Free EMR Newsletter Want to receive the latest news on EMR, Meaningful Use, ARRA and Healthcare IT sent straight to your email? Join thousands of healthcare pros who subscribe to EMR and HIPAA for FREE!!

Healthcare AI Could Generate $150B In Savings By 2025

Posted on September 27, 2018 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

Is the buzz around healthcare AI solutions largely hype, or can they deliver measurable benefits? Lest you think it’s too soon to tell, check out the following.

According to a new report from market analyst firm Frost & Sullivan, AI and cognitive computing will generate $150 billion in savings for the healthcare business by 2025.  Frost researchers expect the total AI market to grow to $6.16 billion between 2018 and 2022.

The analyst firm estimates that at present, only 15% to 20% of payers, providers and pharmaceutical companies have been using AI actively to change healthcare delivery. However, its researchers seem to think that this will change rapidly over the next few years.

One of the most interesting applications for healthcare AI that Frost cites is the use of AI in precision medicine, an area which clearly has a tremendous upside potential for both patients and institutions.

In this scenario, the AI integrates a patient’s genomic, clinical, financial and behavioral data, then cross-references the data with the latest academic research evidence and regulatory guidelines. Ultimately, the AI would create personalized treatment pathways for high-risk, high-cost patient populations, according to Koustav Chatterjee, an industry analyst focused on transformational health.

In addition, researchers could use AI to expedite the process of clinical trial eligibility assessment and generate prophylaxis plans that suggest evidence-based drugs, Chatterjee suggests.

The report also lists several other AI-enabled solutions that might be worth implementing, including automated disease prediction, intuitive claims management and real-time supply chain management.

Frost predicts that the following will be particularly hot AI markets:

  • Using AI in imaging to drive differential diagnosis
  • Combining patient-generated data with academic research to generate personalized treatment possibilities
  • Performing clinical documentation improvement to reduce clinician and coder stress and reduce claims denials
  • Using AI-powered revenue cycle management platforms that auto-adjust claims content based on payer’s coding and reimbursement criteria

Now, it’s worth noting that it may be a while before any of these potential applications become practical.

As we’ve noted elsewhere, getting rolling with an AI solution is likely to be tougher than it sounds for a number of reasons.

For example, integrating AI-based functions with providers’ clinical processes could be tricky, and what’s more, clinicians certainly won’t be happy if such integration disrupts the EHR workflow already in existence.

Another problem is that you can’t deploy an AI-based solution without ”training” it on a cache of existing data. While this shouldn’t be an issue, in theory, the reality is that much of the data providers generate is still difficult to filter and mine.

Not only that, while AI might generate interesting and effective solutions to clinical problems, it may not be clear how it arrived at the solution. Physicians are unlikely to trust clinical ideas that come from a black box, e.g. an opaque system that doesn’t explain itself.

Don’t get me wrong, I’m a huge fan of healthcare AI and excited by its power. One can argue over which solutions are the most practical, and whether AI is the best possible tool to solve a given problem, but most health IT pros seem to believe that there’s a lot of potential here.

However, it’s still far from clear how healthcare AI applications will evolve. Let’s see where they turn up next and how that works out.

Does NLP Deserve To Be The New Hotness In Healthcare?

Posted on August 30, 2018 I Written By

Anne Zieger is a healthcare journalist who has written about the industry for 30 years. Her work has appeared in all of the leading healthcare industry publications, and she's served as editor in chief of several healthcare B2B sites.

Lately, I’ve been seeing a lot more talk about the benefits of using natural language processing technology in healthcare. In fact, when I Googled the topic, I turned up a number of articles on the subject published over the last several weeks. Clearly, something is afoot here.

What’s driving the happy talk? One case in point is a new report from health IT industry analyst firm Chilmark Research laying out 12 possible use cases for NLP in healthcare.

According to Chilmark, some of the most compelling options include speech recognition, clinical documentation improvement, data mining research, computer-assisted coding and automated registry reporting. Its researchers also seem to be fans of clinical trial matching, prior authorization, clinical decision support and risk adjustment and hierarchical condition categories, approaches it labels “emerging.”

From what I can see, the highest profile application of NLP in healthcare is using it to dig through unstructured data and text. For example, a recent article describes how Intermountain Healthcare has begun identifying heart failure patients by reading data from 25 different free text documents stored in the EHR. Clearly, exercises like these can have an immediate impact on patient health.

