Readers Write: Taking Clinical Natural Language Processing Mainstream for Effective Care Management

Taking Clinical Natural Language Processing Mainstream for Effective Care Management
By Kevin Agatstein

Kevin Agatstein is CEO of Kaid Health of Boston.

Across healthcare, clinical natural language processing continues to play an ever more influential role. Kreimeyer et al.’s “Natural language processing systems for capturing and standardizing unstructured clinical information” identified over 70 different CNLP systems in the literature, spanning multiple clinical domains. Unfortunately, few of these directly address the applicability of CNLP to care management. This lack of CNLP supporting care managers will and should change. Making this reality will require adapting the technology to the real-world needs of care management programs and the front-line clinicians who staff them. 

To fuel effective care management, actionable data is required across the entire workflow. Examples of actionable data include information that: 

• Identifies which patients require help.
• Stratifies patients for intervention.
• Summarizes the patient for the care manager.
• Determines the specific actions the patient needs.
• Uncovers the barriers to effective care.
• Measures intervention outcomes.

Claims data, lab data, health risk assessments, and motivational interviewing all meaningfully contribute to the above. While all of these are necessary, alas, they are not sufficient. For the care manager to meaningfully coordinate patient care, to accomplish the six steps listed above, they must have access to actual clinical data. They need the medical record. More precisely, they needs the nuggets of actionable insights buried in the massive EHR data set. Finally, they need it to be quickly digestible. Thus, CNLP can not only help, it is all but required.

This actionable data is almost all in the EHR; however, it can be hard to find. A patient’s medical record is often hundreds of pages of text, alongside hundreds of discrete data points (labs, medications, allergies, etc.) Within this morass of usually loosely organized data is the patient’s health history. While claims and labs can give some sense of the patient’s clinical experience, the chart has the diagnosed but not coded conditions, the written but not filled prescriptions, and more. It also has a plethora of exam findings, laboratory reports, radiologic data, and pathology findings that never get put into “structured” EHR fields.

Kharrazi et al., in “The Value of Unstructured Electronic Health Record Data in Geriatric Syndrome Case Identification,” found that the EHR text resulted in finding 1.5 times more patients with dementia than just reviewing the structured EHR data. That same ratio was 1.7 with decubitus ulcers, 2.9 for weight loss, and 3.2 for a history of falling.

Beyond traditional clinical data, the chart often contains insights into the patient’s family health history. It also has data on psychosocial barriers to care, limitations on activities of daily living, and other elements impacting the patient’s care journey. Just as crucial for care managers, the chart typically has data on the patient’s social determinants of health. While SDOH are almost never coded in claims, (and yes, there are ICD-10 SDOH codes), they are noted in charts. AI-powered healthcare data analysis and provider engagement platforms have found hundreds of SDOH in primary care, specialists, ED, and behavioral health charts. Kharrazi found similar results. For example, they found that it is 456 times more likely to find a patient with a “lack of social support” in the free text of the medical note than in the structured data.

For a care manager to do their job well, this data cannot be ignored.

More than just summarizing the patient’s health, the medical record can help translate the EHR text into a structured, actionable, trackable ambulatory care plan by summarizing the physician’s treatment plan noted for each encounter. Specifically, NLP can create a patient to-do list such as follow-up visits, getting testing or labs, addressing unhealthy behaviors, and more. These identified tasks can become the basis of a care management care plan or added to existing plans. As new data enters the chart, either as structured information or new medical notes, the to-do list can be updated. Tasks can be marked as completed, new tasks added, existing tasks amended, and more.

It’s important to remember that NLP algorithms do not digest a medical note the way a human does. Rather, they predict how a trained human would interpret the presented text. This is much more than finding key words. CNLP solutions also need to account for:

• Negation (“does not have cancer”).
• Family history (“the patient’s mother had an MI before age 55”).
• Uncertainty, (e.g., “initial lab findings mean early-stage chronic kidney disease possible, but additional testing is needed”).
• And more.

Making such determinations isn’t perfect, but making useful interpretations of clinical text has been proven possible. Moreover, CNLP does not fatigue as humans do. For example, Suh, et. al. found in “Identification of Preanesthetic History Elements by a Natural Language Processing Engine” that CNLP frequently identified salient clinical facts that a physician reviewer missed. 

Now, new data standards, notably FHIR, and regulatory mandates to share data combine to markedly simplify a CNLP deployment process. This, plus cloud and other emerging data exchange standards, mean CNLP go-lives can be measured in days, not months. By working with partners with rigid technological and workflow controls, extensive security training, and a culture of data security, the data can be processed safely as well.

For a real-world deployment, a care management CNLP solution should be intuitive to clinicians. It should be focused on the needs of care managers to anticipate the workflow. Care managers today deal with several different medical record and care management documentation systems. Effectively managing these variations, and the vagaries of existing workflows, comes only with experience. Most importantly, CNLP needs to add value for the user practically out of the box. They can, and they will.

Readers Write: Diagnostically Connected Data – The Key to EHR Clinical Usability

Diagnostically Connected Data: The Key to EHR Clinical Usability
By Dave Lareau

Dave Lareau is CEO of Medicomp Systems of Chantilly, VA.

Clinicians are among the most highly trained knowledge workers in any industry, yet the systems they use to care for patients often actually hinder their ability to deliver care. We hear anecdotes from patients about clinicians spending inordinate amounts of time trying to find information in their EHRs – only to often give up rather than search through other sections of the chart to find a lab result, view past encounter notes, or try to correlate medications with problems or the course of a condition.

EHRs require users to spend too much time searching for clinically relevant information for the patient they are treating and, once that information is located, to go through a series of disconnected processes to complete their work.

This situation will only get worse once the floodgates of healthcare data interoperability are opened. Then, it will be even more challenging for clinical users to find what they need.

Consider the bright side of this data-driven conundrum: The effects of the 21^st Century Cures Act and TEFCA will make it easier for HIT systems to send and receive information. Plus, emerging terminology standards and the use of common codes such as ICD-10, SNOMED, LOINC, RxNorm, CPT, DSM5, CTCAE, UNII, CVX, and others will provide a basis for what is often called “semantic interoperability.” And today, the performance of natural language processing is getting more consistent and reliable, providing a means to convert free-text notes that use those same terminologies and codes.

So, does that mean that more coded data is a good thing?

Not necessarily – that is, unless clinicians can readily locate the information they need to assess, evaluate, treat, and manage a given patient and their clinical problems. With the widespread adoption of risk-based reimbursement through Medicare Advantage and similar programs sharpening the focus on chronic condition management, it will be increasingly crucial for clinicians to see a diagnostically focused view for each patient along with their medical problems. They need instant access to this view, without searching through disparate sections of the EHR.

Semantic interoperability facilitated by standard terminologies and code sets is a great start – and is necessary for sharing clinical information between systems. It will also drive better analytics and population health insights. But it will not make it easier for clinicians to find the data they need for the patient at the point of care (whether that patient is in-office or on a screen.)

Most existing EHRs, and the terminologies and codes for semantic interoperability, are structured in distinct “domains.” In an EHR, this typically shows up as separate sections or tabs – problem list, medication list, laboratory orders and results, procedures, encounter notes, discharge summaries, etc. Problems, meanwhile, have ICD-10 and SNOMED codes, labs have CPT and LOINC codes, medications have RxNorm or NDC codes, and other domains use other code sets. These codes were designed for their specific domain. They were not designed to work together for the clinical user.

The key to usability is to link these to the problem list, so that the user can click on a problem and immediately view the related medications, labs, procedures, therapies, co-morbidities, and findings from encounter notes that all are related to the problem. This diagnostically filtered presentation could be viewed longitudinally and supported by millions of mappings from standard terminologies and code sets.

Such a unique diagnostic relevancy engine would provide both the semantic – and diagnostic – interoperability that enables clinicians to not only see what they need at the point of care, but also to harness the flood of interoperability-driven data that will soon complicate their work.

Readers Write: Does Cryptocurrency Have a Future in Healthcare?

Does Cryptocurrency Have a Future in Healthcare?
By Curtis Bauer

Curtis Bauer is chief product officer of Sphere of Nashville, TN.

Cryptocurrency seems to have found itself used in some capacity in just about every industry. Well, every industry except healthcare.

Healthcare has been hesitant to adopt cryptocurrency, such as the well-known bitcoin, primarily because of cryptocurrency’s various nuances that are not inherent with more traditional forms of electronic payments. Those nuances include volatility, lack of consumer demand, increasing government regulation, and most importantly, challenges with reconciliation.

To understand cryptocurrency and its future in healthcare, you must first understand the underlying technology. Cryptocurrency is built on what is known as blockchain technology. Blockchain can be difficult to understand, in part because blockchain is not a plug-and-play technology, a silver bullet standalone technology solution, or an app that can be easily installed.

