Newer posts are loading.
You are at the newest post.
Click here to check if anything new just came in.

September 13 2012

Growth of SMART health care apps may be slow, but inevitable

This week has been teaming with health care conferences, particularly in Boston, and was declared by President Obama to be National Health IT Week as well. I chose to spend my time at the second ITdotHealth conference, where I enjoyed many intense conversations with some of the leaders in the health care field, along with news about the SMART Platform at the center of the conference, the excitement of a Clayton Christiansen talk, and the general panache of hanging out at the Harvard Medical School.

SMART, funded by the Office of the National Coordinator in Health and Human Services, is an attempt to slice through the Babel of EHR formats that prevent useful applications from being developed for patient data. Imagine if something like the wealth of mash-ups built on Google Maps (crime sites, disaster markers, restaurant locations) existed for your own health data. This is what SMART hopes to do. They can already showcase some working apps, such as overviews of patient data for doctors, and a real-life implementation of the heart disease user interface proposed by David McCandless in WIRED magazine.

The premise and promise of SMART

At this conference, the presentation that gave me the most far-reaching sense of what SMART can do was by Nich Wattanasin, project manager for i2b2 at Partners. His implementation showed SMART not just as an enabler of individual apps, but as an environment where a user could choose the proper app for his immediate needs. For instance, a doctor could use an app to search for patients in the database matching certain characteristics, then select a particular patient and choose an app that exposes certain clinical information on that patient. In this way, SMART an combine the power of many different apps that had been developed in an uncoordinated fashion, and make a comprehensive data analysis platform from them.

Another illustration of the value of SMART came from lead architect Josh Mandel. He pointed out that knowing a child’s blood pressure means little until one runs it through a formula based on the child’s height and age. Current EHRs can show you the blood pressure reading, but none does the calculation that shows you whether it’s normal or dangerous. A SMART app has been developer to do that. (Another speaker claimed that current EHRs in general neglect the special requirements of child patients.)

SMART is a close companion to the Indivo patient health record. Both of these, aong with the i2b2 data exchange system, were covered in article from an earlier conference at the medical school. Let’s see where platforms for health apps are headed.

How far we’ve come

As I mentioned, this ITdotHealth conference was the second to be held. The first took place in September 2009, and people following health care closely can be encouraged by reading the notes from that earlier instantiation of the discussion.

In September 2009, the HITECH act (part of the American Recovery and Reinvestment Act) had defined the concept of “meaningful use,” but nobody really knew what was expected of health care providers, because the ONC and the Centers for Medicare & Medicaid Services did not release their final Stage 1 rules until more than a year after this conference. Aneesh Chopra, then the Federal CTO, and Todd Park, then the CTO of Health and Human Services, spoke at the conference, but their discussion of health care reform was a “vision.” A surprisingly strong statement for patient access to health records was made, but speakers expected it to be accomplished through the CONNECT Gateway, because there was no Direct. (The first message I could find on the Direct Project forum dated back to November 25, 2009.) Participants had a sophisticated view of EHRs as platforms for applications, but SMART was just a “conceptual framework.”

So in some ways, ONC, Harvard, and many other contributors to modern health care have accomplished an admirable amount over three short years. But some ways we are frustratingly stuck. For instance, few EHR vendors offer API access to patient records, and existing APIs are proprietary. The only SMART implementation for a commercial EHR mentioned at this week’s conference was one created on top of the Cerner API by outsiders (although Cerner was cooperative). Jim Hansen of Dossia told me that there is little point to encourage programmers to create SMART apps while the records are still behind firewalls.

Keynotes

I couldn’t call a report on ITdotHealth complete without an account of the two keynotes by Christiansen and Eric Horvitz, although these took off in different directions from the rest of the conference and served as hints of future developments.

Christiansen is still adding new twists to the theories laid out in c The Innovator’s Dilemma and other books. He has been a backer of the SMART project from the start and spoke at the first ITdotHealth conference. Consistent with his famous theory of disruption, he dismisses hopes that we can reduce costs by reforming the current system of hospitals and clinics. Instead, he projects the way forward through technologies that will enable less trained experts to successively take over tasks that used to be performed in more high-cost settings. Thus, nurse practitioners will be able to do more and more of what doctors do, primary care physicians will do more of what we current delegate to specialists, and ultimately the patients and their families will treat themselves.