However, stories like the above are actually pretty unusual. Yes, healthcare organizations have been working to use NLP to mine text for some time, and it seems like a very logical way to filter out critical information. But is there a reason that NLP use even for this purpose isn’t as widespread as one might think? According to one critic, the answer is yes.

In a recent piece, Dale Sanders, president of technology at HealthCatalyst, goes after the use of comparative data, predictive analytics and NLP in healthcare, arguing that their benefits to healthcare organizations have been oversold.

Sanders, who says he came to healthcare with a deep understanding of NLP and predictive analytics, contends that NLP has had ”essentially no impact” on healthcare. ”We’ve made incremental progress, but there are fundamental gaps in our industry’s data ecosystem– missing pieces of the data puzzle– that inherently limit what we can achieve with NLP,” Sanders argues.

He doesn’t seem to see this changing in the near future either. Given how much money has already been sunk in the existing generation of EMRs, vendors have no incentive to improve their capacity for indexing information, Sanders says.

“In today’s EMRs, we have little more than expensive word processors,” he writes. “I keep hoping that the Googles, Facebooks and Amazons of the world will quietly build a new generation EMR.” He’s not the only one, though that’s a topic for another article.

I wish I could say that I side with researchers like Chilmark that see a bright near-term future for NLP in healthcare. After all, part of why I love doing what I do is exploring and getting excited about emerging technologies with high potential for improving healthcare, and I’d be happy to wave the NLP flag too.

Unfortunately, my guess is that Sanders is right about the obstacles that stand in the way of widespread NLP use in our industry. Until we have a more robust way of categorizing healthcare data and text, searching through it for value can only go so far. In other words, it may be a little too soon to pitch NLP’s benefits to providers.

What Were The Best Practices and Benefits of Implementing a CDI Program at Baystate?

Posted on October 28, 2014 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

I recently sat down with Walter Houlihan, Director of Health and Information Management and Clinical Documentation at Baystate Health, and Steve Bonney, EVP of Business Development and Strategy at RecordsOne to talk about the CDI (Clinical Documentation Improvement) program at Baystate Health. In the video below Walter and Steve talk about the savings that Baystate Health has received from their CDI program including how Walter has used dashboards, metrics and quality to convince senior management to increase Walter’s CDI staff from 4 FTEs to 10 FTEs so that they can review 100% of patients.

Steve and Walter also talk about how they use technology to make those 10 employees more efficient and make it possible for their CDI employees to work remotely.

How is your CDI program working? What technology are you using to make your CDI efforts more efficient? Have you had the success that Walter has had getting buy in from senior management?

What Would Make Us Not Delay ICD-10 in 2015?

Posted on July 3, 2014 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

While at the HFMA ANI conference in Las Vegas, I talked to a lot of people about the future of healthcare reimbursement. Talk of ICD-10 and the ICD-10 delay came up regularly with most of us rolling our eyes that ICD-10 was delayed again. Some argued that we still need to be prepared, but from what I’m seeing the majority of the market just pushed their plans out a year and will pick them up again later this year or early next year.

With that said, we all agreed that every organization will be much more hesitant preparing for ICD-10 next year since they’re afraid that ICD-10 will just be delayed again.

As I had these discussions, I started thinking about what will be different in 2015 when it comes to ICD-10? As I asked people this question, all of the same arguments that we made in 2014 are what we’re going to have in 2015. Some of them include: the rest of the world adopted this years ago, we’re falling behind on the data we’re capturing, we need more specificity in the way we code so we can improve healthcare, etc etc etc.

Considering these arguments, what will be different next year?

All of the above arguments for not delaying ICD-10 were valid in 2014 and we’ll be just as valid in 2015. Can you think of any reasons that we should not delay ICD-10 in 2015 that weren’t reasons in 2014? I can’t think of any. The closest I’ve come is that with the extra year, we’re better prepared for ICD-10. Although, given people’s propensity to delay, does anyone think we’ll be much better prepared for ICD-10 in 2015 than we were in 2014? In some ways I think we’ll be less prepared because many will likely think the delay will happen again.

Given that the environment will be mostly the same, why wouldn’t we think that ICD-10 will be delayed again in 2015?

Personally, I’ll be watching CMS and HHS closely and see what they say. I think this year they looked really bad when they very publicly proclaimed that ICD-10 was coming at HIMSS just to be hit from the side by the ICD-10 delay. I’d hope that this time CMS will work with Congress to know what they’re planning or thinking before they make such strong assertions. Of course, this would mean that they’d have to understand what Congress is thinking (not an easy task).

