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!!

Has Amazon Brought Something New To Healthcare Data Analytics?

Posted on November 29, 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.

Amazon’s announcement that it was getting into healthcare data analytics didn’t come as a major surprise. It was just a matter of time.

After all, the retail giant has been making noises about its health IT ambitions for a while now, and its super-sneaky 1492 team’s healthcare feints have become common knowledge.

Now, news has broken that its massive hosting division, Amazon Web Services, is offering its Comprehend Medical platform to the healthcare world. And at the risk of being a bit too flip, my reaction is “so?” I think we should all take a breath before we look at this in apocalyptic terms.

First, what does Amazon say we’re looking at here?

Like similar products targeting niches like travel booking and supply-chain management, the company reports, Comprehend Medical uses natural language processing and machine learning to pull together relevant information from unstructured text.

Amazon says Comprehend Medical can pull needed information from physician notes, patient health records and clinical trial reports, tapping into data on patient conditions and medication dosage, strength and frequency.

The e-retailer says that users can access the platform through a straightforward API call, accessing Amazon’s machine learning expertise without having to do their own development or train models of their own. Use cases it suggests include medical cohort analysis, clinical decision support and improving medical coding to tighten up revenue cycle management.

Comprehend Medical customers will be charged a fee each month based on the amount of text they process each month, either $0.01 per 100-character unit for the NERe API, which extracts entities, entity relationships, entity traits and PHI, or $0.0014 per unit if they use its PHId API, which only supports identifying PHI for data protection.

All good. All fine. Making machine learning capabilities available in a one-off hosting deal — with a vendor many providers already use — can’t be wrong.

Now, let’s look coldly at what Amazon can realistically deliver.

Make no mistake, I understand why people are excited about this announcement. As with Microsoft, Google, Apple and other top tech influencers, Amazon is potentially in the position to change the way things work in the health IT sector. It has all-star brainpower, the experience with diving into new industries and enough capital to buy a second planet for its headquarters. In other words, it could in theory change the healthcare world.

On the other hand, there’s a reason why even IBM’s Watson Health stumbled when it attempted to solve the data analytics puzzle for oncologist. Remember, we’re talking IBM here, the last bastion of corporate power. Also, bear in mind that other insanely well-capitalized, globally-recognized Silicon Valley firms are still biding their time when it comes to this stuff.

Finally, consider that many researchers think NLP is only just beginning to find its place in healthcare, and an uncertain one at that, and that machine learning models are still in their early stages, and you see where I’m headed.

Bottom line, if Google or Microsoft or Epic or Salesforce or Cerner haven’t been able to pull this off yet, I’m skeptical that Amazon has somehow pole-vaulted to the front of the line when it comes to NLP-based mining of medical text. My guess is that this product launch announcement is genuine, but was really issued more as a stake in the ground. Definitely something I would do if I worked there.

Providers Tell KLAS That Existing EMRs Can’t Handle Genomic Medicine

Posted on November 26, 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.

Providers are still in the early stages of applying genomics to patient care. However, at least among providers that can afford the investment, clinical genomics programs are beginning to become far more common, and as a result, we’re beginning to get a sense of what’s involved.

Apparently, one of those things might be creating a new IT infrastructure which bypasses the provider’s existing EMR to support genomics data management.

KLAS recently spoke with a number of providers about the vendors and technologies they were using to implement precision medicine. Along the way, they were able to gather some information on the best practices of the providers which can be used to roll out their own programs.

In its report, “Precision Medicine Provider Validations 2018,”  KLAS researchers assert that while precision medicine tools have become increasingly common in oncology settings, they can be useful in many other settings.

Which vendors they should consider depends on what their organization’s precision medicine objectives are, according to one VP interviewed by the research firm. “Organizations need to consider whether they want to target a specific area or expand the solutions holistically,” the VP said. “They [also] need to consider whether they will have transactional relationships with vendors or strategic partnerships.”

Another provider executive suggests that investing in specialty technology might be a good idea. “Precision medicine should really exist outside of EMRs,” one provider president/CEO told KLAS. “We should just use software that comes organically with precision medicine and then integrated with an EMR later.”

At the same time, however, don’t expect any vendor to offer you everything you need for precision medicine, a CMO advised. “We can’t build a one-size-fits-all solution because it becomes reduced to meaninglessness,” the CMO told KLAS. “A hospital CEO thinks about different things than an oncologist.”

