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!!

Vendor Study Says Wearables Can Promote Healthy Behavior Change

Posted on November 28, 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.

A new study backed by a company that makes an enterprise health benefits platform has concluded that wearables can encourage healthy behavior change, and also, serve as an effective tool to engage employees in their health.

The data from the study, which was sponsored by Mountain View, CA-based Jiff, comes from a two-year research project on employer-sponsored wearables. Rajiv Leventhal, who wrote about the study for Healthcare Informatics, argues that these findings challenge common employer beliefs about these type of programs, including that participation is typically limited to young and healthy employees, and that engagement with these rules can’t be sustained over time.

The data, which was drawn from 14 large employers with 240,000 employees, apparently suggests that wearable adoption and long-term engagement is possible for employees of all ages. The company reported that among the employers offered the wearables program via its enterprise health platform, 53% of employees under 40 years old participated, and 36% of employees over 50 years participated as well.

Jiff researchers also found that employee engagement had not measurably fallen for more than nine months following the program rollout, and that for one employer, levels of engagement have been progressively increasing for more than 18 months, the company reported.

According to Jiff, they have helped sustain employee engagement by employing three tactics:  Using “challenges,” time-bound immersive and social games that encourage healthy actions, “device credits,” subsidies that offset the cost of purchasing wearables and “behavioral incentives,” rewards for taking healthy actions such as walking a minimum number of steps per day.

The thing is, as interesting as these numbers might be — and they do, if nothing else, underscore the role of engaging consumers rather than waiting for them to engage with healthier behaviors on their own — the story doesn’t address one absolutely crucial issue, to wit, what concrete health impact are companies seeing from employee use of these devices.

I don’t think I’m asking for too much here when I demand some quantitative data suggesting that the setup can actually achieve measurable health results. Everything I’ve read about employee wellness initiatives to date suggests that they’ve been a giant bust, with few if any accomplishing anything measurable.

And here we have Jiff, a venture-backed hotshot company, which I’m guessing had the resources to report on results if it found any. After all, if I understand the study right, with their researchers had access to 540,000 employees for significant amount of time.  So where are the health conclusions that can be drawn from this population?

And by the way, no, I don’t accept that patient engagement (no matter how genuine) can be used as a proxy or predictive factor for health improvement. It’s a promising step in the right direction but it isn’t the real thing yet.

So, I shared the study with you because I thought you might find it interesting. I did. But I wouldn’t take it too seriously when it comes to signs of real change — either for wearables used for employee wellness initiatives. At this point both are more smoke than substance.

Are Healthcare Data Streams Rich Enough To Support AI?

Posted on November 21, 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.

As I’ve noted previously, artificial intelligence and machine learning applications are playing an increasingly important role in healthcare. The two technologies are central to some intriguing new data analytics approaches, many of which are designed to predict which patients will suffer from a particular ailment (or progress in that illness), allowing doctors to intervene.

For example, at New York-based Mount Sinai Hospital, executives are kicking off a predictive analytics project designed to predict which patients might develop congestive heart failure, as well as to care for those who’ve are done so more effectively. The hospital is working with AI vendor CloudMedx to make the predictions, which will generate predictions by mining the organization’s EMR for clinical clues, as well as analyzing data from implantable medical devices, health tracking bands and smartwatches to predict the patient’s future status.

However, I recently read an article questioning whether all health IT infrastructures are capable of handling the influx of data that are part and parcel with using AI and machine learning — and it gave me pause.

Artificial intelligence, the article notes, functions on collected data, and the more data AI solution has access to, the more successful the implementation will be, contends Elizabeth O’Dowd in HIT Infrastructure. And there are some questions as to whether healthcare IT departments can integrate this data, especially Internet of Things datapoints such as wearables and other personal devices.

After all, O’Dowd notes, for the AI solution to crawl data from IoT wearables, mobile apps and other connected devices, the data must be integrated into the patient’s medical record in a format which is compatible with the organization’s EMR technology. Otherwise, the organization’s data analytics solution won’t be able to process the data, and in turn, the AI solution won’t be able to evaluate it, she writes.

Without a doubt, O’Dowd has raised some important issues here. But the real question, as I see it, is whether such data integration is really the biggest bottleneck AI and machine learning must pass through before becoming accessible to a wide range of users. For example, healthcare AI-based Lumiata offers a FHIR-compliant API to help organizations integrate such data, which is certainly relevant to this discussion.