Blockchain is a decentralized, distributed, peer-to-peer network. As opposed to a system in which applications are controlled by one entity, a blockchain network enables control to be shared across a group of decentralized computers and networks.

Blockchain is built on distributed ledger technology, which creates a record of transactions over time while allowing for tracking and analysis, documenting the transfer of ownership, and ultimately serving as a means for proving ownership. The advantages of blockchain include the elimination of a need for third-party intermediaries to verify transactions and a high level of security.

As it relates to healthcare, although there are significant challenges that need to be overcome before cryptocurrency will ever become mainstream, there is a strong likelihood that the underlying blockchain technology will become a staple in the world of payments and other business segments that have a need for authenticating transactions and minimizing the risk for fraud.

Blockchain is changing the world in several ways, as there are 300 million estimated global cryptocurrency users, according to a report from the US Department of Health and Human Services’ Office of Information Security. Consider bitcoin, which is itself just one of thousands of cryptocurrencies in existence. Approximately 17% of the US adult population owns bitcoin. It has a global market cap of $775 billion. It is accepted by more than 15,000 businesses for payment globally.  Crypto-economics, which is a field of economics based on blockchain technologies, is now a recognized academic field. Non-fungible tokens, which are also built on blockchain, are selling for millions of dollars.

Yet if blockchain and cryptocurrency are so innovative, exciting, and cutting-edge, then why have they been so slow to penetrate the healthcare market? There are several reasons, and they begin with the extreme volatility of cryptocurrency.

The value of cryptocurrency fluctuates wildly in short periods of time, sometimes by the minute. In general, cryptocurrency lacks the stability of traditional government-issued currencies, and that is unlikely to change any time soon.

Similarly, given cryptocurrency’s extreme volatility, exchange rates with other types of currency are constantly in flux. For example, between the time a transaction is agreed upon and the buyer obtains the product, the cryptocurrency-to-dollar exchange rate may have substantially changed.

The next problem is regulation. The federal government views cryptocurrency not as legal tender, but more like a piece of property or even gold from a tax perspective. Every time cryptocurrency is bought or sold, it must be reported to the Internal Revenue Service, so attempting to use cryptocurrency similar to cash or credit cards becomes a tax and accounting nightmare. Healthcare providers who begin to accept cryptocurrency would be subject to the same accounting and income tax implications when they move to convert or exchange the cryptocurrency back into fiat money or government-issued money that is not backed by a physical commodity, such as gold or silver.

Finally, there is the Catch-22 situation of consumer and merchant demand when it comes to cryptocurrency. Consumers are reluctant to embrace it because merchants don’t accept it, and merchants are hesitant to devote time to learning how to accept it because so few consumers use it.

The credit card is likely to remain king well into the future for healthcare transactions, making cryptocurrency unlikely to make much of an impact on healthcare any time soon, and possibly ever. But the blockchain technology that undergirds cryptocurrency is another story. Due to the premium that the technology places on security and transparency, there are two notable use cases for blockchain in healthcare.

• Patient record-sharing. The healthcare industry has traditionally faced substantial barriers in ensuring patient access to all their health records across all service providers in order to have a complete view of medical histories, while ensuring their records are secure. However, blockchain-based medical record systems can be linked into existing medical record software and act as an overarching, single view of a patient’s record without placing patient data on the blockchain. This approach provides patients with a comprehensive, single source for accurate medical records.
• Supply chain transparency. Blockchain is ideal for enhancing the transparency of the healthcare supply chain, particularly for pharmaceuticals. To combat prescription counterfeiting, the industry must be able to track each package’s end-to-end movement from the point of origin, including manufacturers, wholesale, and transportation. Blockchain enables stakeholders throughout the prescription drug supply chain to verify the authenticity of medicines, expiry dates, and other important information.

For healthcare transactions, the credit card is likely to remain king for some time. In that regard, one concrete step providers can take now is to steal a page from retail and focus on minimizing shopping cart abandonment. In other words, providers must ensure a convenient and easy buying experience that enables patients to quickly submit payment. To this end, providers should store payment information electronically for patients, so payment is fast and seamless when they log into patient portals and practice websites.

Though cryptocurrency will likely continue to grow in popularity across many sectors, it’s unlikely that healthcare will embrace it as a mainstream payment option any time soon.

Readers Write: The Retail Revolution is Changing Modern Medical Care and Healthcare Organizations Need to Act Now

The Retail Revolution is Changing Modern Medical Care and Healthcare Organizations Need to Act Now
By Shelley Davis, RN

Shelley Davis, RN, MSN is VP of clinical strategy at Lightbeam Health Solutions of Irving, TX.

As patients and healthcare providers continue to navigate a post-pandemic world, we have begun to see an overlying trend — especially among the younger generation — that favors convenience and transparency in the way healthcare services are obtained. Retail health is defining a generation of patients who are taking healthcare into their own hands and steering away from the relationship-based patient-PCP (primary care physician) system that older generations have followed.

This can come with some benefits, as more convenient healthcare makes treatment accessible for a wider patient population. However, this new healthcare trend also has potential downsides.

To grow and change with the world around us, health systems must be able to answer two questions. Why are these changes are taking place? How can this new mindset be leveraged to make healthcare more accessible and forge a positive, meaningful impact on many lives?

Consumers Can Shop for Anything They Need, Including Healthcare Providers

The retail health phenomenon comes at a time when digital fluency is high. Most Millennial- and Generation Z-aged patients prefer to choose provider offices that offer a better patient-centered experience or with the highest reviews, much like shopping for a new product or home appliance.

In the past, one might have found it odd to receive an eye exam or mammogram at Walmart or to check into a walk-in clinic instead of contacting a PCP when you become sick. Nowadays, a person’s first thought when it comes to their healthcare options is, typically, convenience. This can be due to any number of reasons. Patients may prefer:

• To be seen at a moment’s notice.
• To come in late or on weekends.
• To have financial transparency or listed prices.
• To see a provider without having insurance.
• To go to the clinic or office closest or within walking distance to them.
• To multi-task, such as grocery shopping immediately after receiving a check-up or vaccine.

Many of these scenarios can be tied back to the health inequities that impact a patient’s ability to acquire the medical care they need. It makes sense that patients have to make decisions based on whether they will have finances, transportation, or even shelter. However, while the convenience of retail health does offer benefits, its drawbacks cannot be ignored.

Benefits and Downsides to the Retail Health Model

When taking it at face value, the trend toward retail health might seem appealing. After all, having this level of convenience allows providers to see patients at intervals flexible with many schedules. More benefits include:

• Retail health pushes organizations to be more transparent with costs to compete with these convenience-based clinics.
• Retail health overall is more patient-centric. Moving toward a patient-centric approach rather than provider-centric overall prioritizes the needs of patients.
• Through retail health, many patients can receive basic care who otherwise would not receive medical attention at all, even though that care may not be the highest quality.

But with these positives come some clear drawbacks. When patients are given this degree of autonomy over their own health journey, it puts an enormous responsibility on their shoulders. Patients who adhere to the behaviors of retail health must act as their own medical historian, care manager, and health expert.

From the patient side, these concerns are rooted in an extreme lack of consistency and continuation of care, stemming from little to no engagement or follow-up after an appointment, as well as disjointed health record tracking. When patients go to multiple places for care that do not communicate with each other, an information silo is created, resulting in reduced efficiency, lower quality services, and potential treatment duplication.

Additionally, the use of medications is significantly higher in patients who use retail health. If a patient does not see a physician or care team consistently, many things can be missed or misdiagnosed. Preventive screening recommendations take a back seat to addressing acute needs and new symptomatology. It also puts a provider at a disadvantage to not have all the information they need, such as family history, past illnesses, symptoms, allergies, and drug interferences. This, in turn, increases the consumers risk of medication compatibility issues, treatment gaps, and single symptom management.

How Can Healthcare Organizations Bridge the Gap Between Convenience and Quality?

Retail health is setting some great precedents that can be harnessed to elevate the more traditional healthcare model to one that is more inclusive, accessible, convenient, and transparent. Opening healthcare information while respecting HIPAA guidelines and privacy could solve many of the issues that are associated with data silos while giving providers more access to important patient information and taking the onus off the patient to act as their sole care manager.

Telehealth has the building blocks to be a great alternative for easier access to care while maintaining consistency and quality. Its capabilities include:

• Remote patient-provider visits that reach wider audiences and encourage patient engagement.
• Online or virtual classes to encourage medical literacy for chronic conditions that patients may not know how to best manage on their own, such as diabetes and hypertension.
• Improved coordination of care between multiple providers.
• Encouraged patient communities that benefit from cohort-learning or developing interpersonal relationships with others in their group

Going beyond the digital environment, larger healthcare organizations can also take actions to forge partnerships with after-hour facilities or clinics within their communities to bring the high-quality care they provide to those who rely on convenience.