He also has a theory about the progression toward openness. Radically new technologies start out tightly integrated, and because they benefit from this integration they tend to be created by proprietary companies with high profit margins. As the industry comes to understand the products better, they move toward modular, open standards and become commoditized. Although one might conclude that EHRs, which have been around for some forty years, are overripe for open solutions, I’m not sure we’re ready for that yet. That’s because the problems the health care field needs to solve are quite different from the ones current EHRs solve. SMART is an open solution all around, but it could serve a marketplace of proprietary solutions and reward some of the venture capitalists pushing health care apps.

While Christiansen laid out the broad environment for change in health care, Horvitz gave us a glimpse of what he hopes the practice of medicine will be in a few years. A distinguished scientist at Microsoft, Horvitz has been using machine learning to extract patterns in sets of patient data. For instance, in a collection of data about equipment uses, ICD codes, vital signs, etc. from 300,000 emergency room visits, they found some variables that predicted a readmission within 14 days. Out of 10,000 variables, they found 500 that were relevant, but because the relational database was strained by retrieving so much data, they reduced the set to 23 variables to roll out as a product.

Another project predicted the likelihood of medical errors from patient states and management actions. This was meant to address a study claiming that most medical errors go unreported.

A study that would make the privacy-conscious squirm was based on the willingness of individuals to provide location data to researchers. The researchers tracked searches on Bing along with visits to hospitals and found out how long it took between searching for information on a health condition and actually going to do something about it. (Horvitz assured us that personally identifiable information was stripped out.)

His goal is go beyond measuring known variables, and to find new ones that could be hidden causes. But he warned that, as is often the case, causality is hard to prove.

As prediction turns up patterns, the data could become a “fabric” on which many different apps are based. Although Horvitz didn’t talk about combining data sets from different researchers, it’s clearly suggested by this progression. But proper de-identification and flexible patient consent become necessities for data combination. Horvitz also hopes to move from predictions to decisions, which he says is needed to truly move to evidence-based health care.

Did the conference promote more application development?

My impression (I have to admit I didn’t check with Dr. Ken Mandl, the organizer of the conference) was that this ITdotHealth aimed to persuade more people to write SMART apps, provide platforms that expose data through SMART, and contribute to the SMART project in general. I saw a few potential app developers at the conference, and a good number of people with their hands on data who were considering the use of SMART. I think they came away favorably impressed–maybe by the presentations, maybe by conversations that the meeting allowed them to have with SMART developers–so we may see SMART in wider use soon. Participants came far for the conference; I talked to one from Geneva, for instance.

The presentations were honest enough, though, to show that SMART development is not for the faint-hearted. On the supply side–that is, for people who have patient data and want to expose it–you have to create a “container” that presents data in the format expected by SMART. Furthermore, you must make sure the data conforms to industry standards, such as SNOMED for diagnoses. This could be a lot of conversion.

On the application side, you may have to deal with SMART’s penchant for Semantic Web technologies such as OWL and SPARQL. This will scare away a number of developers. However, speakers who presented SMART apps at the conference said development was fairly easy. No one matched the developer who said their app was ported in two days (most of which were spent reading the documentation) but development times could usually be measured in months.

Mandl spent some time airing the idea of a consortium to direct SMART. It could offer conformance tests (but probably not certification, which is a heavy-weight endeavor) and interact with the ONC and standards bodies.

After attending two conferences on SMART, I’ve got the impression that one of its most powerful concepts is that of an “app store for health care applications.” But correspondingly, one of the main sticking points is the difficulty of developing such an app store. No one seems to be taking it on. Perhaps SMART adoption is still at too early a stage.

Once again, we are batting our heads up against the walls erected by EHRs to keep data from being extracted for useful analysis. And behind this stands the resistance of providers, the users of EHRs, to give their data to their patients or to researchers. This theme dominated a federal government conference on patient access.

I think SMART will be more widely adopted over time because it is the only useful standard for exposing patient data to applications, and innovation in health care demands these apps. Accountable Care Organizations, smarter clinical trials (I met two representatives of pharmaceutical companies at the conference), and other advances in health care require data crunching, so those apps need to be written. And that’s why people came from as far as Geneva to check out SMART–there’s nowhere else to find what they need. The technical requirements to understand SMART seem to be within the developers’ grasps.

But a formidable phalanx of resistance remains, from those who don’t see the value of data to those who want to stick to limited exchange formats such as CCDs. And as Sean Nolan of Microsoft pointed out, one doesn’t get very far unless the app can fit into a doctor’s existing workflow. Privacy issues were also raised at the conference, because patient fears could stymie attempts at sharing. Given all these impediments, the government is doing what it can; perhaps the marketplace will step in to reward those who choose a flexible software platform for innovation.

