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!!

AMIA Asks NIH To Push For Research Data Sharing

Posted on January 23, 2017 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 American Medical Informatics Association has is urging leaders at the NIH to take researchers’ data sharing plans into account when considering grant proposals.

AMIA is responding to an NIH Request for Information (topic: “Strategies for NIH Data Management, Sharing and Citation”) was published in November 2016. In the RFI, it asked for feedback on how digital scientific data generated by NIH-funded research should be managed and disclosed to the public. It also asked for input on how to set standards for citing shared data and software.

In its response, AMIA said that the agency should give researchers “institutional incentives” designed to boost data sharing and strengthen data management. Specifically, the trade group suggested that NIH make data sharing plans a “scoreable” part of grant applications.

“Data sharing has become such an important proximal output of research that we believe the relative value of a proposed project should include consideration of how its data will be shared,” AMIA said in its NIH response. “By using the peer-review process, we will make incremental improvements to interoperability, while identifying approaches to better data sharing practices over time.”

To help the agency implement this change, AMIA recommended that applicants earmark funds for data curation and sharing as part of the grants’ direct costs. Doing so will help assure that data sharing becomes part of research ecosystems.

AMIA also recommends that NIH offer rewards to scholars who either create or contribute to publicly-available datasets and software. The trade group argues that such incentives would help those who create and analyze data advance their careers. (And this, your editor notes, would help foster a virtuous cycle in which data-oriented scientists are available to foster such efforts.)

Right now, to my knowledge, few big data integration projects include the kind of front-line research data we’re talking about here.  On the other hand, while few community hospitals are likely to benefit from research data in the near term, academic medical organizations are having a bit more luck, and offer us an attractive picture of how things could be.

For example, look at this project at Vanderbilt University Medical Center which collects and manages translational and clinical research data via an interface with its EMR system.

At Vanderbilt, research data collection is integrated with clinical EMR use. Doctors there use a module within the research platform (known as REDCap) to collect data for prospective clinical studies. Once they get their research project approved, clinicians use menus to map health record data fields to REDCap. Then, REDCap automatically retrieves health record data for selected patients.

My feeling is that if NIH starts pushing grantees to share data effectively, we’ll see more projects like REDCap, and in turn, better clinical care supported by such research. It looks to me like everybody wins here. So I hope the NIH takes AMIA’s proposal seriously.

E-Patient Update:  You Need Our Help

Posted on January 20, 2017 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.

I just read the results of a survey by Black Book Research suggesting that many typical consumers don’t trust, like or understand health IT.

The survey, which reached out to 12,090 adult consumers in September 2016, found that 57% of those interacting with health IT at hospitals or medical practices were skeptical of its benefit. Worse, 87% said they weren’t willing to share all of their information.

Up to 70% of consumers reported that they distrusted patient portals, medical apps and EMRs. Meanwhile, while many respondents said they were interested in using health trackers, 94% said that their physicians weren’t willing or able to synch wearables data with their EMR.

On the surface, these stats are discouraging. At a minimum, they suggest that getting patients and doctors on the same page about health IT continues to be an uphill battle. But there’s a powerful tactic providers can use which – to my knowledge – hasn’t been tried with consumers.

Introducing the consumer health IT champion

As you probably know, many providers have recruited physician or nurse “champions” to help their peers understand and adjust to EMRs. I’m sure this tactic hasn’t worked perfectly for everyone who’s tried it, but it seems to have an impact. And why not? Most people are far more comfortable learning something new from someone who understands their work and shares their concerns.

The thing is, few if any providers are taking the same approach in rolling out consumer health IT. But they certainly could. I’d bet that there’s at least a few patients in every population who like, use and understand consumer health technologies, as well as having at least a sense of why providers are adopting back-end technology like EMRs. And we know how to get Great-Aunt Mildred to consider wearing a FitBit or entering data into a portal.

So why not make us your health IT champions? After all, if you asked me to, say, hold a patient workshop explaining how I use these tools in my life, and why they matter, I’d jump at the chance. E-patients like myself are by our nature evangelists, and we’re happy to share our excitement if you give us a chance. Maybe you’d need to offer some HIT power users a stipend or a gift card, but I doubt it would take much to get one of us to share our interests.