Along with telehealth, other solutions that can be leveraged to match the convenience and transparency of retail health are:

• Deviceless or device-based remote patient monitoring.
• After-hours hospital clinics to capture patients who need care outside of the traditional 8 a.m. to 6 p.m. window.

The new mindset surrounding healthcare and how medical services are obtained is not going anywhere anytime soon. Larger health organizations should listen to the needs of their communities and extend their capabilities to match those needs as best they can. Ultimately, the key is to meet patients where they are.

Readers Write: Digital Care – The Opportunity and Threat for Metropolitan, Community, and Rural Hospitals

Digital Care – The Opportunity and Threat for Metropolitan, Community, and Rural Hospitals
By Cody Strate

Cody Strate is managing partner of Upward Spiral Group of Boulder, CO.

In 2002, I began my career on the vendor side, helping hospitals move away from NCR forms and embosser cards towards centralized e-forms that could be printed on demand, which was some serious eyebrow-raising stuff back in the day. For the next 18 years, I had the pleasure of working with some wonderful people to institute digital solutions to vexing paper-based processes at over 1,000 hospitals spanning more than a dozen countries.

I stepped outside the acute care space in 2019, gaining exposure into how leaders in other industries fundamentally think about the market they serve, the importance of value, proactive versus reactive mindsets, and intent towards consumer experience.

After dancing with technology solutions and problem solving in other industries, I can clearly see that there are some threats not too far afield for hospitals that the all-too-pervasive status quo thinking approach to operation, mindset, and leadership is ill suited to handle. I wanted to write this article to call attention to a few things in hope that it opens a few eyes and facilitates some fresh thinking.

Specifically, I’m going to focus this piece around one single theme, which is the opportunity and threat brought about by the ability to extend care across great distances thanks to advancements in technology, a large and reliable communication network infrastructure, and the prevalent adoption of smartphones.

Caveat alert: given the massive institution that is the hospital and health system ecosystem, there are exceptions to every situation and rule. In other words, this is a generalist view derived from the aggregate of my experience of thousands of interactions with healthcare leaders.

The Stakes: Revenue

Just so we’re clear upfront, the cold hard calculus of the following is that pretty much everything comes down to revenue opportunity versus revenue threat. Revenue is the lifeblood of any company in any industry, and hospitals are not immune to this fact. I could elaborate on this, but I don’t think readers need any Finance 101 lessons from me, so let’s just leave it at: (a) lots of revenue = good, versus (b) little revenue = bad.

The Digital Attack on Proximity-Convenient Care

This situation cuts a couple of different ways that we’ll get into, but before that, let’s get straight on what’s happening. It’s a basic principle and rather self-evident that as technology progresses, it consistently renders “impossible” into “possible.” Case in point — the vast geographic distances that kept people isolated from each other, education, services, and so on, are now being bridged through technology.

Proximity Based Care: The Way It’s Always Been

Community hospitals generally exist in an orbit around a metropolitan center, where total beds decrease as distance from the metro area increases. This geographic distance has set the stage for the conventional model we see today, where care is largely accessed and delivered based upon these geographic constraints. In other words, if you live in a rural area, your choice of care is largely dictated by geographic proximity to care. This was my situation as I grew up in rural northeast Texas, where driving into Dallas for big-city healthcare was out of the question. Simply put, geographic proximity to care correlates to convenience of care, which up to this point has served as the primary basis for choice of care.

Potential Winners: Metropolitan Hospitals

Thanks to the combination of (a) 85% of the US population has a smartphone in hand, 84% in suburban areas versus 80% in rural areas; and (b) the emergence of digital capabilities to offer care through these devices, metropolitan hospitals can extend their reach out into suburban and rural areas. If I’m a metropolitan hospital, I would be creating targeted ads regarding specific services to even more specific personas and deploying them through the Facebook ad network, Google display ads, YouTube, TikTok, and the like.

The siren’s song of getting big-city care in palm of your hand can be tempting to people who traditionally are separated from the big-name healthcare due to physical distance. Marketing access to big-brand name healthcare that’s convenient and digitally accessible to these populations can be a lucrative practice for metropolitan hospital systems looking to add more revenue and/or recuperate revenue lost to specialty care service organizations.

Potential Losers: Community and Rural Hospitals

Whereas metropolitan hospitals have the potential to go on the offensive to bring in more revenue, suburban and rural hospitals are a greater risk of having the patients within their community, along with all accompanying revenue, effectively poached. Convenient access to quality care through one’s smartphone is here, and it will only continue to become more mainstream. This places leadership at community and rural hospitals in a precarious situation. The question is how these smaller facilities will strategically position themselves going forward.

The Mindset Problem: BWADITW Thinking versus Proactive Thinking

After stepping away from the acute care industry for a few years and seeing how other industries operate, there’s one thing that’s clear. Generally speaking, the mindset of hospital leadership is largely one set on BWADITW (“because we’ve always done it this way”) versus opportunity and/or threat-based agility found in many other industries.

This should not be a surprise given that most hospitals have the two things required for BWADITW thinking to flourish: (a) size, since these are very large organizations; and (b) time, since many hospitals are long established serving many generations of their community. However, BWADITW thinking stands as a tremendous threat to community and rural hospitals as it offers an alluring false appeal of safety. Building a fixed strategy based upon what’s worked in the past is folly given technology’s acute ability to alter the landscape of the future. If you want to apply lessons from history, consider a more Darwinian lesson of “adapt or die.”

A more vile and derivative threat born from BWADITW is thinking your patient in your area owes your community or rural hospital unwavering fealty. This is complacent leadership at its worst, thinking that your patients owe you something rather than you owing your patients something. Your organization may have been the only game in town for decades, but that is no longer the case. This begs the question — are you working to earn your patients’ business, or are you resting on laurels expecting your patients’ business?

Move Quick and Focus on Earning Your Patients’ Business Rather Expecting It

In industries that are rife with aggressive competition, there is an understanding born from survival. If you want to earn the business of your consumers, you have to offer more value than the other guys. Value is the key here, and it comes in many forms ranging from quality, convenience, cost, convenience, customer experience, and so on. My fear is that certain hospitals may have grown complacent due to a lack of competition, which does not bode well for protecting future strategic interests.

Metropolitan hospitals, it’s a smart move for you to pursue and seize revenue opportunity by leveraging technology to extend the service boundaries of your organization. If you can offer a service that tangibly has more value for the end consumer, then fair game.

Community and rural hospitals, you should act fast to get in front of this threat and seize the opportunity to leverage technology to offer your longtime customer base the best possible consumer experience before they explore any lures from the big-city hospitals. Your goal should be to proactively provide better service, offer more value to your patients, and lock in new consumer behavior patterns. Be proactive in exploring ways to expose your customer base to a new and more convenient way to access the care offered by your facility as a first line of defense, while still having them come to your facility to access face-to-face level care. Do this and you will develop new behavioral patterns in your consumers / patients that any outside competition will find difficult to break.

Simply put, by focusing on providing a quality consumer experience, you will concurrently better serve your patients, continue to fulfill your hospital’s mission statement (often built around how you exist to serve your community), and protect your financial interests from outside invaders looking poach your you patients and revenue.

Readers Write: AI in Imaging: Improving Outcomes Across the Care Continuum

AI in Imaging: Improving Outcomes Across the Care Continuum
By Calum Cunningham

Calum Cunningham, MBA is SVP/GM of healthcare diagnostic imaging for Nuance Communications of Burlington, MA.

The role of AI in medical imaging has been top-of-mind for a number of years, particularly as deep learning algorithms continue to improve to the point they can even identify findings that are not detectable by the human eye. As these solutions gain traction and adoption in clinical practice, more radiologists acknowledge the need for familiarity with the role AI plays in imaging and how to successfully integrate it into radiology workflows. In fact, RSNA recently launched its first-ever certificate program for imaging AI.

While the benefits to radiologists are significant and broad  — enhanced efficiency, greater satisfaction by automation for repetitive and mundane tasks, and freedom to focus on what matters most — AI in imaging, more specifically an integrated imaging network, adds value across the care continuum.

The radiology workflow is at the heart of a patient’s journey, informing healthcare decisions at the point of care, but also traveling both upstream and downstream. Once a patient’s images have been captured, radiologists depend on a range of technological platforms to integrate those images, relevant patient data, and AI services (such as automated 3D visualization solutions) from across the healthcare ecosystem.

When a radiologist reads a mammogram, for example, they need more than just the images from the patient’s most recent study. The patient’s previous images, information from the medical record (e.g., history, demographics, and symptoms), and increasingly, AI-powered diagnostic models are all essential to helping the radiologist accurately, comprehensively, and efficiently prepare the report.