It seems to me that giving the AI every possible scrap of data to feed on isn’t the be all and end all, and may even actually less important than the clinical rationale developers uses to back up its work. In other words, in the case of Lumiata and its competitors, it appears that creating a firm foundation for the predictions is still as much the work of clinicians as much is AI.

I guess what I’m getting to here is that while AI is doubtless more effective at predicting events as it has access to more data, using what data we have with and letting skilled clinicians manage it is still quite valuable. So let’s not back off on harvesting the promise of AI just because we don’t have all the data in hand yet.

Vocera Aims For More Intelligent Hospital Interventions

Posted on November 14, 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.

Everyday scenes that Vocera Communications would like to eliminate from hospitals:

  • A nurse responds to an urgent change in the patient’s condition. While the nurse is caring for the patient, monitors continue to go off with alerts about the situation, distracting her and increasing the stress for both herself and the patient.

  • A monitor beeps in response to a dangerous change in a patient’s condition. A nurse pages the physician in charge. The physician calls back to the nurse’s station, but the nurse is off on another task. They play telephone tag while patient needs go unmet around the floor.

  • A nurse is engaged in a delicate operation when her mobile device goes off, distracting her at a crucial moment. Neither the patient she is currently working with nor the one whose condition triggered the alert gets the attention he needs.

  • A nurse describes a change in a patient’s condition to a physician, who promises to order a new medication. The nurse then checks the medical record every few minutes in the hope of seeing when the order went through. (This is similar to a common computing problem called “polling”, where a software or hardware component wakes up regularly just to see whether data has come in for it to handle.)

Wasteful, nerve-racking situations such as these have caught the attention of Vocera over the past several years as it has rolled out communications devices and services for hospital staff, and have just been driven forward by its purchase of the software firm Extension Healthcare.

Vocera Communications’ and Extension Healthcare’s solutions blend to take pressures off clinicians in hospitals and improve their responses to patient needs. According to Brent Lang, President and CEO of Vocera Communications, the two companies partnered together on 40 customers before the acquisition. They take data from multiple sources–such as patient monitors and electronic health records–to make intelligent decisions about “when to send alarms, whom to send them to, and what information to include” so the responding nurse or doctor has the information needed to make a quick and effective intervention.

Hospitals are gradually adopting technological solutions that other parts of society got used to long ago. People are gradually moving away from setting their lights and thermostats by hand to Internet-of-Things systems that can adjust the lights and thermostats according to who is in the house. The combination of Vocera and Extension Healthcare should be able to do the same for patient care.

One simple example concerns the first scenario with which I started this article. Vocera can integrate with the hospital’s location monitoring (through devices worn by health personnel) that the system can consult to see whether the nurse is in the same room as the patient for whom the alert is generated. The system can then stop forwarding alarms about that patient to the nurse.

The nurse can also inform the system when she is busy, and alerts from other patients can be sent to a back-up nurse.

Extension Healthcare can deliver messages to a range of devices, but the Vocera badge and smartphone app work particularly well with it because they can deliver contextual information instead of just an alert. Hospitals can define protocols stating that when certain types of devices deliver certain types of alerts, they should be accompanied by particular types of data (such as relevant vital signs). Extension Healthcare can gather and deliver the data, which the Vocera badge or smartphone app can then display.

Lang hopes the integrated systems can help the professionals prioritize their interventions. Nurses are interrupt-driven, and it’s hard for them to keep the most important tasks in mind–a situation that leads to burn-out. The solutions Vocera is putting together may significantly change workflows and improve care.

Health Plans Need Big Data Smarts To Prove Their Value

Posted on November 2, 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, Aetna cut a deal which suggests a new role for health insurers in big data analytics and population health management. In partnership with Merck, the health insurer is launching a new program using predictive analytics to identify target populations and provide them with health and wellness services. AetnaCare will start by targeting patients with diabetes and hypertension in the mid-Atlantic U.S., but it seems likely to go national soon.