Be prepared for a complicated data sharing and standardization process. “We are trying to standardize the genomics data on many different people in our organization so that we can speak a common language and archive data in a common system,” another CMO noted.

At the same time, though, make sure you gather plenty of clinical data with an eye to the future, suggests one clinical researcher. “There are always new drugs and new targets, and if we can’t test patients for them now, we won’t catch things later,” the researcher said.

Finally, and this will be a big surprise, brace yourself for massive data storage demands. “Every year, I have to go back to our IT group and tell them that I need another 400 terabytes,” one LIS manager told the research firm.” When we are starting to deal with 400 terabytes here and 400 terabytes there, we’re looking at potentially petabytes of storage after a very short period of time.”

If you’re like me, the suggestion that providers need to build a separate infrastructure outside the EMR to create precision medicine program is pretty surprising, but it seems to be the consensus that this is the case. Almost three-quarters of providers interviewed by KLAS said they don’t believe that their EMR will have a primary role in the future of precision medicine, with many suggesting that the EMR vendor won’t be viable going forward as a result.

I doubt that this will be an issue in the near term, as the barriers to creating a genomics program are high, especially the capital requirements. However, if I were Epic or Cerner, I’d take this warning seriously. While I doubt that every provider will manage their own genomics program directly, precision medicine will be part of all care at some point and is already having an influence on how a growing number of conditions are treated.

Healthcare Interoperability is a Joke

Posted on November 20, 2018 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.

Did you see the big news last month about healthcare interoperability? That’s right, Carequality announced support for FHIR. Next thing you know, we’re going to get an announcement that CommonWell is going to support faxing.

Seriously, healthcare interoperability is a joke.

The reality is that no EHR vendor wants to do interoperability. And it’s not saying anything groundbreaking to say that Carequality and CommonWell are both driven by the EHR vendors. Unfortunately, I see these organizations as almost a smokescreen that allows EHR vendors to not be interoperable while allowing them to say that they’re working on interoperability.

I’d describe current interoperability efforts as a “just enough” approach to interoperability. EHR vendors want to do just enough to appease the call for interoperability by the government and other patient organizations. It’s not a real effort to be interoperable. That’s most EHR vendors. A few of them are even using interoperability as a weapon to keep vendors out and some are looking at interoperability as a new business model.

Just to be clear, I’m not necessarily blaming the EHR vendors. They’re doing what their customers are asking them to do which is their highest priority. Until their customers ask for interoperability, it’s not going to happen. And in many respects, their customers don’t want interoperability. That’s been the real problem with interoperability since the start and it’s why grand visions of interoperability are unlikely to happen. Micro interoperability, which is how I’d describe what’s happening today, will happen and is happening.

If EHR vendors really cared about being interoperable, they’d spend the time to see where interoperability would lower costs, improve care, and provide a better patient experience. That turns out to be a lot of places. Then, they’d figure out how to make that possible and still secure and safe. Instead, they don’t really do this. The EHR vendors just follow whatever industry standard is out there so they can say they’re working on interoperability. Ironically, many experts say that the industry standards aren’t standard and won’t really make a big impact on interoperability.

There are no leaders in healthcare interoperability. There are just followers of the “just enough” crowd.

Let’s just be honest about what’s really possible when it comes to EHR vendors and healthcare interoperability. There is some point to point use cases that are really valuable and happening (this feels like what FHIR is doing to me). In a large health system, we’re seeing some progress on interoperability within the organization. We’re starting to see inklings of EHR vendors opening up to third-party providers, but that still has a long ways to go. Otherwise, we’re exchanging CCDs, faxes, and lab results.

Will we see anything more beyond this from EHR vendors? I’m skeptical. Let me know what you think in the comments on on Twitter with @HealthcareScene.

Scripps Research Translational Institute Partners To Develop AI Applications

Posted on November 2, 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.

The Scripps Research Translational Institute has agreed to work with graphics processing unit-maker NVIDIA to support the development of AI applications. The partners plan to forge AI and deep learning best practices, tools and infrastructure tailored to supporting the AI application development process.

In collaboration with NVIDIA, Scripps will establish a center of excellence for artificial intelligence in genomics and digital sensors. According to Dr. Eric Topol, the Institute’s founder and director, AI should eventually improve accuracy, efficiency, and workflow in medical practices. This is especially true of the data inputs from sensors and sequencing, he said in an NVIDIA blog item on the subject.