The radiologist’s report likewise becomes part of the integrated imaging network, which breaks down the siloes that traditionally exist between care teams, administrators, payers, and other third parties. Sharing key imaging data with administrative, coding, and billing teams, for example, means supporting the organization’s financial resilience. These teams depend on accurate, comprehensive reports to protect the organization’s revenue cycle. When radiologists harness the power of AI to deliver more content-rich reports, insurance claims may be cleaner, which can result in appropriate reimbursements from payers. Similarly, sharing imaging data in this way can also streamline prior authorizations for treatments, surgeries, and prescriptions.

The downstream impacts don’t end there, however. Health plans and self-insured employers can take advantage of the integrated network to improve coordination and collaboration in ways that can address care quality and cost. Life science companies can make use of these insights to identify candidates for clinical trials.

An integrated imaging network also benefits healthcare provider organizations, which can apply AI-generated insights from diagnostic imaging to support earlier disease diagnosis as well as inform treatment options and planning. Perhaps one of the more exciting aspects of an integrated imaging network is the potential impact on patient follow-up adherence. When a radiologist includes an imaging follow-up recommendation in their report, only about half of those recommendations are adhered to. Not only does this represent a significant risk to the patient in terms of treatment and outcomes, but it can also create liability risks for the providers, not to mention the adverse impact on financial performance for the healthcare organization. The integrated imaging network can help close the loop on these follow-up recommendations, automating certain aspects of provider and patient communication to reduce the risk of delayed diagnosis.

In short, by seamlessly sharing clinical and imaging data and applying AI-generated insights and automation, organizations can maximize the value of existing healthcare IT infrastructure across the care continuum while improving patient outcomes.

Readers Write: What’s Missing from Healthcare’s Consumerization Conversation is Physicians

What’s Missing from Healthcare’s Consumerization Conversation is Physicians
By Casey Jenkins

Casey Jenkins, MBA is VP of product management for Epocrates of Watertown, MA.

The consumerization of healthcare is a trend that’s spreading like wildfire in the HIT industry. Healthcare organizations are increasingly turning to technology systems that create more consumer-friendly interactions for patients with the intention of ultimately improving access to care and boosting patient satisfaction.

Recent research supports this, finding that 74% of healthcare leaders are planning to invest in technologies that drive consumerization. This includes investing in technologies like telehealth, self-scheduling, text correspondence, online payment applications, and accessible patient portals. However, there’s one vital group that’s missing in healthcare’s consumerization conversation — physicians.

Due to the growing pressure to give patients the consumer-grade experience they are accustomed to in other areas of their lives, the physician experience has been deprioritized as a result. That needs to change, as rates of physician burnout are skyrocketing due to factors like information overload and administrative burden. It’s vital that the HIT industry also prioritizes the physician experience as the trend of healthcare consumerization continues to grow. Physicians are consumers, too – they’ve learned and adapted to everyday technology, and physician-facing technology needs to reflect this shift as well.

There are numerous ways that more consumer-friendly technology for physicians can alleviate their pain points in practice. One way is incorporating more personalization capabilities into the clinical information-seeking process. Today’s clinicians simply don’t have enough time in the day to stay abreast of the latest clinical information and can often feel overwhelmed. In fact, a recent study found that 64% of physicians reported not having time to stay up to date in their field.

Stronger personalization capabilities in clinical information tools can help by providing more curated information that’s updated and relevant to a specific physician’s practice and area of interest. This concept emulates the level of personalization that companies like Amazon, Facebook, and Netflix have created and that we’ve all come to expect across all our technology interactions. Personalization in clinical information tools can take the form of a data feed, much like a social media-style feed, that understands what information a specific physician is researching or seeing in the clinic and then presents relevant information in an organized and logical manner. This empowers physicians to sharpen their focus during the information-seeking process and ultimately make a more positive impact around patient care.

The push for more consumerization in physician-facing technology also includes a need for a stronger translation of science into technology applications to help curb information overload. In a recent survey, 89% of physicians reported that more clinical data isn’t always the answer. The right data at the right time is what is most important. When we can connect the right person and information at the right place and time within the clinician / physician workflow, that is when physicians will be able to provide the best-quality care.

Additionally, the HIT industry can help streamline workflows by putting the tools clinicians need in front of them for a more intuitive, easy-to navigate experience. This includes incorporating more thoughtfully designed interactions and experiences with the tools physician most frequently use.

Beyond that, the HIT industry can turn to familiar user experiences like a navigation bar. For example, navigation bars on social media apps include things like notifications, direct messages, or saved posts. In a HIT platform or technology system, a navigation bar could provide quick access to the key features a clinician needs at the point of care. like the patient’s medical chart or the medical news reel with the latest clinical developments. The HIT industry should lean into what people find familiar when determining how to put technology at a clinician’s fingertips.

As there continues to be a societal shift in what we expect from technology, the HIT industry needs to bring the physician experience into the fold of healthcare consumerization to truly improve healthcare outcomes. Stronger consumerization in physician-facing technology has the potential to reduce feelings of information overload, streamline workflows, and empower physicians to provide the best care possible to their patients.

Readers Write: Project or Program: Why It’s Time to Rethink Your Approach to Cyber Risk Management

Project or Program: Why It’s Time to Rethink Your Approach to Cyber Risk Management
By Jon Moore

Jon Moore, MS, JD is chief risk officer and SVP of consulting services for Clearwater of Nashville, TN.

The modern healthcare enterprise constantly expands with new technologies, services, and devices. Still, few have a reliable process to ensure that these new additions meet their cybersecurity standards or are added to their risk analysis. Most do a point-in-time risk analysis or conduct their risk analysis using only a sample of their information assets, or worse, both.

Point-in-time risk analysis in a complex healthcare organization will be outdated nearly as soon as it is completed. Sampling information assets is risky. Any number of assets outside the sample could threaten an organization.

A firewall is not enough to protect an asset, system, or network. Effective, compliant cyber risk management is not just about implementing and protecting the electronic health records (EHR) system.

Today’s cyber risk management should be comprehensive, including all aspects of daily operations and supporting systems, evaluating applications and systems both on-site and in the cloud. That can be challenging for even the best teams to manage and even more difficult for smaller organizations where access to skilled professionals, risk landscape intelligence, and financial re sources can be hard to come by. It’s further complicated in mid-size to larger healthcare organizations, where technologies, software, applications, and configurations can vary from location to location and sometimes from department to department.

Without accurate, up-to-date asset, software, and system inventories, a team can quickly fall into siloed risk management practices that focus on the known, leaving security gaps with the unknown.

Adding more challenges to the mix is the growing third-party risk that healthcare organizations face as their vendor and partner lists grow, especially in new applications or devices that streamline patient care. Owensboro Health CISO Jackie Mattingly recently spoke about the challenges in keeping up with vendors, systems, and programs that are brought into the organization by various departments. “Most of these major EHR systems have a pretty good grip on security for their systems. We use Epic, and they have things pretty well buckled up,” Mattingly said. “They’ll notify us if they detect an incident, but the many other ancillary systems we use pose a greater threat. You have to assess risk across the enterprise.”

A recently released Cyber Readiness Report found that some 74% of healthcare organizations haven’t yet implemented comprehensive software supply chain risk management policies. The report noted that more than 90% of respondents struggled to measure and implement software supply chain risk management policies in healthcare. That should be alarming considering the number of successful healthcare breaches recently resulting from vulnerabilities in third-party software solutions.

While forward-looking security teams are trying to keep pace with healthcare innovation and the adoption of new technologies, it’s important to remember that the data in legacy systems may also be at risk. Late last year, a healthcare organization in Canada discovered a breach that could have affected data dating back to 1996. Although its EHR appears unscathed, data was taken from legacy administrative systems like those used for reporting and patient satisfaction surveying. The breach affected 13 different but overlapping data categories, such as medical and other information, and impacted others, such as an affiliated non-profit that purchases IT services and file storage from the core agency.

If you’re still approaching cyber risk as an annual project or initiative, it’s time to rethink this approach. While nothing can guarantee that a cyberattack won’t become a breach, having a comprehensive ongoing program in place means that even in the worst-case scenario, you’ll be prepared to show that you did what was reasonable and appropriate to protect your systems and patient data. This goes a long way when the Office for Civil Rights investigates a breach or audits your organization. It can save you countless hours, resources, and money by resulting in a short investigation and more favorable determination.

