Future of Health IT: Trends and Scenarios

NJIT Researcher Develops New Algorithm Cluster To Data Mine Health Records

“Large collections of electronic patient records have long provided abundant, but under-explored information on the real-world use of medicines. But when used properly these records can provide longitudinal observational data which is perfect for data mining,” Duan said. “Although such records are maintained for patient administration, they could provide a broad range of clinical information for data analysis. A growing interest has been drug safety.”

In this paper, the researchers proposed two novel algorithms—a likelihood ratio model and a Bayesian network model—for adverse drug effect discovery. Although the performance of these two algorithms is comparable to the state-of-the-art algorithm, Bayesian confidence propagation neural network, by combining three works, the researchers say one can get better, more diverse results.

via www.njit.edu

I saw this a few weeks ago, and while I haven't had the time to delve deep into the details of this particular advance, it did at least give me more reason for hope with respect to the big picture of which it is a part.

It brought to mind the controversy over Vioxx starting a dozen or so years ago, documented in a 2004 article in the Cleveland Clinic Journal of Medicine. Vioxx, released in 1999, was a godsend to patients suffering from rheumatoid arthritic pain, but a longitudinal study published in 2000 unexpectedly showed a higher incidence of myocardial infarctions among Vioxx users compared with the former standard-of-care drug, naproxen. Merck, the patent holder, responded that the difference was due to a "protective effect" it attributed to naproxen rather than a causative adverse effect of Vioxx.

One of the sources of empirical evidence that eventually discredited Merck's defense of Vioxx's safety was a pioneering data mining epidemiological study conducted by Graham et al. using the live electronic medical records of 1.4 million Kaiser Permanente of California patients. Their findings were presented first in a poster in 2004 and then in the Lancet in 2005. Two or three other contemporaneous epidemiological studies of smaller non-overlapping populations showed similar results. A rigorous 18-month prospective study of the efficacy of Vioxx's generic form in relieving colon polyps showed an "unanticipated" significant increase in heart attacks among study participants.

Merck's withdrawal of Vioxx was an early victory for Big Data, though it did not win the battle alone. What the controversy did do was demonstrate the power of data mining in live electronic medical records. Graham and his colleagues were able to retrospectively construct what was effectively a clinical trial based on over 2 million patient-years of data. The fact that EMR records are not as rigorously accurate as clinical trial data capture was rendered moot by the huge volume of data analyzed.

Today, the value of Big Data in epidemiology is unquestioned, and the current focus is on developing better analytics and in parallel addressing concerns about patient privacy. The HITECH Act and Obamacare are increasing the rate of electronic biomedical data capture, and improving the utility of such data by requiring the adoption of standardized data structures and controlled vocabularies.

We are witnessing the dawning of an era, and hopefully the start of the transformation of our broken healthcare system into a learning organization.

 

Posted with Blogsy

Related articles

The big-data revolution in US health care: Accelerating value and innovation | McKinsey & Company

Data Mining: So What's the Big Deal?

The big-data revolution in US health care: Accelerating value and innovation | McKinsey & Company

While health-care costs may be paramount in big data’s rise, clinical trends also play a role. Physicians have traditionally used their judgment when making treatment decisions, but in the last few years there has been a move toward evidence-based medicine, which involves systematically reviewing clinical data and making treatment decisions based on the best available information. Aggregating individual data sets into big-data algorithms often provides the most robust evidence, since nuances in subpopulations (such as the presence of patients with gluten allergies) may be so rare that they are not readily apparent in small samples.

via www.mckinsey.com

I found another report on Big Data and healthcare, this time from McKinsey and Company. This report leans in the direction of favoring technology over the personal interactions between patient and physician. I'm still feeling divided. This link goes to an executive summary, but it has a link where you can download the full report.

Blumenthal Suggests Different Paths to MU | healthsystemcio.com

Rather than requiring all eligible providers and hospitals fill out what is generally the same checklist for Meaningful Use, organizations which prove they are achieving outcomes far beyond the norm could qualify right off the bat, suggested National Coordinator for Healthcare IT David Blumenthal, M.D., at the October HIT Policy Committee meeting.

via healthsystemcio.com

HealthSystemCIO's Anthony Guerra posted a brief report suggesting that maybe there will be different ways to meet the Meaningful Use (MU) criteria. Or maybe different criteria, I can't quite tell from his remarks.

Just what every family practitioner needs right now -- more uncertainty about HITECH! It's not surprising that a wait-and-see approach may be the path of the vast majority in the 2011 first round of MU.

We at Cielo are hard at work on activities leading to MU certification, but we are working hardest on meeting a higher standard, Meaningful Usability.