It’s worth the effort

Of course, most people who read this will probably flinch a bit, as taking this on might seem like a big hassle. But consider the following:

  • Finding such people shouldn’t be too tough. For example, I talk about wearables, mobile health options and connected health often with my PCP, and my enthusiasm for them is a little hard to miss. I doubt I’m alone in this respect.
  • All it would take to get started is to get a few of us on board. Yes, providers may have to market such events to patients, offer them coffee and snacks when they attend, and perhaps spend time evaluating the results on the back end. But we’re not talking major investments here.
  • You can’t afford to have patients fear or reject IT categorically. As value-based care becomes the standard, you’ll need their cooperation to meet your goals, and that will almost certainly include access to patient-generated data from mobile apps and wearables. People like me can address their fears and demonstrate the benefits of these technologies without making them defensive.

I hope hospitals and medical practices take advantage of people like me soon. We’re waiting in the wings, and we truly want to see the public support health IT. Let’s work together!

Healthcare Industry Leads In Blockchain Deployment

Posted on January 19, 2017 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 by Deloitte concludes that healthcare and life sciences companies stand out as planning the most aggressive blockchain deployments of any industry. That being said, healthcare leaders are far from alone in paying close attention to blockchain, which seems to be coming into its own as corporate technology.

According to Deloitte, 39% of senior executives at large US companies had little or no knowledge of blockchain technology, but the other 61% reported their blockchain knowledge level as broad to expert. The execs who were well-informed about blockchain told Deloitte that it would be crucial for both their company and industry. In fact, 55% of the knowledgeable group said their company would be at a competitive disadvantage if they failed to adopt blockchain, and 42% believed it would disrupt their industry.

Given this level of enthusiasm, it’s not surprising that respondents have begun to invest in blockchain internally. Twenty-eight percent of respondents said their company had invested $5 million of more in blockchain tech to date, and 10% reported investing $10 million or more. Not only that,  25% of respondents expected to invest more than $5 million in blockchain technology this year.

While the level of blockchain interest seems to be pronounced across industries studied by Deloitte, healthcare and life science companies lead the pack when it came to deployment, with 35% of industry respondents saying that their company expects to put blockchain into production during 2017.

All that being said, aggressive deployment may or may not be a good thing just yet. According to research by cloud-based blockchain company Tierion, the majority of blockchain technology isn’t ready for deployment, though worthwhile experiments are underway.

Tierion argues that analysts and professional experts are overselling blockchain, and that most of blockchain technology is experimental and untested. Not only that, its research concludes that at least one healthcare application – giving patients the ability to manage their health data – is rather risky, as blockchain security is shaky.

It seems clear that health IT leaders will continue to explore blockchain options, given its tantalizing potential for sharing data securely and flexibly. And as the flurry of interest around ONC’s blockchain research challenge demonstrates, many industry thought leaders take this technology seriously. If the winning submissions are any indication, blockchain may support new approaches to health data interoperability, claims processing, medical records, physician-patient data sharing, data security, HIEs and even the growth of accountable care.

If nothing else, 2017 should see the development of some new and interesting healthcare blockchain applications, and probably the investment of record new amounts of capital to build them. In other words, whether blockchain is mature enough for real time deployment or not, it’s likely to offer an intriguing show.

FDA Weighs In On Medical Device Cybersecurity

Posted on January 5, 2017 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, medical devices lived in a separate world from standard health IT infrastructure, typically housed in a completely separate department. But today, of course, medical device management has become much more of an issue for health IT managers, given the extent to which such devices are being connected to the Internet and exposed to security breaches.

This has not been lost on the FDA, which has been looking at medical device security problems for a long time. And now – some would say “at long last” – the FDA has released final guidance on managing medical device cybersecurity. This follows the release of earlier final guidance on the subject released in October 2014.

While the FDA’s advice is aimed at device manufactures, rather than the health IT managers who read this blog, I think it’s good for HIT leaders to review. (After all, you still end up managing the end product!)

In the guidance, the FDA argues that the best way to bake cybersecurity protections into medical devices is for manufacturers to do so from the outset, through the entire product lifecycle:

Manufacturers should build in cybersecurity controls when they design and develop the device to assure proper device performance in the face of cyber threats, and then they should continuously monitor and address cybersecurity concerns once the device is on the market and being used by patients.

Specifically, the agency is recommending that manufacturers take the following steps:

  • Have a way to monitor and detect cybersecurity vulnerabilities in their devices
  • Know assess and detect the level of risk vulnerabilities pose to patient safety
  • Establish a process for working with cybersecurity researchers and other stakeholders to share information about possible vulnerabilities
  • Issue patches promptly, before they can be exploited

The FDA also deems it of “paramount” importance that manufacturers and stakeholders consider applying core NIST principles for improving critical infrastructure cybersecurity.