Unsure of where to begin? Consider:

• Adopting reasonable and appropriate security controls across all of your information assets. Be sure to account for the legacy data you may have in storage somewhere. It needs protection, too.
• Employing identity and access management processes that limit access to patient data to only what is needed for an employee to perform their job.
• Segmenting your network as appropriate to reduce the ability of threat actors to move laterally through networks and systems.
• Using a risk management software solution to power an ongoing risk assessment and risk management program so you always know where your risks are and how to address them
• Working with an expert to develop a comprehensive risk management program for your organization, including seeking out program weaknesses and making plans to mature it over time.

Readers Write: The Next Frontier for Healthcare Consumerization

The Next Frontier for Healthcare Consumerization
By Aaron Fulner

Aaron Fulner, MS is senior director of product marketing at Edifecs of Bellevue, WA.

The pandemic accelerated consumers’ move to the driver’s seat of their healthcare. Consumers are using digital health devices now more than ever and are demanding a personalized, on-demand healthcare experience. To meet these heightened expectations, the healthcare industry needs to better stitch together all of the pieces – telehealth, artificial intelligence (AI) and machine learning, and interoperability standards – to create a comprehensive delivery model. A model, where data can be exchanged quickly and accurately. This is the next frontier for the consumer healthcare movement.

To reach this next stage, the healthcare industry needs to ensure data can be shared seamlessly across the healthcare system to best equip providers with real-time health information. Here’s how we get there:

Expand Telehealth from Acute Care to Chronic Condition Management

It’s no secret that telehealth use skyrocketed during the pandemic. Even following its peak in 2020 and 2021, telehealth usage is still 38 times higher than prior to the pandemic. Patient and provider muscle memory is changing, and telehealth is now the go-to for urgent care needs. The next chapter of the telehealth story includes a movement from tele-urgent care to telehealth for chronic care management and preventative care. This is especially important as 40% of adults in the U.S. reported avoiding medical care due to the pandemic. This means providers are playing catch up to ensure patients’ routine and preventative care needs are met.

Additionally, as providers work to offer comprehensive care to patients, they must have access to rich datasets about each patient. This includes using administrative information from encounter and enrollment files as well as clinical data stored in electronic medical records.  A comprehensive view of a patient enables the provider to be an informed partner in the care of a patient.

Integrate Artificial Intelligence and Machine Learning into the Internet of Things

Beyond telehealth, consumers are embracing the Internet of Things (IoT) to monitor their health at home. These digital health devices – smart watches, exercise bikes, glucose monitors, etc. – are used by more consumers today than ever before. For example, a recent Rock Health analysis found that digital health wearable ownership increased from 13% of consumers surveyed in 2015 to 45% in 2021.  The question remains: How can the industry enhance the impact of these tools with machine learning and artificial intelligence (AI)?

Remote monitoring devices combined with machine learning and AI create a powerful tool for providers by delivering real-time information and changes in patient health. For example, if a patient’s glucose is low, a glucose monitoring device with a layer of machine learning and AI proactively sends a notice to their provider to reach out and determine if a change in their care plan is appropriate. Ultimately, this gives providers the data to intervene earlier, work with more patients at a time, and improve margins.

Connect Consumer Digital Health Device Data with Provider Workflows

This increase in digital health tool utilization is ushering in a flood of new patient data. To move forward, the industry must integrate siloed data into provider workflows so providers can deliver holistic care. Connecting consumer health data with provider workflows signifies the convergence of healthcare and business data management standards.

To date, the Health Insurance Portability and Accountability Act (HIPAA) and recent interoperability rules declare the consumer as the agent of personal health data. Meanwhile, Health Level Seven International (HL7)’s Fast Healthcare Interoperability Resources (FHIR) and the Da Vinci Project have established the technical standardizations with consumer data and how it is exchanged across stakeholders.The Office of the National Coordinator for Health Information Technology (ONC) is leading the final push through its Trusted Exchange Framework and Common Agreement (TEFCA), which outlines business rules for data exchange and determines allowable uses for payment, reimbursement, and care data without consumers’ permission. The last mile for closing this gap between consumer data, payer, and provider workflows lies in empowering service providers to adopt these standards industry-wide.

The key to the future of healthcare consumerization is to determine how data is exchanged across the healthcare industry to better inform care, improve provider workflow, and integrate digital health data solutions into one place.

Readers Write: The ABCs of Using NLP for SDOH

The ABCs of Using NLP for SDOH
By Marty Elisco

Marty Elisco, MBA is CEO of Augintel of Northbrook, IL.

It has been established loud and clear: social determinants of health (SDOH) have a huge impact, even more than physical health, in determining the overall well-being of individuals. Yet obtaining an understanding of how specific SDOH factors affect individual patients is extremely difficult because SDOH data is not methodically collected by clinicians and social workers. This is a problem.

Unfortunately, it is just too difficult and time-consuming for clinicians to make sense of all the SDOH data because most SDOH data is buried in patient notes. This ultimately inhibits their ability to consume the data to inform decisions about individuals receiving care.

Natural language processing (NLP), a key discipline of AI that uses computers to understand the written word, tackles this problem head on. I encourage hospitals and health and human services organizations to explore NLP in their practices, particularly as technological innovation in this area is rising across healthcare.

Listed below are the simple ABCs of why health and human services organizations and hospitals should adopt NLP to make sense of SDOH. But before diving into the list, I want to emphasize: the technology is now here. NLP has matured significantly over the last five years, and it is now a proven method to extract key concepts in narrative healthcare data, such as SDOH, from text.

Cost Savings and More Efficient Care

Clinicians and case workers spend an overwhelming amount of time combing through narrative data — for example, reading typed or handwritten patient notes and case notes — to understand the status of their patient and think through potential courses of treatment. All of this time spent reviewing unstructured data is time that could be better spent in any number of ways, such as spending more time with patients.

The beauty of NLP is that it automatically highlights impactful indicators and trends across case or patient notes, thereby quickly revealing SDOH to the case workers and clinicians on the case. An NLP platform relieves health and social services workers of the time it takes to comb through the staggering amount of records by readily highlighting SDOH across a case.

Improved Outcomes

NLP empowers caseworkers and clinicians with the information they need to make impactful decisions and allow supervisors to maximize quality of care delivered. This is because NLP provides a deeper understanding of a patient or case.

The Gravity Project is a national public collaborative creating diagnostic codes for SDOH factors with the goal of having those codes incorporated into the existing list of medical diagnosis codes. The idea for the Gravity Project originated in 2017, and prior to then, hospitals and health and human services organizations had no way of incorporating SDOH into their care besides entering it in free-form into patient notes, even though it is now widely understood that a range of social, environmental, and economic factors impact health status often greater than the actual delivery of health services. NLP can extract the information in unstructured data and translate that to Gravity codes to support the diagnostic process. These diagnoses can lead to treatments and interventions that improve outcomes.

Risk Mitigation

NLP enables organizations to quickly identify patients at the highest level of risk so interventions can be provided. I firmly believe that you can only truly identify risk by understanding what is included in the narrative data. Most risk stratification systems today simply look at claims data to do this. But claims data is an incomplete picture. If care coordinators had a full picture through SDOH, then they would have a much better tool to identify those who are at most risk, and where early interventions can be referred to prevent serious health conditions from occurring.

The case for using NLP is as easy as ABC. Described above are three tangible benefits to hospitals and health and human services organizations for incorporating NLP into their practices. All players in the healthcare ecosystem share the ultimate goal of improving outcomes while saving costs, and NLP is a surefire way to do just this.

Readers Write: The Changing Dynamics of Today’s Healthcare IT Labor Market

The Changing Dynamics of Today’s Healthcare IT Labor Market
By Mike Silverstein

By Mike Silverstein is managing partner of HIT & Life Sciences for Direct Recruiters, Inc. of Solon, OH.

Whether you are a health system, a health tech company, or an employee of either, the last two years have been a roller coaster. COVID-19 has had rippling impacts across all aspects of the HIT talent market, and the potential economic correction is compounding those ripples.

From March 2020 until June 2020, if you had a job and your employer would let you work from home as COVID-19 spiked, you considered yourself lucky. As an HIT recruiter, it was a scary time that brought me back to my start in 2008, when there were more candidates than positions, and my HIT software company clients were canceling hiring plans indefinitely.

Everyone was trying to adapt to a fully remote working situation. Health systems around the country were pausing elective positions and moving all available administrative roles from on-premise to remote. What is interesting is this felt like something very temporary at the time, but it has proved to be a historic inflection point in employees’ relationships with their employers and patients’ relationships with their doctors.

Today, if you are a health tech company and you don’t offer a virtual work environment or at least a hybrid schedule, it is almost impossible to help you find top talent. If you are a health system / health plan and don’t offer telehealth visits, live chat, virtual scheduling, online payments, and on-demand answers to clinical questions (aka digital front door), your patients/members are going to find a provider / payer that does. This consumerism dynamic signaled an opportunity for an industry disruption that attracted billions of dollars of private investment in the space and led to the craziest talent land grab I have experienced in my 14 years in healthcare recruiting.