August 09 2012

Five elements of reform that health providers would rather not hear about

The quantum leap we need in patient care requires a complete overhaul of record-keeping and health IT. Leaders of the health care field know this and have been urging the changes on health care providers for years, but the providers are having trouble accepting the changes for several reasons.

What’s holding them back? Change certainly costs money, but the industry is already groaning its way through enormous paradigm shifts to meet current financial and regulatory climate, so the money might as well be directed to things that work. Training staff to handle patients differently is also difficult, but the staff on the floor of these institutions are experiencing burn-out and can be inspired by a new direction. The fundamental resistance seems to be expectations by health providers and their vendors about the control they need to conduct their business profitably.

A few months ago I wrote an article titled Five Tough Lessons I Had to Learn About Health Care. Here I’ll delineate some elements of a new health care system that are promoted by thought leaders, that echo the evolution of other industries, that will seem utterly natural in a couple decades–but that providers are loathe to consider. I feel that leaders in the field are not confronting that resistance with an equivalent sense of conviction that these changes are crucial.

1. Reform will not succeed unless electronic records standardize on a common, robust format

Records are not static. They must be combined, parsed, and analyzed to be useful. In the health care field, records must travel with the patient. Furthermore, we need an explosion of data analysis applications in order to drive diagnosis, public health planning, and research into new treatments.

Interoperability is a common mantra these days in talking about electronic health records, but I don’t think the power and urgency of record formats can be conveyed in eight-syllable words. It can be conveyed better by a site that uses data about hospital procedures, costs, and patient satisfaction to help consumers choose a desirable hospital. Or an app that might prevent a million heart attacks and strokes.

Data-wise (or data-ignorant), doctors are stuck in the 1980s, buying proprietary record systems that don’t work together even between different departments in a hospital, or between outpatient clinics and their affiliated hospitals. Now the vendors are responding to pressures from both government and the market by promising interoperability. The federal government has taken this promise as good coin, hoping that vendors will provide windows onto their data. It never really happens. Every baby step toward opening up one field or another requires additional payments to vendors or consultants.

That’s why exchanging patient data (health information exchange) requires a multi-million dollar investment, year after year, and why most HIEs go under. And that’s why the HL7 committee, putatively responsible for defining standards for electronic health records, keeps on putting out new, complicated variations on a long history of formats that were not well enough defined to ensure compatibility among vendors.

The Direct project and perhaps the nascent RHEx RESTful exchange standard will let hospitals exchange the limited types of information that the government forces them to exchange. But it won’t create a platform (as suggested in this PDF slideshow) for the hundreds of applications we need to extract useful data from records. Nor will it open the records to the masses of data we need to start collecting. It remains to be seen whether Accountable Care Organizations, which are the latest reform in U.S. health care and are described in this video, will be able to use current standards to exchange the data that each member institution needs to coordinate care. Shahid Shaw has laid out in glorious detail the elements of open data exchange in health care.

2. Reform will not succeed unless massive amounts of patient data are collected

We aren’t giving patients the most effective treatments because we just don’t know enough about what works. This extends throughout the health care system:

  • We can’t prescribe a drug tailored to the patient because we don’t collect enough data about patients and their reactions to the drug.

  • We can’t be sure drugs are safe and effective because we don’t collect data about how patients fare on those drugs.

  • We don’t see a heart attack or other crisis coming because we don’t track the vital signs of at-risk populations on a daily basis.

  • We don’t make sure patients follow through on treatment plans because we don’t track whether they take their medications and perform their exercises.

  • We don’t target people who need treatment because we don’t keep track of their risk factors.

Some institutions have adopted a holistic approach to health, but as a society there’s a huge amount more that we could do in this area. O’Reilly is hosting a conference called Strata Rx on this subject.

Leaders in the field know what health care providers could accomplish with data. A recent article even advises policy-makers to focus on the data instead of the electronic records. The question is whether providers are technically and organizationally prepped to accept it in such quantities and variety. When doctors and hospitals think they own the patients’ records, they resist putting in anything but their own notes and observations, along with lab results they order. We’ve got to change the concept of ownership, which strikes deep into their culture.

3. Reform will not succeed unless patients are in charge of their records

Doctors are currently acting in isolation, occasionally consulting with the other providers seen by their patients but rarely sharing detailed information. It falls on the patient, or a family advocate, to remember that one drug or treatment interferes with another or to remind treatment centers of follow-up plans. And any data collected by the patient remains confined to scribbled notes or (in the modern Quantified Self equivalent) a web site that’s disconnected from the official records.