What’s unfortunate is that many of the things you need to do to prepare for ICD-10 can also benefit you under ICD-9. The smart organizations understand this and are focusing on clinical documentation improvement (CDI) as the best way to prepare for ICD-10, but still benefit from the program today.

Outfitting for the ICD-10 Voyage – Breakaway Thinking

Posted on November 19, 2013 I Written By

The following is a guest blog post by Laura Speek from The Breakaway Group (A Xerox Company) and Honora Roberts from Xerox. Check out all of the blog posts in the Breakaway Thinking series.
ICD-10 Boat
These are challenging times for healthcare providers in every imaginable vessel – and the whitewater ride is not over yet. Just around the bend looms the transition to ICD-10, scheduled for October 1, 2014. Most providers know the wisest course is to start preparing now, yet few have dared to navigate these uncharted waters.

For many, a major problem is not knowing where to start. Others may be suffering from protracted procrastination. And still others may be well on the road to ruin via the path of good intentions.

An effective way to put some wind in your ICD-10 sails is to get real about the serious costs of noncompliance. After October 1, 2014, claims must be submitted using ICD-10 coding to be eligible for reimbursement. In other words, if you don’t bill with ICD-10 codes, you simply won’t get paid. And that’s the cold, hard truth.

The transition to ICD-10 will affect every facet of healthcare, but it begins with understanding the basic differences between ICD-9 and ICD-10. First and foremost, ICD-10 is not just a simple expansion of ICD-9. There is no reliable one-to-one mapping system. Some ICD-9 codes equate to multiple ICD-10 codes, while some do not correspond to any.

ICD-10 codes include much greater specificity; care providers must document etiology, laterality, exact anatomical site, and other information. Patient encounter documentation must include proper detail to enable coders to locate the correct ICD-10 diagnosis and procedure codes. Physicians and mid-level providers should begin to assess their documentation today to identify where ICD-10 coding requirements are already being met and where improvement is needed.

Because clinical documentation is at the core of every patient encounter, it must be complete, precise, and accurately reflect the scope of care and services provided. Assuring depth and consistency of documentation represents a challenge for many organizations.

ICD-10 encompasses a huge increase in accessible codes. The ICD-10-CM diagnostic code set, used in all healthcare settings, increases from roughly 13,000 to 68,000 codes. The ICD-10-PCS procedural code set, used within inpatient settings only, expands from roughly 3,000 to 87,000 codes. It should be noted that ambulatory settings will continue to use CPT (Current Procedural Terminology) procedural codes.

Given this massive growth in coding scope, the importance of detailed clinical documentation becomes even more pronounced. Physicians and other healthcare providers typically are not trained to develop proper documentation skills in medical school or residency; nurse practitioners (NPs) and physician assistants (PAs) generally do not receive such training during graduate school or clinical rotations. Hospitals and healthcare systems need to compensate for this training deficiency by instituting educational programs and tools that align healthcare providers with proper documentation practices to clear the decks for successful transition to ICD-10.

ICD-10 requires physicians, NPs, and PAs to thoroughly document each and every patient encounter to a much greater level of specificity than is needed in ICD-9. Nonspecific or incomplete documentation within ICD-10 will cause delays, claim denials, cash-flow interruptions, and inaccurate quality reporting. Definition and terminology changes inherent in ICD-10, particularly for surgical procedures, will also require focused education and training.

At the end of the day, providers aren’t coders. They are far less concerned with ICD-10 codes than they are with improving quality of care. This is where ICD-10 can be viewed as a welcoming beacon on a rocky shore. It gives healthcare providers an incentive to establish a clinical documentation improvement (CDI) program. In fact, implementing and sustaining an effective CDI initiative should be a top priority for all healthcare organizations preparing for ICD-10. For those with no CDI program in place, the time to begin is now. Consider improved clinical documentation as essential equipment for maneuvering through the twists, turns, and churns that accompany the voyage to ICD-10.

Honora Roberts - Xerox
Honora Roberts is Vice President of Healthcare Provider Services at Xerox.

Laura Speek  - The Breakaway Group
Laura Speek is a Learning and Development Specialist at The Breakaway Group (a Xerox company).

Xerox is a sponsor of the Breakaway Thinking series of blog posts.