Scripps is already a member of a unique data-driven effort known as the “All of Us Research Program,” which is led by the National Institutes of Health. This program, which collects data on more than 1 million US participants, looks at the intersection of biology, genetics, environment, data science, and computation. If successful, this research will expand the range of conditions that can be treated using precision medicine techniques.

NVIDIA, for its part, is positioned to play an important part in the initial wave of AI application rollouts. The company is a leader in producing performance chipsets popular with those who play high-end, processor-intensive gaming which it has recently applied to other processor intensive projects like blockchain. It now hopes its technology will form the core of systems designed to crunch the high volumes of data used in AI projects.

If NVIDIA can provide hardware that makes high-volume number-crunching less expensive and more efficient, it could establish an early lead in what is likely to be a very lucrative market. Given its focus on graphics processing, the hardware giant could be especially well-suited to dominate rapidly-emerging radiology AI applications.

We can certainly expect to see more partnerships like this file into place over the next year or two. Few if any IT vendors have enough scientific expertise in-house to make important gains in biotech AI, and few providers have enough excess IT talent available to leverage discoveries and data in this arena.

It will be interesting to see what AI applications development approaches emerge from such partnerships. Right now, much AI development and integration is being done on a one-off basis, but it’s likely these projects will become more systematized soon.

Will UnitedHealth’s New Personal Health Record Make An Impact?

Posted on October 26, 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.

Though the idea of a personal health record was a hot thing for a while, it didn’t become the fixture of the healthcare market that pundits had predicted. In fact, as many readers will recall, even deep pockets like Google and Microsoft couldn’t get their users to sign on to their PHRs en masse.

One of the main reasons the PHR model didn’t take is that people simply didn’t want to use them. In fact, at least at the time, the PHR was almost entirely a solution in search of a problem. After all, if a health data power user and patient advocate like myself didn’t want one, what hope did PHR backers have of interesting your average Joe Blow in aggregating their health data online?

Over time, however, the personal health data landscape has changed, with patient records becoming a bit more portable. While consumers still aren’t beating down the doors to get their own PHR, those who are interested in pulling together their medical records electronically have better access to their history.

Not only that, wearables makers like Apple and Fitbit are sweetening the pot, primarily by helping people pull self-generated data into their health record. Arguably, patient-generated data may not be as valuable as traditional records just yet, but consumers are likely to find it more interesting than the jargon-laden text found in provider records.

Given recent developments like these, I wasn’t entirely surprised to learn that UnitedHealth Group is picking up the PHR torch. According to an article in MedCity News, the giant payer plans to launch what sounds like an updated PHR platform next year to its 50 million benefited plan members.

Apparently, on an earnings call last week UnitedHealth CEO Dave Wichmann said that the company will launch a “fully integrated and fully portable individual health record” in 2019. Notably, this is not just a data repository, but rather an interactive tool that “delivers personalized next-best health actions to people and their caregivers.”

The new health record will be based on UnitedHealth’s Rally health and wellness platform, which the insurer picked up when it acquired Audax Health in 2014. The platform, which has 20 million registered users, works to influence members to perform healthy behaviors in exchange for the incentive dollars,

Over time, Wichmann said, UHG intends to build Rally into a platform which collects and distributes “deeply personalized” health information to individual members, MedCity reported. The idea behind this effort is to highlight gaps in care and help patients assess the care that they get.  Wichmann told earnings call listeners that the platform data will be packaged and presented to clinicians in a form similar to that used by existing EHRs.

UHG’s plans here are certainly worth keeping an eye on over the next year or two. I have no doubt that the nation’s largest commercial payer has some idea of how to format data and make it digestible by systems like Cerner and Epic.

But while patients have become a bit more familiar with the benefits of having their health data on hand, we’re not exactly seeing consumers stampede the providers demanding their own health record either, and I’m far from convinced that this effort will win new converts.

My skepticism comes partly from first-hand experience. As a recent UnitedHealth beneficiary, I’ve used the Rally application, and I didn’t find it all that motivating. Honestly, I doubt any online platform will make much of an impact on patient health on its own, as the reasons for many health issues are multifactorial and can’t be resolved by handing one of us a few Rally bucks.

Personal gripes aside, though, the bigger question remains whether consumers think they’ll get something valuable out of using the new UHG tool. As always, you can never count on them coming just because you built it.

AMA Releases Great Guide To Digital Health Implementation

Posted on October 25, 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.