Doctors don’t trust patients. They have some good reasons for this: medical records are complicated documents in which a slight rewording or typographical error can change the meaning enough to risk a life. But walling off patients from records doesn’t insulate them against errors: on the contrary, patients catch errors entered by staff all the time. So ultimately it’s better to bring the patient onto the team and educate her. If a problem with records altered by patients–deliberately or through accidental misuse–turns up down the line, digital certificates can be deployed to sign doctor records and output from devices.

The amounts of data we’re talking about get really big fast. Genomic information and radiological images, in particular, can occupy dozens of gigabytes of space. But hospitals are moving to the cloud anyway. Practice Fusion just announced that they serve 150,000 medical practitioners and that “One in four doctors selecting an EHR today chooses Practice Fusion.” So we can just hand over the keys to the patients and storage will grow along with need.

The movement for patient empowerment will take off, as experts in health reform told US government representatives, when patients are in charge of their records. To treat people, doctors will have to ask for the records, and the patients can offer the full range of treatment histories, vital signs, and observations of daily living they’ve collected. Applications will arise that can search the data for patterns and relevant facts.

Once again, the US government is trying to stimulate patient empowerment by requiring doctors to open their records to patients. But most institutions meet the formal requirements by providing portals that patients can log into, the way we can view flight reservations on airlines. We need the patients to become the pilots. We also need to give them the information they need to navigate.

4. Reform will not succeed unless providers conform to practice guidlines

Now that the government is forcing doctors to release informtion about outcomes, patients can start to choose doctors and hospitals that offer the best chances of success. The providers will have to apply more rigor to their activities, using checklists and more, to bring up the scores of the less successful providers. Medicine is both a science and an art, but many lag on the science–that is, doing what has been statistically proven to produce the best likely outcome–even at prestigious institutions.

Patient choice is restricted by arbitrary insurance rules, unfortunately. These also contribute to the utterly crazy difficulty determining what a medical procedure will cost as reported by e-Patient Dave and WBUR radio. Straightening out this problem goes way beyond the doctors and hospitals, and settling on a fair, predictable cost structure will benefit them almost as much as patients and taxpayers. Even some insurers have started to see that the system is reaching a dead-end and are erecting new payment mechanisms.

5. Reform will not succeed unless providers and patients can form partnerships

I’m always talking about technologies and data in my articles, but none of that constitutes health. Just as student testing is a poor model for education, data collection is a poor model for medical care. What patients want is time to talk intensively with their providers about their needs, and providers voice the same desires.

Data and good record keeping can help us use our resources more efficiently and deal with the physician shortage, partly by spreading out jobs among other clinical staff. Computer systems can’t deal with complex and overlapping syndromes, or persuade patients to adopt practices that are good for them. Relationships will always have to be in the forefront. Health IT expert Fred Trotter says, “Time is the gas that makes the relationship go, but the technology should be focused on fuel efficiency.”

Arien Malec, former contractor for the Office of the National Coordinator, used to give a speech about the evolution of medical care. Before the revolution in antibiotics, doctors had few tools to actually cure patients, but they live with the patients in the same community and know their needs through and through. As we’ve improved the science of medicine, we’ve lost that personal connection. Malec argued that better records could help doctors really know their patients again. But conversations are necessary too.

August 08 2012

Technical requirements for coordinating care in an Accountable Care Organization

The concept of an Accountable Care Organization (ACO) reflects modern hopes to improve medicine and cut costs in the health system. Tony MCormick, a pioneer in the integration of health care systems, describes what is needed on the ground to get doctors working together.

Highlights from the full video interview include:

  • What an Accountable Care Organization is. [Discussed at the 00:19 mark]
  • Biggest challenge in forming an ACO. [Discussed at the 01:23 mark]
  • The various types of providers who need to exchange data. [Discussed at the 03:08 mark]
  • Data formats and gaps in the market. [Discussed at the 03:58 mark]
  • Uses for data in ACOs. [Discussed at the 5:39 mark]
  • Problems with current Medicare funding and solutions through ACOs. [Discussed at the 7:50 mark]

You can view the entire conversation in the following video:

July 25 2012

Democratizing data, and other notes from the Open Source convention

There has been enormous talk over the past few years of open data and what it can do for society, but proponents have largely come to admit: data is not democratizing in itself. This topic is hotly debated, and a nice summary of the viewpoints is available in this PDF containing articles by noted experts. At the Open Source convention last week, I thought a lot about the democratizing potential of data and how it could be realized.