All of this sounds good. But considering the immensity of the medical device infrastructure – and the rate of its growth – don’t expect these guidelines to make much of an impact on the device cybersecurity problem.

After all, there are an estimated 10 million to 15 million medical devices in US hospitals today, according to health tech consultant Stephen Grimes, who spoke on biomedical device security at HIMSS ’16. Grimes, a past chair of the HIMSS Medical Device Security Task Force, notes that one 500-bed hospital could have 7,500 devices on board, most of which will be networked. And each networked monitor, infusion pump, ventilator, CT or MRI scanner could be vulnerable to attack.

Bottom line, we’re looking at some scary risks regardless of what manufacturers do next. After all, even if they do a much better job of securing their devices going forward, there’s a gigantic number of existing devices which can be hacked. And we haven’t even gotten into the vulnerabilities that can be exploited among home-based connected devices.

Don’t get me wrong, I’m glad to see the FDA stepping in here. But if you look at the big picture, it’s pretty clear that their guidance is clearly just a small step in a very long and complicated process.

Patient Engagement Platforms Are 2017’s Sexiest Tech

Posted on January 3, 2017 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 months, I’ve become convinced that the predictable star of 2017 — population health management — isn’t going to be as hot as people think.

Instead, I’d argue that the trend to watch is the emergence of new technologies that guide, reach out to and engage with patients at key moments in their care process. We’re at the start of a period of spectacular growth for patient engagement platforms, with one analyst firm predicting that the global market for these solutions will hit $34.94 billion by 2023.

We all seem to agree already that we need to foster patient engagement if we want to meet population health goals. But until recently, most of the approaches I’ve seen put in place are manual, laborious and resource-intensive. Yes, the patient portal is an exception to that rule – and seems to help patients and clinicians connect – but there’s only so much you can do with a portal interface. We need more powerful, flexible solutions if we hope to make a dent in the patient engagement problem.

In the coming year, I think we’ll see a growing number of providers adopt technology that helps them interact and engage with patients more effectively. I’m talking about initiatives like the rollout of technology by vendor HealthGrid at ColumbiaDoctors, a large multispecialty group affiliated with Columbia University Medical Center, which was announced last month.

While I haven’t used the technology first hand, it seems to offer the right functions, all available via mobile phone. These include pre- and post-visit communications, access to care information and a clinically-based rules engine which drives outreach regarding appointments, educations, medications and screening. That being said, HealthGrid definitely has some powerful competitors coming at the same problem, including the Salesforce.com Health Cloud.

Truth be told, it was probably inevitable that vendors would turn up to automate key patient outreach efforts. After all, unless providers boost their ability to target patients’ individual needs – ideally, without hiring lots of costly human care managers – they aren’t likely to do well under value-based payment schemes. One-off experiments with mobile apps or one-by-one interventions by nurse care coordinators simply don’t scale.

Of course, these technologies are probably pretty expensive right now – as new tech in an emerging market usually is — which will probably slow adoption somewhat. I admit that when I did a Google search on “patient engagement solutions,” I ran into a vendor touting a $399 a month option for doctors, which isn’t too bad if it can actually deliver. But enterprise solutions are likely to be a big investment, and also, call for a good deal of integration work. After all, if nothing else, health systems will want to connect patient engagement software to their back-office systems and EMR, at minimum, which is no joke.

Still, to my mind there’s little question that patient engagement technologies are going to be the sexiest health IT niche to watch in 2017, one which will generate major buzz in healthcare boardrooms across the country. Whether you invest or not, definitely watch this space.

CVS Launches Analytics-Based Diabetes Mgmt Program For PBMs

Posted on December 29, 2016 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.

CVS Health has launched a new diabetes management program for its pharmacy benefit management customers designed to improve diabetes outcomes through advanced analytics.  The new program will be available in early 2017.

The CVS program, Transform Diabetes Care, is designed to cut pharmacy and medical costs by improving diabetics’ medication adherence, A1C levels and health behaviors.

CVS is so confident that it can improve diabetics’ self-management that it’s guaranteeing that percentage increases in spending for antidiabetic meds will remain in the single digits – and apparently that’s pretty good. Or looked another way, CVS contends that its PBM clients could save anywhere from $3,000 to $5,000 per year for each member that improves their diabetes control.