In its press release on the matter, Aetna says the goal of the program is to “proactively curate various health and wellness services… to support treatment adherence, ensure that critical social support needs are met, and reinforce healthy lifestyle behaviors.” That in and of itself isn’t a big deal. We all know that these are goals shared by providers, employers and health plans, and that most of the efforts health plans make on this front are pie in the sky, half-baked initiatives featuring cutesy graphics and little substance.

But then, Aetna’s chief medical officer gives away the real goal here — to power this effort by analyzing patient data being spun out by patients in varied care settings.  In the release, Dr. Harold Paz notes that patients are getting care in a wide variety of settings, including retail clinics, healthcare devices, pharmaceutical services, behavioral health, and social services, and that these services are seldom coordinated well, and implies that this is the real problem Aetna must solve.

If you listen to this with the ears of a health IT chick like myself, you hear Aetna (and Merck, actually) admitting that they must engage in predictive analytics across all of these encounters – and eventually, use these insights to help patients make good healthcare choices. In other words, they have to think like providers and even offer provider-like services fulfill their mission. And that means competing with or even beating providers at the big data game.

The truth is, health plans are in the same boat as providers, in that they’re at the center of a hailstorm of data and struggling with how to make use of it. Also, like providers they’re facing pressure from health purchasers to slow healthcare cost growth and boost patient wellness. But I’d argue that they’re even less prepared, technically and culturally, to improve health or coordinate care. So jumping in now is critically important.

In fact, I’d argue that health insurers are under greater pressure to improve population health than even sophisticated health systems or ACOs. Why? Because while health systems and ACOs can point to what they do – they make people better, for heaven’s sake — insurance companies are the eternal middleman who must continue to prove that they add value to the healthcare equation.

It remains to be seen whether programs like AetnaCare succeed at helping patients find the resources they need to improve and maintain their health. But even if this concept doesn’t work out, others will follow. Health plans need to leverage their unique data set to boost quality and reduce costs. Otherwise, as providers learn to work under value-based payments and accept risk, employers will have increasingly good reasons to contract directly — and leave the insurance industry out of the game entirely.

E-Patient Update: The Patient Data Engagement Leader

Posted on October 20, 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.

As healthcare delivery models shift responsibility for patient health to the patients themselves, it’s becoming more important to give them tools to help them get and stay healthy. Increasingly, digital health tools are filling the bill.

For example, portals are moving from largely billing and scheduling apps to exchanging of patient data, holding two-way conversations between patient and doctor and even tracking key indicators like blood glucose levels. Wearables are slowly becoming capable of helping doctors improve diagnoses, and patterns revealed by big data should soon be used to create personalized treatment plants.

The ultimate goal of all this, of course, is to push as much data power as possible into the hands of consumers. After all, for patients to be engaged with their health, it helps to make them feel in control, and the more sophisticated information they get, the better choices they can make. Or at least that’s how the traditional script reads.

Now, as an e-patient, the above is certainly true for me. Every incremental improvement in the data I get me brings me closer to taking on otherwise overwhelming health challenges. That’s true, in part, because I’m comfortable reading charts, extrapolating conclusions from data points and visualizing ways to make use of the information. But if you want less tech-friendly patients to get on board, they’re going to need help.

The patient engagement leader

And where will that help come from? I’d argue that hospitals and clinics need to create a new position dedicated to helping engage patients, including though not limited to helping them make their health data their own. This position would cut across several disciplines, ranging from patient health education clinical medicine to data analytics.

The person owning this position would need to be current in patient engagement goals across the population and by disease/condition type, understand the preferred usage patterns established by the hospital, ACO, delivery network or clinic and understand trends in health behavior well enough to help steer patients in the right direction.

It also wouldn’t hurt if such a person had a healthy dose of marketing skills under their belt, as part of the patient engagement process is simply selling consumers on the idea that they can and should take more responsibility for their health outcomes. Speaking from personal experience, a good marketer can wheedle, nudge and empower people by turns, and this will be very necessary to boost your engagement.

While this could be a middle management position, it would at least need to have the full support of the C-suite. After all, you can’t promote population-wide improvements in health by nibbling around the edges of the problem. Such measures need to be comprehensive and strategic to the mission of the healthcare organization as a whole, and the person behind the needs to have the authority to see them through.

