Search the KHIT Blog

Tuesday, August 26, 2014

On "Big Data," research ethics, (and just "too much data")

"No human being on this planet can keep up with the literature."

Tangentially apropos,
It is in vain to expect any great progress in the sciences by the superinducing or engrafting new matters upon old. An instauration must be made from the very foundations, if we do not wish to revolve forever in a circle, making only some slight and contemptible progress.

-Francis Bacon
A culture of denial subverts the health care system from its foundation. The foundation—the basis for deciding what care each patient individually needs—is connecting patient data to medical knowledge. That foundation, and the processes of care resting upon it, are built by the fallible minds of physicians. A new,  secure foundation requires two elements external to the mind: electronic information tools and standards of care for managing clinical information.

Electronic information tools are now widely discussed, but the tools depend on standards of care that are still widely ignored. The necessary standards for managing clinical information are analogous to accounting standards for managing financial information...

This pervasive disorder begins at the system’s foundation. Contrary to what the public is asked to believe, physicians are not educated to connect patient data with medical knowledge safely and effectively. Rather than building that secure foundation for decisions, physicians are educated to do the opposite—to rely on personal knowledge and judgment—in denial of the need for external standards and tools. Medical decision making thus lacks the order, transparency and power that enforcing external standards and tools would bring about.

A simple example will illustrate medicine’s missing foundation. Consider a person with chest pain. Careful review of the literature shows that a practitioner investigating this symptom needs to take into account approximately 100 diagnostic possibilities, involving most medical specialties. Each diagnostic possibility is definable as a combination of simple,inexpensive findings from the history, physical and basic laboratory tests. Checking all of the findings for all of the diagnostic possibilities results in approximately 440 findings on each patient. Each positive finding suggests one or more of the diagnostic possibilities. Each patient’s particular combination of positive findings can be matched against all of the combinations of findings representing the diagnostic possibilities for chest pain. The output of this matching process is an individualized set of diagnostic possibilities, plus the patient’s positive and negative findings for each. These findings constitute initial evidence for and against each possibility. The total set of possibilities (i.e. those for which at least one positive finding is made) represents the diagnoses worth considering for that patient. External tools generate this output by simple matching, without dependence on the fallible minds of costly physicians. The tools distill this output from the accumulated experience of countless patients and practitioners—experience that would be otherwise lost.
This meticulous matching process is feasible only with software tools. The minds of physicians do not have command of all the medical knowledge involved. Nor do physicians have the time to carry out the intricate matching of hundreds of findings on the patient with all the medical knowledge relevant to interpreting those findings. External tools are thus essential. But the tools are trustworthy only when their design and use conform to rigorous standards of care for managing clinical information...
Medical practice is thus trapped in a subjective realm. Unlike scientific practitioners, medical practitioners do not operate in an objective realm, where the contents of thought and knowledge exist independently of the individual mind, a realm where knowledge can be reliably transmitted and applied, where new knowledge can be rapidly translated into practice, where all knowledge can be tested against patient realities. Isolated from this objective realm, the mind becomes a negative force, a cause of confusion and disorder. Physicians are not equipped to fulfill their immense responsibility safely and effectively. Other practitioners are not equipped to share that responsibility with physicians. Patients are not equipped to work effectively with multiple practitioners, nor to assume the ultimate burden of decision making over their own bodies and minds. Third parties are not equipped to create order out of this chaos. Practitioners and patients are not accountable for their own behaviors, while third parties are left free to manipulate disorder for their own advantage.
In short, essential standards of care, information tools and feedback mechanisms are missing from the marketplace. These missing elements are in large part already developed. Yet, the underlying medical culture does not even recognize their absence. This does not prevent some practitioners from becoming virtuoso performers in narrow specialties or skills. But their virtuosity is personal, not systemic, and limited, not comprehensive. Missing is a total system for enforcing high quality care by all practitioners for all patients...
That's from the opening pages of the Weeds' seminal book on medicine and health IT, "Medicine in Denial." I could not recommend it more highly, though I know full well that some physicians will bristle at its core argument. to wit, one of my THCB comment responses.