In the past, I’ve been pretty hard on the AMA when it comes to digital health. Last year I gave the organization a particularly hard time when it rolled out its Physician Innovation Network platform, which is designed to help physicians network directly with health tech firms, as it seemed to be breaking little to no ground.

However, to be fair the AMA has been a relatively quiet but solid presence in health IT for quite some time.  Its health IT efforts include cofounding Health2047, which brings together doctors with established health IT companies to help the companies launch services and products, serving as one of four organizations behind mHealth app standards venture Xcertia and managing a student-run biotechnology incubator in collaboration with Sling Health.

But what it hasn’t done so far, at least to date, has been to offer physicians any hands-on guidance on using emerging health IT. Now, at long last, the AMA has taken the plunge, releasing a guide focused on helping physicians roll out digital health technology in their practice. At least this time around, I have to give the organization a high five.

The new guide takes a lifecycle perspective, helping practices work through the digital health implementation process from preparations to rollout to gathering data on the impact of the new technology. In other words, it lays out the process as a feedback loop rather than a discrete event in time, which is smart. And its approach to explaining each step is concise and clean.

One section identifies six straightforward steps for choosing a digital health technology, including identifying a need, defining success early on in the process, making the case for political and financial buy-in, forming the team, evaluating the vendor and executing the vendor contract.

Along the way, it makes the important but often-neglected point that the search should begin by looking at the practice’s challenges, including inefficiencies, staff pain points or patient health and satisfaction problems. “The focus on need will help you avoid the temptation to experiment with new technologies that ultimately will result in tangible improvements,” the guide notes.

Another offers advice on tackling more immediate implementation issues, including steps like designing workflows, preparing the care team and partnering with the patient. This section of the report differs from many of its peers by offering great advice on building workflow around remote patient monitoring-specific requirements, including handling device management, overseeing patient enrollment and interactions, and assuring that coding and billing for remote patient management activities is correct and properly documented.

The guide also walks practices through the stages of final implementation, including the nature of the rollout itself, evaluating the success of the project and scaling up as appropriate. I was particularly impressed by its section on scaling up, given that most of the advice one sees on this subject is generally aimed at giant enterprises rather than typically smaller medical practices. In other words, it’s not that the section said anything astonishing, but rather that it existed at all.

All told, it’s great to see the AMA flexing some of the knowledge it’s always had, particularly given that the report is available at no cost to anyone. Let’s hope to see more of this in the future.

Is FHIR Adoption At A Turning Point, Or Is This Just More Hype?

Posted on October 8, 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.

Over the last few years, healthcare industry players have continued to experiment with the use of HL7 FHIR to solve key interoperability problems.

Perhaps the most recent efforts to do so is the Da Vinci Project, which brings together a group of payers, health IT vendors, and providers dedicated to fostering value-based care with FHIR. The group has begun work on two test cases, one addressing 30-day medication reconciliation and the other coverage requirements discovery.

This wasn’t big news, as it doesn’t seem to be doing anything that new. In fact, few if any of these projects — of which there have been many — have come close to establishing FHIR firmly established as a standard, much less fostering major change in the healthcare industry.

Now, a new analysis by the ONC suggests that we may finally be on the verge of a FHIR breakthrough.

According to ONC’s research, which looked at how health IT developers used FHIR to meet 2015 Edition certification requirements, roughly 32% of the health IT developers certified are using FHIR Release 2, and nearly 51% of health IT developers seem to be using a version of FHIR combined with OAuth 2.0.

While this may not sound very impressive (and at first glance, it didn’t to me), the certified products issued by the top 10 certified health IT developers serve about 82% of hospitals and 64% of clinicians.

Not only that, big tech companies staking out an expanded position in healthcare are leveraging FHIR 2, the ONC notes. For example, Apple is using a FHIR-based client app as part of its healthcare deployment.  Amazon, Alphabet, and Microsoft are working to establish themselves in the healthcare industry as well, and it seems likely that FHIR-based interoperability will come to play a part in their efforts.

In addition, CMS has shown faith in FHIR as well, investing in FHIR through its Blue Button 2.0,  a standards-based API allowing Medicare beneficiaries to connect their claims data to applications, services, and research programs.

That being said, after citing this progress, the agency concedes that FHIR still has a way to go, from standards development implementation, before it becomes the lingua franca of the industry. In other words, ONC’s definition of “turning point” may be a little different than yours or mine. Have I missed something here?