Patients in control

If things go right, establishing this position would lead to the creation of a better-educated, more-confident patient population with a greater sense of self efficacy regarding their health. While specific goals would vary from one healthcare organization to the other, such an initiative would ideally lead to improvements in key metrics such as A1c levels population-wide, drops in hospital admission and readmission rates and simultaneously, lower spending on more intense modes of care.

Not only that, you could very well see patient satisfaction increase as well. After all, patients may not feel capable of making important health changes on their own, and if you help them do that it stands to reason that they’ll appreciate it.

Ultimately, engaging patients with their health calls for participation by everyone who touches the patient, from techs to the physician, nurses to the billing department. But if you put a patient engagement officer in place, it’s more likely that these efforts will have a focus.

What Do You Think Of Data Lakes?

Posted on October 4, 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.

Being that I am not a high-end technologist, I’m not always up on the latest trends in database management – so the following may not be news to everyone who reads this. As for me, though, the notion of a “data lake” is a new one, and I think it a valuable idea which could hold a lot of promise for managing unruly healthcare data.

The following is a definition of the term appearing on a site called KDnuggets which focuses on data mining, analytics, big data and data science:

A data lake is a storage repository that holds a vast amount of raw data in its native format, including structured, semi-structured and unstructured data. The data structure and requirements are not defined until the data is needed.

According to article author Tamara Dull, while a data warehouse contains data which is structured and processed, expensive to store, relies on a fixed configuration and used by business professionals, a data link contains everything from raw to structured data, is designed for low-cost storage (made possible largely because it relies on open source software Hadoop which can be installed on cheaper commodity hardware), can be configured and reconfigured as needed and is typically used by data scientists. It’s no secret where she comes down as to which model is more exciting.

Perhaps the only downside she identifies as an issue with data lakes is that security may still be a concern, at least when compared to data warehouses. “Data warehouse technologies have been around for decades,” Dull notes. “Thus, the ability to secure data in a data warehouse is much more mature than securing data in a data lake.” But this issue is likely to receive in the near future, as the big data industry is focused tightly on security of late, and to her it’s not a question of if security will mature but when.

It doesn’t take much to envision how the data lake model might benefit healthcare organizations. After all, it may make sense to collect data for which we don’t yet have a well-developed idea of its use. Wearables data comes to mind, as does video from telemedicine consults, but there are probably many other examples you could supply.

On the other hand, one could always counter that there’s not much value in storing data for which you don’t have an immediate use, and which isn’t structured for handy analysis by business analysts on the fly. So even if data lake technology is less costly than data warehousing, it may or may not be worth the investment.

For what it’s worth, I’d come down on the side of the data-lake boosters. Given the growing volume of heterogenous data being generated by healthcare organizations, it’s worth asking whether deploying a healthcare data lake makes sense. With a data lake in place, healthcare leaders can at least catalog and store large volumes of un-normalized data, and that’s probably a good thing. After all, it seems inevitable that we will have to wring value out of such data at some point.

Apple’s Healthcare Data Plans Become Clearer

Posted on October 3, 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.

Though it’s not without competitors, I’d argue that Apple’s HealthKit has stood out since its inception, in part because it was relatively early to the game (mining patient-centered data) and partly because Apple products have a sexy reputation. That being said, it hasn’t exactly transformed the health IT industry either.

Now, though, with the acquisition of Gliimpse, a startup which pulls data from disparate EMRs into a central database, it’s become clearer what Apple’s big-picture goals are for the healthcare market – and if its business model works out they could indeed change health data industry.

According to a nifty analysis by Bloomberg’s Alex Webb, which quotes an Apple Health engineer, the technology giant hopes to see the health data business evolve along the lines of Apple’s music business, in which Apple started with a data management tool (the iPod) then built a big-bucks music platform on the device. And that sounds like an approach that could steal a move from many a competitor indeed.

Apple’s HealthKit splash
Apple made a big splash with the summer 2014 launch of HealthKit, a healthcare data integration platform whose features include connecting patient generated health data with traditional systems like the Epic EMR. It also attracted prominent partners like Cedars-Sinai Medical Center and Ochsner Health System within a year or so of its kickoff.

Still, the tech giant has been relatively quiet about its big-picture vision for healthcare, leaving observers like yours truly wondering what was up. After all, many of Apple’s health data moves have been incremental. For example, a few months ago I noted that Apple had begun allowing users to store their EMR data directly in its Health app, using the HL7 CCD standard. While interesting, this isn’t exactly an earth-shattering advance.