Interviews moved to video, speed became a necessity, and companies who had coffers of fresh funding changed the playing field. If you were an experienced healthcare professional, you had an unparalleled opportunity to leverage your career and have multiple employers bidding for your services. If you were the incumbent, you quickly had to adapt from your employees being grateful for keeping them employed to figuring out what you are going to do to allow them to grow professionally, both in responsibility and finances, while allowing them to be with family and have personal flexibility.

In the past handful of weeks, I have started to feel those dynamics change once again. As inflation has driven up the price of our day-to-day and the Fed has raised interest rates to combat it, employers are starting to draw some lines in the sand. Salary offers are starting to level out and working from an office is creeping its way back into job requirements. The workforce still feels like they have the upper hand, but I think we are going to see a correction like what looms in the housing market. Companies are beginning to get advised by their investors to tighten their belt, and I have heard from several industry leading startups and growth companies that fundraising has gotten more challenging with valuations coming down to earth. From a labor market perspective, that means fewer open roles in the back half of the year, and as a result, a leveling out in terms of job offers.

As a guy who makes a living by matching candidates with employers, this is a little nerve-wracking. The good news is, I think healthcare has changed for good, and because it isn’t getting any cheaper, tech companies that can help lower the cost of healthcare, provide easier access, and improve the quality will continue to have a very bright future and need talent. I also believe at my core that talent wins the day and is always a phenomenal investment. The companies that will thrive regardless of what the economy does are the ones who hire the best people and focus on giving them great support.

There are still countless problems to solve in our industry, and the net-net is healthcare continues to be a terrific place to work, earn, and invest in as we head into the second half of 2022.

Readers Write: Four Keys to Patient Engagement for Complex Care Plans

Four Keys to Patient Engagement for Complex Care Plans
By Jeff Pigatto

Jeff Pigatto is VP and global head of Salesforce practice at Infostretch of Santa Clara, CA.

For 78% of healthcare providers, the COVID-19 pandemic has made patient engagement more important than ever, according to an industry report. Industry leaders recognize the need to improve patient engagement to reduce patient leakage, especially for those with complex care plans. Without robust engagement, patients are more likely to fall through the cracks.

To boost patient engagement, leaders need a plan. I’ll offer four key elements of a patient engagement strategy.

Use a cloud-based single system of engagement

Patients with complex treatment plans often face uncoordinated care, even when they are seeing in-network providers. Some providers, with the help of expensive back-office operations, still rely on paper-based systems to record patient information. Others may use digital tools, but they often depend on local storage and lack key system integrations. In both cases, providers can’t efficiently share patient data. As a result, the patient experience suffers.

Without streamlined data-sharing tools, patients often have to complete similar intake forms at separate care centers. That’s a tedious process,  and a vulnerable one. Complex care patients often have emotionally fraught conditions. When they have to divulge sensitive information again and again, they may grow frustrated, uncomfortable, and unsatisfied. That creates a problem for providers. Dissatisfied patients may turn to other care options or may not receive the care they need, which worsens the patient leakage problem and impacts revenue generation.

With a cloud-based data-sharing system, providers can ensure that all in-network providers have the same access to patient data. This limits duplicate form completion, meaning patients have to divulge information less often. Key software integrations can further simplify patient data management. The result for in-network providers is a streamlined patient experience that’s more compelling than out-of-network options.

Offer proactive patient interaction

A provider will often issue an in-network referral and assume patients will follow through. But patients are human. Schedules quickly change, and people can be forgetful. If providers don’t engage in proactive and consistent outreach, patients will receive slower access to the care they need. That means providers lose out on revenue. With proactive patient interaction, providers can maintain patient engagement while minimizing gaps in care.

An effective patient interaction model includes:

• Scheduling appointments immediately after referral.
• Enabling form completion before care visits.
• Providing a pre-appointment patient checklist.
• Sending regular reminders about care visits and uncompleted forms.
• Emailing patients follow-up actions after each visit.

With consistent updates, patients will know that providers are serious about their care experience. What’s more, they’ll be more likely to remember the steps needed to stay in network.

Emphasize patient education

For many complex care patients, it’s expensive to manage their long-term health. Between repeated clinical visits, treatment, and therapeutics, the costs quickly add up. Over time, patients may see providers as putting profit over care. They might start looking for a more human-centered wellness experience,  and that might be out of network. But consistent patient education can help. When patients feel empowered to manage their health, they can:

• Stabilize or improve their conditions.
• Follow their care plans more effectively.
• Reduce the risk of readmissions or emergency room visits.
• Lower the overall cost of care.

Providers benefit, too. Through patient education, they can prove they’re focused on helping patients heal. That approach could be exactly what patients need to stay with their current provider.

Here’s what patient education looks like in practice. Consider a patient who’s on a weight management plan for diabetes. Every few weeks, their provider can send plain-language materials showing how exercise helps improve insulin sensitivity. If the patient has a smart watch, their provider can suggest downloading a step-tracking app that syncs with the provider’s patient data management system. Then, the provider can use that data to keep tabs on anomalies. If the patient’s steps drastically dip between months, the provider can ask about barriers to wellness management  and help strategize solutions. The result: the patient’s long-term health will likely improve, insurance claims and out of pocket expenses will reduce, and providers can maximize their value.

The patient engagement tactics we’ve looked at so far work together to prevent patient leakage, but they can be tedious to manually implement and maintain. That’s why I recommend a fourth key element of a patient engagement strategy:

Automate patient journeys

When providers use digital tools to automate every stage of the patient journey, they can save time, reduce human error, and minimize manual labor. In the long term, automation can help providers save on labor costs. Patient journey automation might look like:

• Automatically contacting patients to schedule their next care visit.
• Automatically delivering a pre-visit checklist at Day 7 before each visit.
• Sending automated patient follow-ups at Day 1, Day 7, and Day 30 after each visit.

Automating patient journeys can support existing patient engagement efforts to help providers reduce leakage.

Pandemic pressures have made patient engagement a cornerstone of efficient access to complex care. But the pandemic is also expanding the traditional range of complex care patients. In fact, new research suggests that between 20 and 25% of those who catch SARS-CoV-2 will have some form of long COVID. It can last several months and may require a complex care plan. The prevalence of long COVID amounts to what some call a “mass disabling event.” Alongside existing complex care patients, providers must invest in a long-term patient engagement strategy that accounts for an expanding chronically ill population.

Readers Write: Payers Are Approaching a Moment of Reckoning on Fraud, Waste, and Abuse

Payers Are Approaching a Moment of Reckoning on Fraud, Waste, and Abuse
By Ketan Patel, MD

Ketan Patel, MD is chief medical officer of SyTrue of Stateline, NV.

Payers are poised to face a new operating environment with significantly more scrutiny over fraud, waste, and abuse (FWA) in the wake of COVID-19.

Two years ago, the federal government created the Medicare Advantage (MA) Risk Adjustment Data Validation (RADV) program to beef up audits of MA insurers. For 2022, CMS also doubled its budget for fraud, waste, and abuse (FWA) investigations, and the Department of Justice just announced charges against 21 defendants accused of various healthcare fraud schemes involving the COVID-19 pandemic. Meanwhile, payers are working to reconcile billions of dollars in COVID-related medical expenses and correctly identify risk for the surging number of long COVID patients.

These factors have converged to generate significant potential headwinds for payers and will create the following two new realities:

• Payers will be forced to sift through increasingly huge volumes of clinical records to identify potential fraud and waste, as well as confirm bill accuracy to properly compensate providers.
• At the same time, as we head into the third year of the pandemic, payers will uncover an unprecedented amount of FWA related to COVID-19.

How successfully payers manage these challenges will be determined by their ability to replace time-consuming and expensive manual processes with artificial-intelligence-based tools that comb patient records to identify potential fraud, assess patient and population risk, and confirm payment accuracy.

In the past, payers depended on expensive and time-consuming chart reviews to find and extract key unstructured data from patient records, such as information that reveals the need (or lack thereof) for a patient to undergo various COVID-related tests. More recently, though, payers have turned to natural language processing (NLP) as an alternative to manual chart reviews. NLP is an AI-based technology that enables computers to “read” and understand text by simulating humans’ ability to interpret language, but without the limitations of human bias and fatigue.

With NLP, payers can retrospectively analyze longitudinal health data to find a particular piece of clinical information about a single patient or identify subsets within populations that require further exploration. Given today’s environment of increased FWA scrutiny, NLP is poised to play an increasingly important part in helping payers pinpoint instances of FWA.