A primary care provider may find that their newfangled IT system gets in the way of delivering quality care at the same time they are purportedly documenting it. That may be Meaningful Use by HITECH standards, but it's not Meaningful Usability. We are on track to deliver a system that improves the quality of the patient encounter in addition to documenting the improvement for HITCH and other P4P/P4R purposes.

Cielo Clinic, Meaningful Use, and ACOs: My New Obsessions

As regular readers probably already know, I've been hiding out for several months now, getting up to speed in my new position as Chief Technology Officer at Cielo MedSolutions LLC. It's a natural next step for me, because Cielo is commercializing a University of Michigan Health System spinoff technology with which I was intimately involved in my previous position as a research informatician.

The spinoff technology was ClinfoTracker, a relatively simple and straightforward prompt and reminder system for primary care providers (PCPs). Now it has evolved into Cielo Clinic™, a clinical quality management system that can dramatically accelerate a practice's ability to participate in pay-for-performance (P4P) and pay-for-reporting (P4R) programs.  Participation in P4P/R programs translates directly into additional revenue for the practice, and it does so by facilitatinbetter quality care through delivery of evidence-based medicine in situ in the PCP-patient encounter.

There are other applications that support P4P/R participation, of course; some of these also provide alerts that are crude equivalents of Cielo Clinic's prompts and reminders. By "crude"

Cielo's compelling advantage stems from its focus on capturing and using clinical data rather than relying on billing data to drive its rules engine.  Rather than rely on ICD-9, the standard for coding problems in the US third-party payer world, Cielo Clinic employs ICPC and ENCODE, which are specifically designed for the primary care setting. Billing data has been shown to be unreliable for quality management in primary care.

Moreover, Cielo Clinic tracks clinician's response to the prompts. This ensures that, for example, if a physician has already advised a patient to undergo a colonoscopy based on a prompt driven by current clinical guidelines for colorectal cancer screening, and the patient refused, that prompt will not reappear for one year (or at a longer or shorter interval of the clinician's choosing, based on their knowledge of the patient).

We've been working on a new product that will soon become manifest in the marketplace, focused in part on the obvious buzzword of the day: Meaningful Use (MU), the benchmark the HITECH Act will use with its implications for direct patient care providers of $44K in incentives to adopt health IT.

However, we see HITECH and MU as blips on the strategic radar. The real opportunity -- and challenge -- in primary care health IT is in the development of Accountable Care Organizations (ACOs).

Lisa Bielamowicz, MD, Managing Director with the Health Care Advisory Board, the research division of The Advisory Board Company (ABC), recently posted a video entitled Keys to Success With Accountable Care Organizations on the MedPulse Business of Medicine newsletter from Medscape (free membership required to access). It's an 8-minute video that gives some good insights into how PCPs, their local hospitals, and the specialist practitioners with whom they collaborate can work together to improve patient care while reducing costs under the aegis of ACOs.

Can Open Source solve the health information integration problem?

I have a vested interest in better health informatics at the primary care level, both because I am a patient and because of my consulting relationship with Cielo Medsolutions LLC. In the current political environment, with its emphasis on throwing money at the problem, I fear for the public health. Bad health IT is worse than no health IT.

How would I define good health IT at the primary care level? I define it in terms of accuracy and completeness.  For your electronic health record (EHR) to be accurate and complete, the information in it must be up-to-date and cover all key facts about the state of your health and the care provided to you. Because many patients have multiple providers, this means that your EHR must be available to all participating care providers, both to read and to update.

Providers often use different EHR systems from disparate vendors, most of whom store data in proprietary formats, and each of whom has a fiduciary responsibility to its shareholders to resist dilution of control over the health information managed by the vendor's software. Moreover, providers belong to different HIPAA covered entities (i.e. custodians of records containing HIPAA-protected health information).

Thus the challenges in achieving a seamlessly integrated health record are daunting, spanning the technical, political, and regulatory realms. Nonetheless, their is a significant push at the Federal level with bipartisan support to achieve health information integration.

Third-party payers have already compelled a degree of standardization with respect to some of the information in the EHR, though the information they need for efficient claims processing is only a subset of what is needed from the care provider perspective. Adequate or no, at least it's a start.

In addition to the provider and vendor challenges, both because providers can make data entry errors and because the patient does not always take the provider's advice, the record must also be available to the patient to read and update. This latter problem is a matter of providing a patient portal to the integrated EHR shared by the providers, and while it presents its challenges, this is an easier problem to solve than getting to the integrated EHR in the first place.