But in his analysis — which makes a great deal of sense to me – Bloomberg’s Webb argues that Apple’s next act is to take the data it’s been exchanging with wearables and put it to better use. Apple’s long-awaited big idea is to turn Apple’s HealthKit into a system that can improve diagnoses, sources told Bloomberg.

Also, Apple intends to integrate health records as closely with its proprietary devices as possible, offering not only data collection but suggestions for better health in a manner that can’t be easily duplicated on Android platforms. As Webb rightly points out, such a move could undermine Google’s larger healthcare plans, by locking consumers into Apple technology and discouraging a switch to the Google Fit health tracking software.

Big vision, big questions
As we know, even a company with the reputation, cash and proprietary user base enjoyed by Apple is far from a shoo-in for consumer health data dominance. (Consider the fate of Microsoft HealthVault and Google Health.) Its previous successes have come, as noted, by creating a channel then dominating that channel, but there’s no guarantee it can pull off such a trick this time.

For one thing, the wearables market is highly fragmented, and Apple is far from being the leader. (According to one set of stats, Fitbit had 25.4% of the global wearables market as of Q2 ’16, Xiaomi 14%, and Apple just 7%.) That doesn’t bode well for starting a health tracker-based revolution.

On the other hand, though, Apple did manage to create and dominate a channel in the music business, which is also quite resistant to change and dominated by extremely entrenched powers that be. If any upstart healthcare player could make this happen, it’s probably Apple. It will be interesting to see whether Apple can work its magic once again.

Validic Survey Raises Hopes of Merging Big Data Into Clinical Trials

Posted on September 30, 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.

Validic has been integrating medical device data with electronic health records, patient portals, remote patient monitoring platforms, wellness challenges, and other health databases for years. On Monday, they highlighted a particularly crucial and interesting segment of their clientele by releasing a short report based on a survey of clinical researchers. And this report, although it doesn’t go into depth about how pharmaceutical companies and other researchers are using devices, reveals great promise in their use. It also opens up discussions of whether researchers could achieve even more by sharing this data.

The survey broadly shows two trends toward the productive use of device data:

  • Devices can report changes in a subject’s condition more quickly and accurately than conventional subject reports (which involve marking observations down by hand or coming into the researcher’s office). Of course, this practice raises questions about the device’s own accuracy. Researchers will probably splurge for professional or “clinical-grade” devices that are more reliable than consumer health wearables.

  • Devices can keep the subject connected to the research for months or even years after the end of the clinical trial. This connection can turn up long-range side effects or other impacts from the treatment.

Together these advances address two of the most vexing problems of clinical trials: their cost (and length) and their tendency to miss subtle effects. The cost and length of trials form the backbone of the current publicity campaign by pharma companies to justify price hikes that have recently brought them public embarrassment and opprobrium. Regardless of the relationship between the cost of trials and the cost of the resulting drugs, everyone would benefit if trials could demonstrate results more quickly. Meanwhile, longitudinal research with massive amounts of data can reveal the kinds of problems that led to the Vioxx scandal–but also new off-label uses for established medications.

So I’m excited to hear that two-thirds of the respondents are using “digital health technologies” (which covers mobile apps, clinical-grade devices, and wearables) in their trials, and that nearly all respondents plan to do so over the next five years. Big data benefits are not the only ones they envision. Some of the benefits have more to do with communication and convenience–and these are certainly commendable as well. For instance, if a subject can transmit data from her home instead of having to come to the office for a test, the subject will be much more likely to participate and provide accurate data.

Another trend hinted at by the survey was a closer connection between researchers and patient communities. Validic announced the report in a press release that is quite informative in its own right.

So over the next few years we may enter the age that health IT reformers have envisioned for some time: a merger of big data and clinical trials in a way to reap the benefits of both. Now we must ask the researchers to multiply the value of the data by a whole new dimension by sharing it. This can be done in two ways: de-identifying results and uploading them to public or industry-maintained databases, or providing identifying information along with the data to organizations approved by the subject who is identified. Although researchers are legally permitted to share de-identified information without subjects’ consent (depending on the agreements they signed when they began the trials), I would urge patient consent for all releases.