To achieve these results, CVS is using analytics tools to find specific ways enrolled members can better care for themselves. The pharmacy giant is also using its Health Engagement Engine to find opportunities for personalized counseling with diabetics. The counseling sessions, driven by this technology, will be delivered at no charge to enrolled members, either in person at a CVS pharmacy location or via telephone.

Interestingly, members will also have access to diabetes visit at CVS’s Minute Clinics – at no out-of-pocket cost. I’ve seen few occasions where CVS seems to have really milked the existence of Minute Clinics for a broader purpose, and often wondered where the long-term value was in the commodity care they deliver. But this kind of approach makes sense.

Anyway, not surprisingly the program also includes a connected health component. Diabetics who participate in the program will be offered a connected glucometer, and when they use it, the device will share their blood glucose levels with a pharmacist-led team via a “health cloud.” (It might be good if CVS shared details on this — after all, calling it a health cloud is more than a little vague – but it appears that the idea is to make decentralized patient data sharing easy.) And of course, members have access to tools like medication refill reminders, plus the ability to refill a prescription via two-way texting, via the CVS Pharmacy.

Expect to see a lot more of this approach, which makes too much sense to ignore. In fact, CVS itself plans to launch a suite of “Transform Care” programs focused on managing expensive chronic conditions. I can only assume that its competitors will follow suit.

Meanwhile, I should note that while I expect to see providers launch similar efforts, so far I haven’t seen many attempts. That may be because patient engagement technology is relatively new, and probably pretty expensive too. Still, as value-based care becomes the dominant payment model, providers will need to get better at managing chronic diseases systematically. Perhaps, as the CVS effort unfolds, it can provide useful ideas to consider.

Connected Wearables Pose Growing Privacy, Security Risks

Posted on December 26, 2016 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, the healthcare industry treated wearables as irrelevant, distracting or worse. But over that last year or two, things have changed, with most health IT leaders concluding that wearables data has a place in their data strategies, at least in the aggregate.

The problem is, we’re making the transition to wearable data collection so quickly that some important privacy and security issues aren’t being addressed, according to a new report by American University and the Center for Digital Democracy. The report, Health Wearable Devices in the Big Data Era: Ensuring Privacy, Security, and Consumer Protection, concludes that the “weak and fragmented” patchwork of state and federal health privacy regulations doesn’t really address the problems created by wearables.

The researchers note that as smart watches, wearable health trackers, sensor-laden clothing and other monitoring technology get connected and sucked into the health data pool, the data is going places the users might not have expected. And they see this as a bit sinister. From the accompanying press release:

Many of these devices are already being integrated into a growing Big Data digital health and marketing ecosystem, which is focused on gathering and monetizing personal and health data in order to influence consumer behavior.”

According to the authors, it’s high time to develop a comprehensive approach to health privacy and consumer protection, given the increasing importance of Big Data and the Internet of Things. If safeguards aren’t put in place, patients could face serious privacy and security risks, including “discrimination and other harms,” according to American University professor Kathryn Montgomery.

If regulators don’t act quickly, they could miss a critical window of opportunity, she suggested. “The connected health system is still in an early, fluid stage of development,” Montgomery said in a prepared statement. “There is an urgent need to build meaningful, effective, and enforceable safeguards into its foundation.”

The researchers also offer guidance for policymakers who are ready to take up this challenge. They include creating clear, enforceable standards for both collection and use of information; formal processes for assessing the benefits and risks of data use; and stronger regulation of direct-to-consumer marketing by pharmas.

Now readers, I imagine some of you are feeling that I’m pointing all of this out to the wrong audience. And yes, there’s little doubt that the researchers are most worried about consumer marketing practices that fall far outside of your scope.

That being said, just because providers have different motives than the pharmas when they collect data – largely to better treat health problems or improve health behavior – doesn’t mean that you aren’t going to make mistakes here. If nothing else, the line between leveraging data to help people and using it to get your way is clearer in theory than in practice.

You may think that you’d never do anything unethical or violate anyone’s privacy, and maybe that’s true, but it doesn’t hurt to consider possible harms that can occur from collecting a massive pool of data. Nobody can afford to get complacent about the downside privacy and security risks involved. Plus, don’t think the nefarious and somewhat nefarious healthcare data aggregators aren’t coming after provider stored health data as well.