The following are three ways payers can leverage NLP to improve FWA detection:

1. Detect patterns. In cases of FWA, there is often a pattern of repeatability in the data, such as a large number of patients meeting the same prior authorization requirements. NLP helps payers detect these patterns that lack the natural variability found in legitimate patient records.
2. Identify outliers. In the same respect, NLP can help payers spot unusual data that may be representative of fraud, such as expensive tests for which there is no medical necessity. With its ability to accurately analyze unstructured data to identify anomalies within records, NLP can quickly verify the presence, or lack of, critical data.
3. Improve scale. While even the most hard-working humans possess limitations on their ability to perform a high amount of chart reviews in a narrow timeframe, NLP automates the process, enabling substantial improvements in scalability. Because some complex medical records may consist of thousands of pages, NLP can drive significant savings in time and money in reviews.

For payers, the time to prepare for increased FWA scrutiny is now.

Readers Write: How One ACO Used Analytics to Promote Health Equity: Lessons for the ACO REACH Model

How One ACO Used Analytics to Promote Health Equity: Lessons for the ACO REACH Model
By Michael Meucci

Michael Meucci is chief operating officer of Arcadia of Boston, MA.

A greater focus on promoting health equity is at the heart of changes CMS recently made to its direct contract model, now labeled as the Accountable Care Organization Realizing Equity, Access, and Community Health (ACO REACH) Model.

While an emphasis on health equity is long overdue, this shift creates challenges for ACOs in measuring, monitoring, and improving health equity – something that can’t happen without leveraging advanced analytics to account for those factors impacting a patient’s ability to effectively manage their health, otherwise known as social determinants of health (SDoH).

A CMS Direct Contracting Entity, Massachusetts-based Community Care Cooperative (C3) incorporated advanced analytics and tight partnership with community agencies into its health equity program under the MassHealth Medicaid ACO program, driving significant improvement in the health of its diabetes patient population, in addition to a reduction in its total cost of care, positioning C3 for eventual success under the new model.

The US Centers for Medicare and Medicaid Services (CMS) launched the ACO REACH model in February, highlighting the organization’s commitment to “promoting value-based care that improves the healthcare experience of people with Medicare, Medicaid, and Marketplace coverage.” To that end, CMS requires all model participants to develop and implement “robust” health equity plans to identify underserved communities, in addition to implementing initiatives that “measurably” reduce health disparities within their patient populations.

Next, CMS placed a high priority on ensuring that medical providers play a prominent role in ACO REACH participating organizations, requiring that at least 75% control of each ACO’s governing body must be held by participating providers or their designated representatives. That number is a significant jump from the 25% requirement held by the ACO REACH model’s predecessor, which was known as the Global and Professional Direct Contracting Model.

Additionally, the new ACO REACH model is designed to deliver better protection to patients through more ACO participant vetting, monitoring, and greater transparency. CMS will look to accomplish that by asking for more information on applicants’ ownership, leadership, and governing boards to gain better visibility into ownership interests to ensure participants’ interests align with CMS’ vision.

The new model’s first performance year begins on January 1, 2023, with the model planned to run for four performance years through 2026. Applications to participate in the first year were due near the end of April 2022.

For patients, the promise of the model is better care, but with a greater focus on addressing SDoH, such as barriers to transportation, nutrition, and healthcare. For providers, the ACO REACH model offers the potential of a more predictable revenue stream and the ability to use those funds more flexibly to meet their patients’ needs.

Community Care Cooperative is an ACO that formed when the state of Massachusetts launched the MassHealth ACO program. MassHealth, which combines the state’s Medicaid and the Children’s Health Insurance programs, has emphasized engaging with community partners to help treat the whole patient, including addressing social needs that are barriers to care. C3 was created by a network of Federally Qualified Health Centers (FQHCs) to better serve their communities by providing more opportunities for individuals to receive coordinated, holistic, and culturally appropriate care in the communities where they live and work.

Incorporated in 2016, C3 serves over 170,000 MassHealth members with a total cost-of-care budget of $1 billion at 18 statewide health centers. In early 2020, inspired by the national conversation around equity, C3 launched a health equity program aimed at addressing physical and behavioral health needs, in addition to SDoH such as nutrition and housing. Earlier this year, C3 submitted its application to CMS to become a REACH ACO.

C3 started its health equity initiative in 2020 by collecting self-reported SDoH data from members, including race, ethnicity, and language information. While self-reported data may not be perfect, it is a good starting point to begin understanding the challenges facing a population of patients.

Next, C3 formed a diversity, equity, and racial justice committee to examine its patient data to investigate areas for improvement, in addition to thinking about ways to most effectively use the data in its possession. For example, the committee investigated whether the racial and ethnic makeup of patients referred to outside social services agencies was representative of the group’s overall patient population, in addition to the racial breakdown of immunization rates for two-year-olds.

To promote greater transparency, C3 has established a scorecard of key metrics pertaining to not just the usual operational numbers such as cost and utilization, but also data pertaining to health equity, such as comparisons of hypertension control by patients’ race and ethnicity. At each leadership meeting, these scorecards are posted for each of C3’s 18 health centers, prompting discussions of how to improve the metrics.

Perhaps most importantly, the attention to detail around data has led C3 to establish several experimental “flex” programs under Medicaid that are also known as “Section 1115 Demonstrations,” in which C3 partners with various social-services organizations (SSOs) that specialize in addressing SDoH, such as helping patients obtain housing or groceries.

For example, in one demonstration, C3 partnered with an SSO that delivered nutritious meals to patients’ homes. The program yielded impressive results: 68% of members with diabetes who received home-delivered meals had lower HbA1c scores in their post-enrollment tests compared with their pre-enrollment tests. Similarly, the percentage of diabetes patients with HbA1c scores that indicate their diseases are well-controlled grew significantly as a result of the home-delivery program, from 38% prior to the program to 71% after.

Additionally, the home-meal delivery program led to a substantial drop in the cost of care. In the six months after enrollment, total healthcare costs for the 456 patients enrolled in the program dropped by an average of more than 30%, from $17,902 to $12,349, compared to the six months prior.

C3’s experience with using analytics to improve health equity offers an example that ACO REACH participants can emulate. In the future, C3 looks to leverage the cost savings its programs generate to launch expanded initiatives that promote greater health equity.

Christina Severin, president and CEO of Community Care Cooperative, contributed to this article.

Readers Write: Real-World Data Connects the Patient’s Past, Present, and Future: A Systems-Level Approach to Effective, Holistic Cancer Care

Real-World Data Connects the Patient’s Past, Present, and Future: A Systems-Level Approach to Effective, Holistic Cancer Care
By Miruna Sasu, Ph.D.

Miruna Sasu, PhD, MBA is president and chief executive officer of COTA, Inc. of New York, NY.

Too often, fragmentation across the care continuum prevents the delivery of timely, tailored cancer therapies. By leveraging real-world data to inform our decision-making at the systems level, we can ensure that cancer patients have access to personalized, effective treatments.

For the typical cancer patient, the road to remission is anything but a straight line. From getting the right diagnosis to accessing the most effective therapies, patients face a fragmented and disjointed journey that can be filled with roadblocks and detours.

Part of the problem is the nature of cancer itself. It adapts and evolves to evade treatment, driving oncologists and life sciences companies to continually develop innovative therapies and update their standards of care.

But equally problematic is the way we direct patients along their journey. In too many cases, we cannot access the data-driven insights that we need to make timely decisions with our patients. We struggle to overcome systemic barriers, such as competing incentives and overly narrow methods of care delivery. And we don’t have the shared infrastructure in place to continuously learn from our patients and enhance future decision-making based on the lessons of the past.

Fortunately, we can change the status quo if we adjust our notions of what it means to work together at a systems level  and if we leverage emerging assets, such as real-world data (RWD), to create a more comprehensive, predictive, and personalized pathway to better cancer care for all patients.

Healthcare is an industry of extreme specialization, which brings both benefits and challenges to patient care.

Naturally, it’s crucial to have experts with deep experience in very specific fields to ensure that people with complex conditions get the care they need. But specialization can make it more difficult for patients to get the right care at the right time.

For example, if a patient goes to a podiatrist for pain in their foot, the podiatrist will do everything she can to examine the relevant structures.

If they finds nothing remarkable, however, they likely won’t suspect that the problem might actually be referred pain from ovarian cancer. And chances are, they won’t have access to information about the patient’s mother’s BRCA-1 mutation, which potentially raises the risk of that cancer in the person they are treating. The patient will go home with a recommendation to rest and ice their foot, not a referral to an oncologist, and it may be weeks or months before they get the correct diagnosis.

Both the patient and the podiatrist did everything “right” in this situation, yet the outcome is still suboptimal for everyone involved.

That’s because both our care practices and our patient data are viewed through an overly narrow lens, causing us to miss the big picture and make connections that may fall outside of the traditional site-specific approach to medical care.