Pharma companies are already under intense pressure for hiding the results of trials–but even the new regulations cover only results, not the data that led to those results. Organizations such as Sage Bionetworks, which I have covered many times, are working closely with pharmaceutical companies and researchers to promote both the software tools and the organizational agreements that foster data sharing. Such efforts allow people in different research facilities and even on different continents to work on different aspects of a target and quickly share results. Even better, someone launching a new project can compare her data to a project run five years before by another company. Researchers will have millions of data points to work with instead of hundreds.

One disappointment in the Validic survey was a minority of respondents saw a return on investment in their use of devices. With responsible data sharing, the next Validic survey may raise this response rate considerably.

The Burden of Structured Data: What Health Care Can Learn From the Web Experience (Part 2 of 2)

Posted on September 23, 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 first part of this article summarized what Web developers have done to structure data, and started to look at the barriers presented by health care. This part presents more recommendations for making structured data work.

The Grand Scheme of Things
Once you start classifying things, it’s easy to become ensnared by grandiose pipe dreams and enter a free fall trying to design the perfect classification system. A good system is distinguished by knowing its limitations. That’s why microdata on the Web succeeded. In other areas, the field of ontology is littered with the carcasses of projects that reached too far. And health care ontologies always teeter on the edge of that danger.

Let’s take an everyday classification system as an example of the limitations of ontology. We all use genealogies. Imagine being able to sift information about a family quickly, navigating from father to son and along the trail of siblings. But even historical families, such as royal ones, introduce difficulties right away. For instance, children born out of wedlock should be shown differently from legitimate heirs. Modern families present even bigger headaches. How do you represent blended families where many parents take responsibilities of different types for the children, or people who provided sperm or eggs for artificial insemination?

The human condition is a complicated one not subject to easy classification, and that naturally extends to health, which is one of the most complex human conditions. I’m sure, for instance, that the science of mosquito borne diseases moves much faster than the ICD standard for disease. ICD itself should be replaced with something that embodies semantic meaning. But constant flexibility must be the hallmark of any ontology.

Transgender people present another enormous challenge to ontologies and EHRs. They’re a test case for every kind of variation in humanity. Their needs and status vary from person to person, with no classification suiting everybody. These needs can change over time as people make transitions. And they may simultaneously need services defined for male and female, with the mix differing from one patient to the next.

Getting to the Point
As the very term “microdata” indicates, those who wish to expose semantic data on the Web can choose just a few items of information for that favored treatment. A movie theater may have text on its site extolling its concession stand, its seating, or its accommodations for the disabled, but these are not part of the microdata given to search engines.

A big problem in electronic health records is their insistence that certain things be filled out for every patient. Any item that is of interest for any class of patient must appear in the interface, a problem known in the data industry as a Cartesian explosion. Many observers counsel a “less is more” philosophy in response. It’s interesting that a recent article that complained of “bloated records” and suggested a “less is more” approach goes on to recommend the inclusion of scads of new data in the record, to cover behavioral and environmental information. Without mentioning the contradiction explicitly, the authors address it through the hope that better interfaces for entering and displaying information will ease the burden on the clinician.

The various problems with ontologies that I have explained throw doubt on whether EHRs can attain such simplicity. Patients are not restaurants. To really understand what’s important about a patient–whether to guide the clinician in efficient data entry or to display salient facts to her–we’ll need systems embodying artificial intelligence. Such systems always feature false positives and negatives. They also depend on continuous learning, which means they’re never perfect. I would not like to be the patient whose data gets lost or misclassified during the process of tuning the algorithms.

I do believe that some improvements in EHRs can promote the use of structured data. Doctors should be allowed to enter the data in the order and the manner they find intuitive, because that order and that manner reflect their holistic understanding of the patient. But suggestions can prompt them to save some of the data in structured format, without forcing them to break their trains of thought. Relevant data will be collected and irrelevant fields will not be shown or preserved at all.

The resulting data will be less messy than what we have in unstructured text currently, but still messy. So what? That is the nature of data. Analysts will make the best use of it they can. But structure should never get in the way of the information.

The Burden of Structured Data: What Health Care Can Learn From the Web Experience (Part 1 of 2)

Posted on September 22, 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.