Solving the political challenges, both inter-vendor and at the governmental level, is outside my scope. I do, however, have some insights into the technical challenges to health information integration, in particular the syntactic and semantic obstacles that must be overcome.

Getting information out of proprietary systems is essential to making it available for integration, and there do exist commercial entities who specialize in "cracking" proprietary schemas. Recently, though, I learned of the existence of an Open Source initiative in this arena, which brings me to the interview linked below from opensource.com. In it, Jason Hibbets of Red Hat interviews Matt Mattox of Axial Exchange, a company that provides an Open Source data interchange appliance and sells services related thereto.

I'll provide a taste from the interview, and leave you to read it (or not) without further commentary on my part. I'm still investigating them so I can't provide an opinion of any sort with respect to Axial, but I do have to say I find their business concept highly intriguing.

When you take a system where suppliers create their own demand--which is what happens when physicians both diagnose and treat illness--and combine it with model where a third party picks up most of the fees, costs can rise quickly.

In terms of the care model, the physician practice and acute care hospital were designed in the early 1900s. Medical knowledge has evolved dramatically since then. Today, there are relatively inexpensive ways to treat conditions that a century ago were understood only by their symptoms. We have an opportunity to re-organize our institutions around the state of the science.

These changes won't happen overnight. The first step is to extract data from locked-down proprietary systems so that health information can be made available to the appropriate people at the appropriate times. Once the data has been freed, we can begin to innovate around new care and payment models. Freeing clinical data is the problem we're working on at Axial.

via opensource.com

The Cost of Fear | Why Docs Don't Embrace Technology (Dr. Rob)

I recently read a post on Dr. Rob's Musings of a Distractibel Mind blog on the barriers to adoption among primary care providers and their consultants. I found it very insightful. It opens with a description of an interaction between Dr. Rob and a consultant, in which he offers to exchange information via email and met with silence followed by a polite refusal. He goes on:

This is a typical reaction I get from my colleagues when suggest using the new-fangled communication tool called email.  The palms sweat, the speech stumbles, and the awkwardness is thick in the air.  It’s as if I am suggesting they join me in an evil conspiracy, or as if I am asking them to join my technology nerd cult.  There is a culture of fear in our healthcare system; it’s a wall against change, a current of stubbornness, a root of suspicion that looks at anything from the outside as a danger.  Instead of embracing technology, doctors see it as a tool in the hands of others intent on controlling them.  They see it as a collar on their neck that they only wear because others are stronger than them.

via distractible.org

Email, Fax, and HIPAA

Comments on the blog suggested that the objections might be based in part on security concerns. The consultant may prefer fax over email as a better way to protect patient privacy.

Sadly, many folks think that faxes are somehow encrypted and therefore secure, but they are not. Their advantage over email in this respect is that faxes contain image data, which would be harder to mine for useful information than the plain text of most email. Transmitting HIPAA PHI in either is a violation of the HIPAA Security and Privacy Rules.

There are ways of encrypting both fax and email transmissions. The former requires a commercial product of some sort, the latter either a commercial solution or arcane and cumbersome freeware technologies.

It seems like a better approach would be a shared system that uses HTTPS for all communication. GMail can do this, and HTTPS is now GMail's default transport layer for its user interface, but whether or not communication with any remote mail system is secure is situation-dependent and opaque to the sender and receiver. It is unclear whether the GMail databases are HIPAA Security compliant. Our Health System uses Groupwise for internal communications, which is encrypted both in transport and storage, with all storage maintained inside the data centers and behind the firewalls of the covered entity.

PHR systems like Google Health and Microsoft HealthVault offer another alternative. In both cases the information is "owned" by the patient, who must grant access explicitly to others; all inter-system communication over public channels is encrypted. DOD's MiCARE system (http://bit.ly/dlz2iW) interfaces with both PHRs, providing relatively painless and secure sharing of health information between and among primary, secondary, and tertiary care providers, consulting clinicians, and non-clinical care providers. The only catch is that the patient must trust the MiCARE system to identify, authenticate and authorize external systems that need to read from or write to the PHR.

Whether Google Health and HealthVault are truly secure is an open question. I have found no explicit assertion from either that their back-end databases are encrypted, though both employ extensive physical and administrative controls at their data centers. Not providing any details of their technical controls (e.g. encryption of databases) is probably wise, since any information at all would be potentially useful to hackers. Still, an assertion that the back-end database are encrypted would be appreciated by patients and by liability-sensitive providers accessing their systems.

The Real Issue

All that said, the most substantive objections to the use of email in the minds of healthcare providers are probably social and psychological rather than legal or technical. Use of email may be perceived as a slippery slope to being lured or compelled into more extensive IT adoption. Primary care physicians in particular are late adopters of technology, and with the lack of emphasis on usability in many systems currently available, it is difficult to blame them for their reluctance in this regard.