For Providers, Revenue Assurance through the ICD-10 Transition is Key

Posted on July 16, 2013 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

The following is a guest blog post by Vik Anantha, Vice President – Financial Management Solutions, Edifecs, Inc.
Anantha Vik - Edifecs
We all know ICD-10 is a complex and costly initiative. One of the promises of ICD-10 is the potential for enhanced granularity, laterality and overall reporting accuracy. This is particularly important to providers because health plans use the ICD code set to determine reimbursements based on the medical condition of the patient and procedure(s) used for treatment.

With promise comes risk. ICD-10 not only exponentially increases the number of diagnostic and procedure codes, it changes the structure of the coding scheme and introduces new clinical concepts, terminology and granularity. These widespread changes will force business process and policy changes in areas such as benefits, medical management, and payer contracting. In other words, ICD-10 will affect almost every operational, clinical and financial process.

On the business side of ICD-10, revenue neutrality is a big concern for healthcare CFOs and revenue cycle management leaders. While it’s unrealistic to expect revenue neutrality at a claim level (there will always be some variation), it’s entirely possible to achieve revenue neutrality in aggregate. And this should be the goal.

It won’t be easy. Improper and incomplete coding can increase denial rates, causing significant revenue loss. Even error-free claims hold financial risk, particularly for healthcare organizations that depend on DRG (diagnosis-related group) methodology for reimbursement. The process of mapping ICD-9 codes to their counterparts in ICD-10 can be very complex, and there is often no single, one-to-one relationship.

The DRG for a certain claim is selected based on the ICD code(s) present on the patient claim. Therefore, the reimbursement on every claim depends on the assignment of diagnosis codes and inpatient procedure codes to specific DRGs.: As a result, migration to ICD-10 could result in significant over- or underpayment when using DRG-based reimbursement if providers use the wrong code.

Here are a few real-world examples:

  • ICD-9 procedure code 38.12 (extirpations of upper arteries with an open approach) is grouped to DRG 039. The same procedure in ICD-10 has 31 mapping options. Thirteen of these map to the same DRG and will generate the same reimbursement. However, the remaining 18 ICD-10 codes group to DRG 027, which generates a higher reimbursement. Selecting one ICD-10 code over another could result in nearly a 100% payment increase ($5,927.14 for DRG 039 vs. $12,409.74 for DRG 027.)
  • ICD-9 procedure code 2754 (repair of cleft lip) groups to DRG 134. This procedure has six potential ICD-10 codes, all of which group to a lower-weighted DRG 138, which represents a more generic procedure. This could reduce reimbursement by approximately $1,000 ($5,269.34 for DRG 134 vs. $4,203.28 for DRG 138.)
  • ICD-9 diagnosis code 86.01 (traumatic pneumothorax with open wound into thorax) is grouped to DRG 201. In ICD-10, this claim maps to a combination of two ICD-10 codes. Together, the two codes group to DRG 199, which increases reimbursement by 276% ($3,910.60 for DRG 201 vs. $10,816.98 for DRG 199.)

These examples show that payment variation under ICD-10 can cut both ways. If a provider organization can’t quantify its risks, it may end up dealing with unfavorable payer contracts, longer collection cycles and uncertain financials.

Of course, this type of analysis can be very time- and labor-intensive. Providers and payers should work together to identify and prioritize areas of risk, based on actual historical data. Analyzing a provider’s own data based on reality-based ICD-9 to ICD-10 mapping scenarios delivers the “street-level view” of the real operational and financial risks posed by ICD-10 to the organization, rather than just a list of every possible risk.

Many providers already have clinical documentation improvement (CDI) initiatives underway, and coding improvements made by these teams can be a key part of the financial analysis as well. The CDI process will narrow the number of ICD-10 codes to those the provider will actually use, which can then be used to build financial modeling maps specific to that provider, rather than using generic maps such as GEMs.

Providers looking to ensure consistent revenue cycle management through the ICD-10 transition should take the following steps:

  • Identify high-level risks at the outset, using historical data
  • Integrate with physician/clinical/coding training and CDI efforts
  • Refine analysis and prioritize risk with refined, “reality-based” mapping
  • Iterate, validate and improve to allocate resources based on real risk
  • Test and transition with highest possible degree of confidence

ICD-10 does hold promise for the healthcare industry. The transition period is likely to be bumpy and somewhat painful. But with some foresight and commitment to working with each other, providers and payers can assure themselves of financial neutrality in both directions.