Most innovations in electronic health records, notably those tied to the Precision Medicine initiative that has recently raised so many expectations, operate by moving clinical information into structure of one type or another. This might be a classification system such as ICD, or a specific record such as “medications” or “lab results” with fixed units and lists of names to choose from. There’s no arguing against the benefits of structured data. But its costs are high as well. So we should avoid repeating old mistakes. Experiences drawn from the Web may have something to teach the health care field in respect to structured data.

What Works on the Web
The Web grew out of a structured data initiative. The dream of organizing information goes back decades, and was embodied in Standard Generalized Markup Language (SGML) years before Tim Berners-Lee stole its general syntax to create HTML and present information on the Web. SGML could let a firm mark in its documents that FR927 was a part number whereas SG1 was a building. Any tags that met the author’s fancy could be defined. This put semantics into documents. In other words, the meaning of text could be abstracted from the the text and presented explicitly. Semantics got stripped out of HTML. Although the semantic goals of SGML were re-introduced into the HTML successor XML, it found only niche uses. Another semantic Web tool, JSON, was reserved for data storage and exchange, not text markup.

Since the Web got popular, people have been trying to reintroduce semantics into it. There was Dublin Core, then RDF, then microdata in places like schema.org–just to list a few. Two terms denoting structured data on the Web, the Semantic Web and Linked Data, have been enthusiastically taken up by the World Wide Web Consortium and Tim Berners-Lee himself.

But none of these structured data initiatives are widely known among the Web-browsing public, probably because they all take a lot of work to implement. Furthermore, they run into the bootstrapping problem faced by nearly all standards: if your web site uses semantics that aren’t recognized by the browser, they’re just dropped on the ground (or even worse, the browser mangles your web pages).

Even so, recent years have seen an important form of structured data take off. When you look up a movie or restaurant on a major search engine such a Google, Yahoo!, or Bing, you’ll see a summary of the information most people want to see: local showtimes for the movie, phone number and ratings for a restaurant, etc. This is highly useful (particularly on mobile devices) and can save you the trouble of visiting the web site from which the data comes. Google calls these summaries Rich Cards and Rich Snippets.

If my memory serves me right, the basis for these snippets didn’t come from standards committees involving years of negotiation between stake-holders. Google just decided what would be valuable to its users and laid out the standard. It got adopted because it was a win-win. The movie theaters and restaurants got their information right into the viewer’s face, and the search engine became instantly more valuable and more likely to be used again. The visitors doing the search obviously benefitted too. Everyone found it worth their time to implement the standards.

Interestingly, as structure moves into metadata, HTML itself is getting less semantic. The most recent standard, HTML5, did add a few modest tags such as header and footer. But many sites are replacing meaningful HTML markup, such as p for paragraph, with two ultra-generic tags: div for a division that is set off from other parts of the page, and span for a piece of text embedded within another. Formatting is expressed through CSS, a separate language.

Having reviewed a bit of Web history, let’s see what we can learn from it and apply to health care.

Make the Customer Happy
Win-win is the key to getting a standard adopted. If your clinician doesn’t see any benefit from the use of structured data, she will carp and bristle at any attempt to get her to enter it. One of the big reasons electronic health records are so notoriously hard to use is, “All those fields to fill out.” And while lists of medications or other structured data can help the doctor choose the right one, they can also help her enter serious errors–perhaps because she chose the one next to the one she meant to choose, or because the one she really wanted isn’t offered on the list.

Doctors’ resentment gets directed against every institution implicated in the structured data explosion: the ONC and CMS who demand quality data and other fields of information for their own inscrutable purposes, the vendor who designs up the clunky system, and the hospital or clinic that forces doctors to use it. But the Web experience suggests that doctors would fill out fields that would help them in their jobs. The use of structured data should be negotiated, not dictated, just like other innovations such as hand-washing protocols or checklists. Is it such a radical notion to put technology at the service of the people using it?

I know it’s frustrating to offer that perspective, because many great things come from collecting data that is used in analytics and can turn up unexpected insights. If we fill out all those fields, maybe we’ll find a new cure! But the promised benefit is too far off and too speculative to justify the hourly drag upon the doctor’s time.

We can fall back on the other hope for EHR improvement: an interface that makes data entry so easy that doctors don’t mind using structured fields. I have some caveats to offer about that dream, which will appear in the second part of this article.