Are We Waiting For An Interoperability Miracle?

Posted on December 12, 2016 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.

Today, in reading over some industry news, my eyes settled on an advertising headline that gave me pause: “Is Middleware The Next Interoperability Miracle?”  Now, I have to admit a couple things: 1) that vendors have to pitch the latest white paper with all the fervor they can command, and 2) that it never hurts to provoke conversation with a strong assertion. But seeing a professional advertisement include the word “miracle” — an expostulatory term which you might use to sell dishwashers — still took me back a bit.

And then I began to think about what I had seen. I wondered whether it will really take a miracle to achieve health data interoperability sometime in our lifetime. I asked myself whether health IT insiders like you, dear readers, are actually that discouraged. And I wondered if any vendor truly believes that they can produce such a miracle, if indeed one is needed.

First, let’s ask ourselves about whether we need a Hail Mary pass or even a miracle to salvage industry hopes for data interoperability. I’m afraid that in my view, the answer is quite possibly yes. In saying this, I’m assuming that interoperability must arrive soon to meet our current needs, at least within the next several years.

Unfortunately, nothing I’ve seen suggests that we can realistically achieve robust interoperability within the next say, 5 to 10 years, despite all appearances to the contrary. I know some readers may disagree with me, but as I see it the combination of technical and behavioral obstacles to interoperability are just too profound to be addressed in a timely manner.

Okay, then, on to whether health IT rank and file are so burned out on interoperability efforts that they just want the problem taken off of their hands. If they did, I would certainly sympathize, as the forces in play here are beyond the control of any individual IT staffer, consultant, hospital or health system. The forces holding back interoperability are interwoven with technical, financial, policy and operational issues which can’t be addressed without a high level of cooperation between competing entities — and perhaps not even then.

So, back to where we started. Headline aside, does the vendor in question or any other truly believe that they can engineer a solution to such an intractable problem, conquer world interoperability issues and grow richer than Scrooge McDuck? Probably not. Interoperability is a set of behaviors as much as a technology, and I doubt even the cockiest startup thinks it can capture that many hearts and minds.

Ultimately, though, whoever wrote that headline is probably keying into something real. While the people doing the hard work of attempting health data sharing aren’t exactly desperate, I think there’s a growing sense that we’re running out of time to get this thing done. Obviously, other than artificial ones imposed by laws and regulations, we aren’t facing any actual deadline, but things can’t go on like this forever.

In fact, I’d argue that if we don’t create a useful interoperability model soon, a window of opportunity for doing so will be lost for quite some time. After all, we can’t keep spending on this infrastructure if it’s never going to offer a payback.

The cold reality is that eventually, the data sharing system we have — such as it is — will fall apart of its own weight, as organizations simply stop paying for their part of it. So while we might not need a miracle as such, being granted one wouldn’t hurt. If this effort fails us, who knows when we’ll have the time and money to try again.

What Would A Community Care Plan Look Like?

Posted on November 16, 2016 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.

Recently, I wrote an article about the benefits of a longitudinal patient record and community care plan to patient care. I picked up the idea from a piece by an Orion Health exec touting the benefits of these models. Interestingly, I couldn’t find a specific definition for a community care plan in the article — nor could I dig anything up after doing a Google search — but I think the idea is worth exploring nonetheless.

Presumably, if we had a community care plan in place for each patient, it would have interlocking patient-specific and population health-level elements to it. (To my knowledge, current population health models don’t do this.) Rather than simply handing patients off from one provider to another, in the hope that the rare patient-centered medical home could manage their care effectively on its own, it might set care goals for each patient as part of the larger community strategy.

With such a community care strategy, groups of providers would have a better idea where to allocate resources. It would simultaneously meet the goals of traditional medical referral patterns, in which clinicians consult with one another on strategy, and help them decide who to hire (such as a nurse-practitioner to serve patient clusters with higher levels of need).

As I envision it, a community care plan would raise the stakes for everyone involved in the care process. Right now, for example, if a primary care doctor refers a patient to a podiatrist, on a practical level the issue of whether the patient can walk pain-free is not the PCP’s problem. But in a community-based care plan, which help all of the individual actors be accountable, that podiatrist couldn’t just examine the patient, do whatever they did and punt. They might even be held to quantitative goals, if the they were appropriate to the situation.