I recently sat through a vituperative diatribe from a family physician whose employer adopted one of the major EMR provider's systems over a year ago, and she stated that the system actively interfered with her ability to provide care. Her objections were multiple, but most prominent were twofold.

First, the system demanded excessive navigation due to inflexible and poorly designed user experience design and information architecture, leading to severe reduction of direct contact with the patient and broken concentration. Second, the system overwhelmed her with prompts and reminders she had long since determined were irrelevant for a given patient. The system provided no way to suppress them, which she was told was due to liability issues.

Another physician I overheard in the YMCA locker room was lamenting the fact that computerization had led to a requirement that he spend more than half of what had previously been his lamentably small amount of free time on nights and weekends updating the EMR. This was in his view better than attempting to use the EMR system in situ.

I know there are many success stories in primary care EMR adoption. Dr. Rob is one of them, and I personally know of a number of others, including my own family physician. The Federal initiative to computerize primary care is laudable, even though the road ahead will be rocky for some time to come.

Hopefully the systems that end up dominating the primary care EMR marketplace will succeed based on usability, quality, and workflow flexibility rather than on company name. The enterprise-system vendor offerings in the primary care arena tend to be dumbed-down, check-the-box knockoffs whose designers seem oblivious to the unique and highly variable requirements of primary care clinics and practices. Which vendor(s) will succeed, and on what basis, and with what ultimate effect on the public health, only time will tell.

Personal Tech: Medical Apps for the iPhone

From NY Times Personal Tech: Medical Apps for the iPhone

After a lot of time reading "best medical apps" stories online, asking Twitter users for their suggestions and reading online reviews, I finally boiled the list down to about 50 promising apps. I tried them out and further winnowed the list to a bunch that I ultimately demo'ed in my talk. Eventually, the video of the talk will be posted at ted.com/talks, but in the meantime, here's what I covered.

(I haven't really given them full-blown testing, so read the online reviews before you spend good money on them. Except for the free ones--you've got nothing to lose!)
--Dave Pogue

I read David Pogue's personal tech blog at the NY Times to keep up on consumer IT trends, but this post from a couple weeks ago seemed really relevant to the readers of FutureHIT. I've been putting off posting because I wanted to say something eloquent, but work and home life have made that impossible. I'll settle for a few hints at what I believe are the most interesting among the items Pogue lists. I'm focused on the ones targeted at health professionals, but the consumer tools have a lot of potential as well.

• OsiriX. "An amazing viewer of medical images (X-rays, scans of all sort)".  I think this is probably just a DICOM viewer, but it requires special server software, so it may be adding some value. Regardless, it's very cool.
• AirStrip OB. "Lets an obstetrician monitor a patient’s status, right down to the baby’s heartbeat, from elsewhere in the hospital (or the town)."  As Pogue points out, this is a good pointer at the types of remote monitoring applications we can expect to see as ubiquitous/pervasive computing moves into the mainstream.

Actually I will mention a thought I've had about one of the consumer apps...

• Retina. "It’s for color-blind people like me. You hold it in front of something—clothes in your closet, for example—and it tells you by name what color you’re seeing."  This is an examplary augmented reality application, intriguing not so much for what it does -- which is of great value, I don't mean to denigrate it -- but for what it portends.  As image analysis becomes more sophisticated, it's easy to picture diagnostic tools that will look at the patient in visible light and infrared and point out diagnostic signs the clinician might overlook. A more prosaic application not yet built but within the reach of current technology would be a program that "looks" at the patient and points out relevant facts and decision guidelines based on the part of the patient's body on which the phone's camera is focused.

I think all this is intimately related to the technology I spotlighted in my recent post on the Open Data Kit, which is aimed at moving advanced tech for the clinician into community settings. As I said in that post, these types of tools will serve the developed world as well as the developing world, because even in the most advanced economies there are segments of the population that are underserved because they can't or won't go to a traditional healthcare provider setting.

There are challenges in all this that take some of the rosy glow out of the picture, notably patient privacy and truth maintenance, i.e. making sure the various information stores relied on by the remote devices have the most up to date information, and can update it as well. In addition there is the very real concern I feel as a patient that healthcare providers may become overly dependent on distributed computing and communications technologies, and be at a loss when connections break down (and they will, oh yes, they will).

Nonetheless, on balance the future for these technologies is bright and getting brighter, and the value they add is potentially enormous.