In cases like these, what we need is a generalist: a holistic, comprehensive view of the patient, their history, their clinical and non-clinical risks, and all of the other factors that may point to the correct diagnosis or a favorable response to a certain therapy.

Data can be that generalist. By combining RWD from electronic health records; claims; medical devices; patient reports; and other sources with clinical trial information, registry data, and additional inputs, we can begin to develop the systems-level thinking we need to effectively diagnose and treat patients with cancer.

To maximize the value of our data to inform care decisions, we need to reexamine the fundamental architecture of our operating environment.

Life sciences companies, clinical providers, payers, and regulators struggle with trust issues and conflicting incentives that inhibit collaboration and prevent us from working together efficiently as a coordinated system.

If patient data is to be the generalist that unlocks silos in care, we need to stop treating it as proprietary, competitive leverage and start viewing it as a shared resource that can actively save patient lives.

In order to successfully make this shift, we must transcend our individual motivations and more effectively share precise and applicable data-driven insights across the divide so that everyone can benefit from what RWD can tell us about the right patient care.

With this approach, we can begin to take that holistic, bird’s-eye view of patient care that is crucial for identifying and treating cancer as quickly as possible. We can start to build cohorts of similar patients based on rich and comprehensive information about their treatment paths and outcomes. Then, we can predict the experiences of future patients and get them on therapy sooner, make the next correct treatment decision, or enroll them in promising clinical trials.

The result will be better experiences and outcomes for patients and more fuel for innovation for life sciences companies and providers, including a more robust and targeted pipeline for filling clinical trials.

If used correctly, RWD can be the bridge that connects the isolated corners of the care environment and leads us along a smoother, faster, more personalized pathway to high-value cancer care.

RWD will be crucial for understanding how to efficiently pivot for the patient as their story evolves. As we integrate RWD into our decision-making processes, we will need to work together to make certain that it is created, collected, and curated correctly while paying the utmost attention to patient privacy and data security.

We know this won’t be an easy task, especially if we let historical divisions influence our relationships with one another. We know that we have a great deal of work ahead of us to realign incentives, develop our real-world data assets, and set appropriate guardrails for a newly collaborative industry.

However, it can be done. If we can put aside our personal viewpoints and look at the cancer journey through the eyes of a frustrated, frightened patient, we will be able to successfully focus on our shared mission to find new treatments for cancer, improve patient experiences, and ultimately save lives.

Readers Write: Answering the Call of Nurses Month: Arming Nursing Schools to Fill the Practice Gap

Answering the Call of Nurses Month: Arming Nursing Schools to Fill the Practice Gap
By Julie Stegman

Julie Stegman is vice president of the nursing segment of health learning, research, and practice business at Wolters Kluwer.

The theme of Nurses Month this year is “Nurses Make a Difference.” But they can only continue to do so if they are supported in their roles, and that starts with education.

The ongoing nursing shortage has devastated hospitals across the nation, affecting patient care and driving high rates of burnout among those still practicing. And as the population continues to grow and age, demand for healthcare services will only increase. Reports project that 1.2 million new registered nurses (RNs) will be needed by 2030. To address today’s nursing crisis and empower nurses to continue making a difference, we need a collaborative approach that brings practice and academia together to improve new nurses’ confidence and competence, overall nurse retention, and to produce more nurses ready for the field, eager and product to care for patients.

While practice adjustments such as more flexible work schedules, cross training, and alternative care models can help address the current shortage by better supporting and thereby retaining nurses in the field, academia also has a significant role to play. Training new nurses efficiently and effectively is essential to meet the demands of practice today and for years to come. Yet a survey by the Association of Colleges of Nursing found over 80,000 qualified BSN applicants have been turned away from nursing school due to budgetary constraints and a lack of faculty, clinical sites, and classroom space.

During the pandemic, these challenges were exacerbated as hospitals and academic medical centers closed their doors for educational purposes because they did not want students using the limited personal protective equipment they had on hand, or to be exposed to COVID-19. Sites that had previously closed their doors to students are now becoming more available, but the underlying challenge of a lack of clinical sites continues to limit nursing school applicants.

While the adoption of simulation and other virtual technologies was already underway in nurse education before COVID-19 hit, the pandemic accelerated rapid adoption of virtual simulation, virtually overnight, to help fulfill the necessary clinical time requirements for graduation. This shift was a necessary one, as virtual simulation has proven its value as an essential resource for nursing schools to bridge the gap between classroom and clinical practice, including the use of high-fidelity manikin-based simulation, to ensure professional competency for nurses about to enter the field. It also provides an essential training resource for nurses to learn how to personalize and individualize care based on patient needs and clinical cues.

Simulation programs have offered a vital stand-in for real-world clinical sites that have been unable to take on nursing students during the pandemic. By mirroring real clinical practice, virtual simulation teaches nursing students to recognize and analyze cues such as pain, paleness, urticaria — effectively to take action and respond to unfolding visual and audio responses from the patient to improve clinical reasoning skills in a safe virtual environment. Simulated nursing education programs also offer end-to-end practice instruction, including reflective practice and debriefing after the simulated interaction is complete.

While this technology has been in use for nearly a decade, the last two years have accelerated adoption of virtual tools in and out of classrooms. Simulation can offer a sustained impact on nursing by addressing the shortage of clinical sites that has been a limiting factor to nursing school admission.

While our frontline nurses are continuing to provide care throughout this pandemic, healthcare systems are embracing the opportunity to innovate and modernize their practices to better support their nurses. At the same time, academia continues to innovate to ensure the ripple effects of the pandemic don’t impact the critical nursing education system. Effecting change at the education level is crucial and will positively affect the nursing profession as a whole, creating more practice-ready nurses who are equipped to manage the demands of real-world practice. Staring Nurses Month in the face, we need to enact immediate change at both the practice and academic level to create a more resilient nursing workforce and continue delivering the best care possible to patients.

Readers Write: How Automation Can Transform Healthcare Delivery

How Automation Can Transform Healthcare Delivery
By Lisa Weber, MSHA, MEA

Lisa Weber is director in industry solutions practice at UiPath of New York, NY.

A recent survey found that 90% of clinicians agreed that quality measures, including patient satisfaction, have driven change in healthcare in the last decade. The desire for better quality of care and patient experience is clear, but many healthcare organizations struggle with where to start. Consider automation.

One of the major barriers to providing the best care is the crushing amount of tedious, administrative work tasked to clinical and administrative healthcare workers. It is hard to think about a doctor’s office without hearing the constant click of a computer keyboard by every type of healthcare worker. Whether it is updating patient records, scheduling follow-up appointments, or simply taking notes, it can seem like everyone is spending more time looking at a screen than looking at the patient, which can be frustrating for both the patient and staff.

Integrating automation tools, such as software robots, can help healthcare organizations improve inefficiencies, alleviate healthcare provider workloads, and transform healthcare delivery by reclaiming time for patient engagement. The saved time ultimately leads to better, more personalized patient care. Doctors, nurses, and supporting staff would rather devote more time to patients and less to navigating and maintaining online records.

Software robots—think of them as digital assistants—can take over day-to-day tasks that involve accessing, entering, and updating systems and processes just as a human would. Much of the routine and repetitive work that medical professionals dread doing – such as data entry, revising records, checking records for compliance, and scheduling appointments – are perfectly suited tasks for digital assistants. They not only give healthcare workers ample time back in their day, but also boost productivity and workplace satisfaction, accuracy of data, and improved patient experiences.

Specific capabilities of digital assistants for the medical field include completing tasks like:

• Preparing charts ensuring that all the relevant clinical data (from multiple sources, including other physicians) is available and current.
• Making sure all paperwork is completed, signed, and up to date.
• Verifying insurance coverage and collecting any due amounts.
• Scheduling follow-up appointments, labs, and other testing.
• Initiating prior authorizations and physician referrals.

During the height of the pandemic, a hospital’s infection control department was struggling to keep up with the hundreds of people coming in every day for COVID-19 testing. As fast diagnosis and response are crucial in preventing the spread of COVID-19, nurses at the hospital needed digital assistance to not only streamline testing, but also to take the pressure off already overworked staff. Using software robots, COVID-19 test result information was processed in a fraction of the time, disseminating patient results in minutes. Overall, the hospital saved three hours a day by using automation to distribute COVID-19 test results.

Utilizing digital assistants significantly reduces the administrative workload of healthcare providers, meaning they have more time for patient engagement and other tasks that make better use of their talent and expertise. These positive effects start to snowball as less time on tedious administrative work means less burnout and turnover, and greater employee satisfaction and productivity. And all these organizational benefits gained from digital assistants in turn improve the quality of care and the patient experience.