I also envision a community care plan as involving a higher level of direct collaboration between providers. Sure, providers and specialists coordinate care across the community, minimally, but they rarely talk to each other, and unless they work for the same practice or health system virtually never collaborate beyond sharing care documentation. And to be fair, why should they? As the system exists today, they have little practical or even clinical incentive to get in the weeds with complex individual patients and look at their future. But if they had the right kind of community care plan in place for the population, this would become more necessary.

Of course, I’ve left the trickiest part of this for last. This system I’ve outlined, basically a slight twist on existing population health models, won’t work unless we develop new methods for sharing data collaboratively — and for reasons I be glad to go into elsewhere, I’m not bullish about anything I’ve seen. But as our understanding of what we need to get done evolves, perhaps the technology will follow. A girl can hope.

The Pain of Recording Patient Risk Factors as Illuminated by Apixio (Part 2 of 2)

Posted on October 28, 2016 I Written By

Andy Oram is an editor at O'Reilly Media, a highly respected book publisher and technology information provider. An employee of the company since 1992, Andy currently specializes in open source, software engineering, and health IT, but his editorial output has ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. His articles have appeared often on EMR & EHR and other blogs in the health IT space. Andy also writes often for O'Reilly's Radar site (http://oreilly.com/) and other publications on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM, and DebConf.

The previous section of this article introduced Apixio’s analytics for payers in the Medicare Advantage program. Now we’ll step through how Apixio extracts relevant diagnostic data.

The technology of PDF scraping
Providers usually submit SOAP notes to the Apixio web site in the form of PDFs. This comes to me as a surprise, after hearing about the extravagant efforts that have gone into new CCDs and other formats such as the Blue Button project launched by the VA. Normally provided in an XML format, these documents claim to adhere to standards and offer a relatively gentle face to a computer program. In contrast, a PDF is one of the most challenging formats to parse: words and other characters are reduced to graphical symbols, while layout bears little relation to the human meaning of the data.

Structured documents such as CCDs contain only about 20% of what CMS requires, and often are formatted in idiosyncratic ways so that even the best CCDs would be no more informative than a Word document or PDF. But the main barrier to getting information, according to Schneider, is that Medicare Advantage works through the payers, and providers can be reluctant to give payers direct access to their EHR data. This reluctance springs from a variety of reasons, including worries about security, the feeling of being deluged by requests from payers, and a belief that the providers’ IT infrastructure cannot handle the burden of data extraction. Their stance has nothing to do with protecting patient privacy, because HIPAA explicitly allows providers to share patient data for treatment, payment, and operations, and that is what they are doing giving sensitive data to Apixio in PDF form. Thus, Apixio had to master OCR and text processing to serve that market.

Processing a PDF requires several steps, integrated within Apixio’s platform:

  1. Optical character recognition to re-create the text from a photo of the PDF.

  2. Further structuring to recognize, for instance, when the PDF contains a table that needs to be broken up horizontally into columns, or constructs such the field name “Diagnosis” followed by the desired data.

  3. Natural language processing to find the grammatical patterns in the text. This processing naturally must understand medical terminology, common abbreviations such as CHF, and codings.

  4. Analytics that pull out the data relevant to risk and presents it in a usable format to a human coder.

Apixio can accept dozens of notes covering the patient’s history. It often turns up diagnoses that “fell through the cracks,” as Schneider puts it. The diagnostic information Apixio returns can be used by medical professionals to generate reports for Medicare, but it has other uses as well. Apixio tells providers when they are treating a patient for an illness that does not appear in their master database. Providers can use that information to deduce when patients are left out of key care programs that can help them. In this way, the information can improve patient care. One coder they followed could triple her rate of reviewing patient charts with Apixio’s service.

Caught between past and future
If the Apixio approach to culling risk factors appears round-about and overwrought, like bringing in a bulldozer to plant a rosebush, think back to the role of historical factors in health care. Given the ways doctors have been taught to record medical conditions, and available tools, Apixio does a small part in promoting the progressive role of accountable care.

Hopefully, changes to the health care field will permit more direct ways to deliver accountable care in the future. Medical schools will convey the requirements of accountable care to their students and teach them how to record data that satisfies these requirements. Technologies will make it easier to record risk factors the first time around. Quality measures and the data needed by policy-makers will be clarified. And most of all, the advantages of collaboration will lead providers and payers to form business agreements or even merge, at which point the EHR data will be opened to the payer. The contortions providers currently need to go through, in trying to achieve 21st-century quality, reminds us of where the field needs to go.