Wiser OWL learns to unravel doctor talk (The University of Manchester)

I saw a really good news bit today, actually two days old but that's how far behind I am on non-critical email:

A good example of the scale of the problem facing medics and computer scientists is the NCI Cancer Thesaurus that has swollen from 20,000 medical terms in 2004 to over 50,000 terms today.

As new terms are being added all the time, ensuring that all these terms are described, updated and linked together correctly is a mammoth task for humans. However, by using OWL 2 definitions can be written in such a way that computer programs can tirelessly update these terms, enriching the structure of the Thesaurus and pointing out where there are errors.
 
"The first stage was writing the NCI Thesaurus in the original version of the language, OWL, but now OWL 2 enables computer programs to interpret these terms in a much more human-like way, for instance reasoning that if a fracture is located on a bone which is part of a leg then that fracture is a fracture of that leg," said Bijan Parsia of the University of Manchester’s School of Computer Science.

via www.manchester.ac.uk

I can't write more about it now, but it's a critical step in the right direction for the evolution of the Semantic Web. Some maintain it hasn't even been born yet, much less started to evolve. There's an element of truth in that, but it's a sign of the change in our sense of time that we would expect something as complex as the Semantic Web to  move along more quickly than it has so far. Kudos to the folks at Manchester and Oxford who made this manifest earlier this week.

Driven to Distraction - At 60 M.P.H., Office Work Is a High-Risk Job - Series - NYTimes.com

On Wednesday, the Transportation secretary, Ray LaHood, called the broader phenomenon of distracted driving a “deadly epidemic” at a meeting on the issue in Washington. Real estate brokers, pharmaceutical sales people, entrepreneurs, marketers and others say they have little choice but to transform their cars into cubicles. In this merciless economy, they say, they have to make every minute count, and respond instantly to opportunities and challenges.

And they argue that the convenience of constant contact — and the chance to tick off items from an endless to-do list while driving — far outweigh what they think are slim chances that it could lead to a wreck.

via www.nytimes.com

The NY Times has been running a series on the perils of multi-tasking while driving. Today's installment highlights how work pressures, often self-imposed in the case of knowledge workers, are causing people to kill themselves as well as innocent bystanders through stupid mistakes made while trying to be on the telephone, send email, and drive all at the same time (or similar combinations of ICT activities).

It may be that in our culture, this pattern of behavior is Darwinian natural selection at work, though the loss of innocent bystanders doesn't quite fit the pattern. It does represent a continuation of the obliviousness we feel with respect to the dangers of multitasking. In addition to this kind of life-threatening danger, there are less obvious but more pervasive effects. In a paper published earlier this year in PNAS Early Edition, "Cognitive control in media multitaskers", Ophir and colleagues described a controlled behavioral trial in which they showed that media multitasking degrades personal productivity and effectiveness:

A trait media multitasking index was developed to identify groups of heavy and light media multitaskers. These two groups were then compared along established cognitive control dimensions. Results showed that heavy media multitaskers are more susceptible to interference from irrelevant environmental stimuli and from irrelevant representations in memory. This led to the surprising result that heavy media multitaskers performed worse on a test of task-switching ability, likely due to reduced ability to filter out interference from the irrelevant task set.

In all likelihood, many of us in the knowledge business will be as oblivious to this evidence as we have been to the numerous past studies of the dangers of using cell phones while driving. Sad, but true, I fear.

BBC NEWS | Virtual health care gets UK trial

You can read about the Aberdeen Royal Infirmary's venture into the brave new world of virtual healthcare in the  BBC News article entitled Virtual health care gets UK trial.Here's a taste:

Cutting edge telemedicine technology, that will allow medical staff to offer "virtual" health care, is being trialled at Aberdeen Royal Infirmary.

HealthPresence, a system developed by Cisco, links up doctors with patients through a video conferencing booth.

Blood pressure, temperature, pulse rate, weight and lung function can be assessed at a distance in the booth if patients can not make appointments.

If the trial is successful, booths may be set up in locations across the UK.

Possible future locations for the mobile health suite could include schools, workplaces, shopping centres and even people's homes.

(picture from BBC news story)

This trial uses kiosks manned by a human attendant; the kiosk can administer simple diagnostic tests, in addition to providing audiovisual teleconferencing. The presence of the human attendant goes a long ways toward allaying my fears about patient data security.

While not exactly a groundbreaking innovative concept, the Aberdeen trial is one of the first uses of rich Internet-based telecommunications media in the mundane world of primary care. I'm excited to see it, especially on behalf of my less well-off rural relatives and friends who currently have limited access to high-quality healthcare.

Now, if we could only get them health insurance coverage... :-)