Look, I don’t like being “that guy,” but how encouraging is this really? By my standards at least, FHIR uptake is relatively modest for such a hot idea. For example, compare FHIR adoption of AI technology or blockchain. In some ways, interoperability may be a harder “get” than blockchain or AI in some ways, but one would think it would be further along if it were completely practical. Maybe I’m just a cynic.

Number Of Health Data Breaches Grew Steadily Over Last Several Years

Posted on October 5, 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.

New research has found that while the number of patient records exposed per breach has varied widely, the number of health data breaches reported grew substantially between 2010 and 2017.

The study, which was conducted by researchers with Massachusetts General Hospital, was published in JAMA. Its aim was to look at the changes in data breach patterns as EHRs have come into wider use.

The authors analyzed 2,149 reported breaches over the previous seven years. The number of records breached for incident varied from 500 to almost 79 million patient records.

Researchers behind the study put breaches reported in three categories: those taking place at healthcare provider sites, within health plans, and at business associate locations.

One thing that stuck out from among the data points was that over that seven-year period, the number of breaches increased from 199 the first year to 344 in 2017. During that period, the only year that did not see an increase in incident volume was 2015.

Another notable if unsurprising conclusion drawn by the researchers was that while 70% of all breaches took place within provider organizations, incidents involving health plans accounted for 63% of all breached records.

Overall, the greatest number of patient records breached was due to compromised network servers or email messages. However, the top reasons for breaches have varied from year-to-year, the analysis found.

For example, the most common type of breach reported in 2010 was theft of physical records. The most commonly breached type of media that year was laptop computer data storage, followed by paper and film records.

Meanwhile, by 2017 data hacking or other information technology incidents accounted for the largest number of breaches, followed by unauthorized access to or disclosure of patient data. In addition, a large number of breaches could be attributed to compromised network servers or email messages.

The number of patient records exposed differed depending on what media was breached. For example, while the total of 510 breaches of paper and film records impact about 3.4 million patient records, 410 breaches of network servers affected nearly 140 million records.

Patient Billing And Collections Process Needs A Tune-Up

Posted on October 1, 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.

A new study from a patient payments vendor suggests that many healthcare organizations haven’t optimized their patient billing and collections process, a vulnerability which has persisted despite their efforts to crack the problem.

The survey found that while the entire billing collections process was flawed, respondents said that collecting patient payments was the toughest problem, followed by the need to deploy better tools and technologies.

Another issue was the nature of their collections efforts. Sixty percent of responding organizations use collections agencies, an approach which can establish an adversarial relationship between patient and provider and perhaps drive consumers elsewhere.

Yet another concern was long delays in issuing bills to patients. The survey found that 65% of organizations average more than 60 days to collect patient payments, and 40% waited on payments for more than 90 days.

These results align other studies that look at patient payments, all of which echo the notion that the patient collection process is far from what it should be.

For example, a study by payment services vendor InstaMed found that more than 90% of consumers would like to know what the payment responsibility is prior to a provider visit. Worse, very few consumers even know what the deductible, co-insurance and out-of-pocket maximums are, making it more likely that the will be hit with a bill they can’t afford.

As with the Cedar study, InstaMed’s research found that providers are waiting a long time to collect patient payments, three-quarters of organizations waiting a month to close out patient balances.

Not only that, investments in revenue cycle management technology aren’t necessarily enough to kickstart patient payment volumes. A survey done last year by the Healthcare Financial Management Association and vendor Navigant found that while three-quarters of hospitals said that their RCM technology budget was increasing, they weren’t necessarily getting the ROI they’d hoped to see.

According to the survey, 77% of hospitals less than 100 beds and 78% of hospitals with 100 to 500 beds planned to increase their RCM spending. Their areas of investment included business intelligence analytics, EHR-enabled workflow or reporting, revenue integrity, coding and physician/clinician documentation options.

Still, process improvements seem to have had a bigger payoff. These hospitals are placing a lot of faith in revenue integrity programs, with 22% saying that revenue integrity was a top RCM focus area for this year. Those who would already put such a program in place said that it offered significant benefits, including increased net collections (68%), greater charge capture (61%) and reduced compliance risks (61%).

As I see it, the key takeaways here are that making sure patients know what to expect financially and putting programs in place to improve internal processes can have a big impact on patient payments. Still, with consumers financing a lot of their care these days, getting their dollars in the door should continue to be an issue. After all, you can’t get blood from a stone.

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.