived in healthcare revenue cycle?” I shared that as a company born in a digital age, Salud recognizes the need to collect, store, and analyze clinical and financial data that can help predict outcomes and improve processes that affect cash.

However, I questioned then and continue to question whether the industry does revenue cycle artificial intelligence well – yet. The pathway to meaningful AI and machine learning requires smart design, lots of data and continuous focus, and I am not sure how many are hitting that trifecta. With all of the pressure on revenue cycle today, we need to be taking steps now to ensure we are ready when the tools and processes of AI that are common in other industries make their way into everyday use.

You might start by completing this question: “Wouldn’t it be great if we could use artificial intelligence to …?” How many revenue cycle professionals would answer almost reflectively, “… to get the patient’s bill paid.” Unfortunately, that is not possible today, but the promise of AI does apply to individual steps in the end-to-end cycle that over time will come together so payment starts to “figure itself out” – automatically, accurately and in a timely manner.

AI has near-term potential throughout the revenue cycle, including areas such as patient access, health information management and utilization review. It has applications in value-based reimbursement systems, consumer-driven care models and population health. Efficient revenue management is the common thread through all of this. Salud’s commitment to assist in the health of the communities that our clients call home, as well as our calling and mission align well with our clients’.

While you may have a robust and aggressive plan for applying AI throughout your organization, Salud’s vision is to be the national model for the delivery of revenue cycle services, so we focus on improving efficiency, accuracy and the patient experience. We seek the information we need from electronic health information and from outside the healthcare space and then apply analytics and trending data to bring meaning and quality execution to this vision.

Rich data for analytics in electronic transactions
Consider dissecting and expanding on the data contained in the 837 transaction set, established to meet HIPAA requirements for the electronic submission of healthcare claim information that broadly falls into four categories:

  • Patient demographics
  • Patient conditions/reasons for treatment
  • Services provided
  • Prices for services

Depending on the problem you are trying to solve, the 837 is rich with data for healthcare analytics (and AI). This data also reside in your EMR, but we find most providers struggle to extract and store data as concisely as it can be found in electronic data interchange 837 files.

The 835 transaction set, aka the Health Care Claim Payment and Remittance Advice, is the electronic transmission of healthcare payment/benefit information. It contains some of your data, but adds payer information that may inform advanced analytics; most importantly, payments and denials. Once again, you may be storing some 835 data in your EMR system.

If you have trouble aggregating demographic, service, and payer data and extracting it from your systems, Salud recommends you begin now to store these electronic files, as they are rich with data you likely need for your future work with AI.

Data not captured in your information systems
Salud looks within and outside of the industry to find information that our providers don’t have, but that should be part of our AI framework. We’ve been impressed with providers partnering to share data in health information exchanges.

Of course, the industry still lags way behind banking, social media, pharmaceutical companies, and even pizza chains, all of which already collect and understand our habits, struggles and capability/propensity to pay. Earlier this month it was reported by Atlantic magazine that one political party has “3,000 data points on almost every voter in America, and they use those data points to determine how exactly to pitch their message.” Salud sees parallels in utilizing data points in determining how exactly to “pitch” care and the account resolution process most seamlessly.

AI requires a dedication to collecting and archiving meaningful data. Those who would like to move the needle on the delivery of revenue cycle services need to advance current capabilities in this area. From this rich(er) base of data, what can then be mined and designed are the most efficient workflows and exception processing systems for your operation.

Salud’s digital infrastructure already helps simplify processes, drives results and enhances patient experience. With the proper balance of data and human ingenuity, we look forward to building on our platforms so that sophisticated AI will soon connect data, predict outcomes and prescribe real world, powerful solutions. Until such advanced capabilities become available, Salud is focused on pre-AI, akin to machine learning analytics, while simultaneously acquiring and storing the most meaningful data from which to mine optimal workflow and liquidity.

We are excited to partner with providers looking for the right revenue cycle model for the digital age where many or all of these AI and machine learning concepts may already be in the discussion or planning stage.