Who benefits from data sets

At a high level, large businesses and other well-funded organizations have three natural advantages over the general public in the exploitation of data sets:

  • The resources to gather the data
  • The resources to do the necessary programming to crunch and interpret the data
  • The resources to act on the results

These advantages will probably always exist, but data can be useful to the public too. We have some tricks that can compensate for each of the large institutions’ advantages:

  • Crowdsourcing can create data sets that can help everybody, including the formation of new businesses. OpenStreetMap, an SaaS project based on open source software, is a superb example. Its maps have been built up through years of contributions by people trying to support their communities, and it supports interesting features missing from proprietary map projects, such as tools for laying out bike paths.

  • Data-crunching is where developers, like those at the Open Source convention, come in. Working at non-profits, during week-end challenges, or just on impulse, they can code up the algorithms that make sense of data sets and apps to visualize and accept interaction from people with less technical training.

  • Some apps, such as reports of neighborhood crime or available health facilities, can benefit individuals, but we can really drive progress by joining together in community organizations or other associations that use the data. I saw a fantastic presentation by high school students in the Boston area who demonstrated a correlation between funding for summer jobs programs and lowered homicides in the inner city–and they won more funding from the Massachusetts legislature with that presentation.

Health care track

This year was the third in which the Open Source convention offered a health care track. IT plays a growing role in health care, but a lot of the established institutions are creaking forward slowly, encountering lots of organizational and cultural barriers to making good use of computers. This year our presentations clustered around areas where innovation is most robust: personal tracking, using data behind the scenes to improve care, and international development.

Open source coders Fred Trotter and David Neary gave popular talks about running and tracking one’s achievements. Bob Evans discussed a project named PACO that he started at Google to track productivity by individuals and in groups of people who come together for mutual support, while Anne Wright and Candide Kemmler described the ambitious BodyTrack project. Jason Levitt gave the science of sitting (and how to make it better for you).

In a high-energy presentation, systems developer Shahid Shah described the cornucopia of high-quality, structured data that will be made available when devices are hooked together. “Gigabytes of data is being lost every minute from every patient hooked up to hospital monitors,” he said. DDS, HTTP, and XMPP are among the standards that will make an interconnected device mesh possible. Michael Italia described the promise of genome sequencing and the challenges it raises, including storage requirements and the social impacts of storing sensitive data about people’s propensity for disease. Mohamed ElMallah showed how it was sometimes possible to work around proprietary barriers in electronic health records and use them for research.

Representatives from OpenMRS and IntraHealth international spoke about the difficulties and successes of introducing IT into very poor areas of the world, where systems need to be powered by their own electricity generators. A maintainable project can’t be dropped in by external NGO staff, but must cultivate local experts and take a whole-systems approach. Programmers in Rwanda, for instance, have developed enough expertise by now in OpenMRS to help clinics in neighboring countries install it. Leaders of OSEHRA, which is responsible for improving the Department of Veteran Affairs’ VistA and developing a community around it, spoke to a very engaged audience about their work untangling and regularizing twenty years’ worth of code.

In general, I was pleased with the modest growth of the health care track this year–most session drew about thirty people, and several drew a lot more–and both the energy and the expertise of the people who came. Many attendees play an important role in furthering health IT.

Other thoughts

The Open Source convention reflected much of the buzz surrounding developments in computing. Full-day sessions on OpenStack and Gluster were totally filled. A focus on developing web pages came through in the popularity of talks about HTML5 and jQuery (now a platform all its own, with extensions sprouting in all directions). Perl still has a strong community. A few years ago, Ruby on Rails was the must-learn platform, and knock-off derivatives appeared in almost every other programming language imaginable. Now the Rails paradigm has been eclipsed (at least in the pursuit of learning) by Node.js, which was recently ported to Microsoft platforms, and its imitators.

No two OSCons are the same, but the conference continues to track what matters to developers and IT staff and to attract crowds every year. I enjoyed nearly all the speakers, who often pump excitement into the dryest of technical topics through their own sense of continuing wonder. This is an industry where imagination’s wildest thoughts become everyday products.

Older posts are this way If this message doesn't go away, click anywhere on the page to continue loading posts.
Could not load more posts
Maybe Soup is currently being updated? I'll try again automatically in a few seconds...
Just a second, loading more posts...
You've reached the end.

Don't be the product, buy the product!

Schweinderl