Not yet available in Kindle/eBook format.


Another interesting related observation:
"Just when we are starting to have some impact, for example, ideologically motivated pseudoskeptics try to steal the mantle of skepticism to deny established science. Social media has also been a double-edged sword. It has greatly expanded our reach, but unfamiliarity with the medium and a lack of filters has also exposed some poorly considered and unflattering opinions among some science promoters.

A lot of ideological opinion is getting mixed in with the science, and this can be divisive and distracting..."
From The Neurologica Blog, Scientific Literacy.

Given Time, 'Big Data' Promises to Transform Patient Care

August 27, 2014 11:28 am Michael Laff – With limited time and a heavy patient load, physicians face a daunting task trying to identify a patient's multiple needs during a single office visit.

Now, growing implementation of electronic health records (EHRs) and other health information technology, combined with rapidly evolving clinical analytics techniques, promises to make this task easier. By collecting and analyzing data that present a more comprehensive, detailed medical picture of entire patient populations, physician practices can monitor their patient panels more efficiently -- often without scheduling additional office visits.

"Big data" in health care refers to a wide-ranging combination of clinical, genetic and genomic, outcomes, claims, social and other data that is collected from multiple sources. Bringing diverse sets of data together will allow physicians to use predictive analytics and identify patients who are, for example, most likely to be "high-cost" -- that is, frequent utilizers of costly health care services.

AAFP News recently reached out to David Bates, M.D., to discuss how physicians can use big data to anticipate patient needs. A general internist, Bates is a professor and chief of the Division of General Medicine at Brigham and Women's Hospital in Boston, as well as a professor in the Department of Health Policy and Management at Harvard Medical School. He has written widely on the use of technology in health care, most recently as co-author of an article on big data( published last month in Health Affairs...
One hopes. But, problems and barriers will dog the utility of "Big Data."

From Science Based Medicine:
Bad Science Journals
Posted by Steven Novella on August 27, 2014

It’s an excellent business model. The only real infrastructure you need is a website, and you can have a custom site made for 5-10 thousand. Then you just have the monthly bandwidth charges. The rest is just e-marketing, which can be done for free, or the cost of some e-mails lists. After that, the money just comes rolling in.

The best part is that other people do all the actual work. All you have to do is charge them for publishing on your open-access online journal.

What you are selling is essentially scientific/academic fraud.

Unfortunately, this is a good business model, even though it is a terrible scientific model, and so it has proliferated. We may be living in the heyday of dubious open-access scientific journals...
Great post. Read all of it.

Pulse Systems Publishes Free eBook About Meaningful Use
eBook Teaches Eligible Professionals How to Attest for Meaningful Use and Earn Financial Incentives From CMS
Free with cursory registration. Not bad. Nice graphic renderings, good content. 130 pages.


HSPC Incorporates, Gears Up to Tackle Interoperability Problem

The Healthcare Services Platform Consortium, a group of providers, IT vendors, system integrators and venture-led firms dedicated to solving the industry-wide interoperability problem, has filed for incorporation in the State of Delaware as a first step to gaining legitimacy as an organization...

There are three levels of health IT interoperability: foundational, structural, and semantic. Of the three, semantic interoperability--which relies on a Services Oriented Architecture (SOA)—provides the highest level of interoperability, namely the ability of two or more systems or elements to exchange information and to use the information that has been exchanged taking advantage of both the structuring of the data exchange and the codification of the data including vocabulary so that the receiving IT systems can interpret the data.

This level of interoperability supports the electronic exchange of patient summary information among caregivers and other authorized parties via potentially disparate EHR systems and other systems to improve quality, safety, efficiency, and efficacy of healthcare delivery. According to HSPC, this services orientation will allow the healthcare industry to “transcend conventional clinical-data operations to enable software application developers to respond to events across disparate information systems, seamlessly aggregate data from both new and legacy systems, deliver advanced clinical decision support with data analytics, and support business process interoperability.”...
How about a dad-gumbed Data Dictionary Standard? Instead of / in addition to 36 pages of nicely rendered Interoperababble (pdf).

More to come...

No comments:

Post a Comment